Hao Zhang

All Publications

• Dosimetric and treatment efficiency comparison of lung SBRT using three different motion management strategies. Clinical and translational radiation oncology Lansing, T., Harris, W., Yu, M., Cheema, Z., He, X., Fu, Y., Lee, S. K., Cervino, L., Li, T., Li, X., Moran, J., Mueller, B., Gelblum, D., Berry, S., Zhang, H. 2026; 56: 101044

  Abstract

  To compare the dosimetry and treatment efficiency of lung stereotactic body radiation therapy (SBRT) using the deep inspiration breath hold (DIBH), free breathing (FB), and respiratory gating (RG) strategies.308 lung SBRT patients with middle to lower zone lung tumors were included in this retrospective study. The prescriptions were 1000 cGy x 5 fractions, 1200 cGy x 4 fractions, or 1800 cGy x 3 fractions. They were all treated with a volumetric modulated arc therapy (VMAT) technique and 6 MV flattening filter free (FFF) beam on C-arm linear accelerators, but using different motion management strategies (151 DIBH, 136 FB, 21 RG). The lung dose (mean lung dose (MLD), V5, V20) and treatment time (on table, imaging & verification, delivery) of these patients were retrospectively collected for statistical comparison.The average doses (MLD, V5, V20) to the ipsilateral lung were 408.2 cGy, 20.1 %, 5.7 % for the DIBH cohort, 569.8 cGy, 27.6 %, 8.4 % for the FB cohort, and 519.6 cGy, 23.5 %, 7.5 % for the RG patients. Correspondingly, the average time (on table/imaging & verification/delivery) for the three patient cohorts was 22.3/16.0/6.3 min, 13.6/10.5/3.1 min, and 22.7/14.6/8.1 min, respectively.Quantitative comparison of lung dose and treatment efficiency for three commonly used motion management strategies in lung SBRT is reported. While the relative advantages and disadvantages of these strategies are well recognized, our findings further confirm these differences and provide clinicians with quantitative data to support informed decision-making in clinical practice.

  View details for DOI 10.1016/j.ctro.2025.101044

  View details for PubMedID 40994620

  View details for PubMedCentralID PMC12454274

• Dynamic cone beam CT reconstruction via spatiotemporal Gaussian neural representation. Medical physics Fu, Y., Zhang, H., Cai, W., Xie, H., Kuo, L., Cervino, L., Moran, J., Li, X., Li, T. 2025; 52 (11): e70127

  Abstract

  In image-guided radiotherapy (IGRT), four-dimensional cone-beam computed tomography (4D-CBCT) is critical for assessing tumor motion during a patient's breathing cycle prior to beam delivery. However, generating 4D-CBCT images with sufficient quality requires significantly more projection images than a standard 3D-CBCT scan, leading to extended scanning times and increased imaging dose to the patient.To introduce a novel spatiotemporal Gaussian neural representation framework to reconstruct high-temporal dynamic CBCT images from 1-minute acquisition, preserving motion dynamics and fine spatial details without relying on prior images or motion models.Our framework employs a differentiable 4D Gaussian representation initialized from average CBCT images. Gaussian points are characterized by position, covariance, rotation, and density, offering a compact and dynamic model for CBCT scenes. A Gaussian deformation network, incorporating a HexPlane encoder and multi-head decoder, predicts Gaussian deformations to minimize L1 and structural similarity index measure (SSIM) losses between rendered and measured projections. Adaptive Gaussian control refines the representation by pruning underutilized Gaussians and densifying points in high-gradient regions. The method was benchmarked on the AAPM SPARE challenge datasets and further validated with clinical CBCT scans from a Varian TrueBeam system. For the AAPM SPARE challenge datasets, the performance of the proposed method was evaluated using the root-mean-squared-error (RMSE) and the structural similarity index (SSIM) in the four regions of interest: Body, Lung, PTV, and Bone. The geometric accuracy was evaluated by calculating the registration error when aligning the tumor to the ground truth using the Elastix package, focusing on pixels within the planning target volume (PTV). To demonstrate our method's capability in high-temporal motion dynamic modeling using extremely undersampled projections, the clinical half-fan projections from a 1-minute Varian TrueBeam acquisition were sorted into 50 phases with approximately 18 projections per phase, significantly finer than the commonly used 10-phase binning.Compared to the AAPM SPARE challenge participant methods, our method achieved superior geometric accuracy in terms of PTV alignment error, and comparable RMSE and SSIM when no prior 4DCT or motion model is used for our reconstruction. For PTV alignment, our method achieved translational and rotational errors of 0.54 mm (LR), 0.76 mm (SI), 1.36 mm (AP), 0.55° (rAP), and 0.93° (rSI), and 1.31° (rLR), respectively. For high temporal dynamic CBCT reconstruction, our method successfully reconstructed a 50-phase CBCT from a 1-minute Varian Truebeam half-fan scan, demonstrating effective streak artifact suppression, respiratory motion preservation, and fine detail restoration. Reconstruction on a single NVIDIA RTX A6000 GPU required approximately 30-80 min, depending on the number of Gaussian points used (ranging from 50 to 400K), to reconstruct CBCT from 680 projections acquired with a 30 × 40 cm detector. Our code and reconstruction results can be found at: https://github.com/fuyabo/4DGS_for_4DCBCT/tree/main.The spatiotemporal Gaussian framework is a novel data-driven dynamic CBCT reconstruction technique that features excellent geometric accuracy in terms of PTV alignment and high-temporal motion modeling, indicating promise for tumor motion assessment and high-temporal respiratory motion modeling based on a 1-minute half-fan scan prior to beam delivery.

  View details for DOI 10.1002/mp.70127

  View details for PubMedID 41188011

• Next-generation nonstop gated CBCT for respiratory gating lung radiotherapy: Scan time and imaging dose. Medical physics He, X., Yu, M., Berry, S., Gao, Y., Fu, Y., Harris, W., Cai, W., Erdi, Y., Stiles, K., Lynch, D., Lim, S. B., Cervino, L., Li, T., Li, X., Moran, J., Zhang, H. 2025; 52 (10): e70065

  Abstract

  Free-breathing gated CBCT (gCBCT) is commonly prescribed for lung cancer patients undergoing respiratory gating radiotherapy. Recently, the nonstop gated CBCT (ngCBCT) has been proposed to significantly reduce scanning time and imaging dose while preserving high image quality.To implement the novel ngCBCT imaging technique on a C-arm linear accelerator (LINAC) and quantitatively compare its scan time and imaging dose with those of the current clinical gCBCT.ngCBCT was implemented via a customized XML file in the developer mode of a C-arm LINAC, while gCBCT was acquired in the clinical mode. Both techniques employed the same thorax imaging protocol (half fan, full trajectory). Scan times were calculated from the timestamps of acquired projection data. Imaging dose was characterized using the weighted Cone-Beam Dose Index (CBDIw), measured with a standard CTDI body phantom and two pencil chambers placed centrally and peripherally. Respiratory motion was simulated using a CIRS motion platform with both Cos4 waveforms (3-6 s cycles) and seven clinical patient breathing traces. Gating duty cycles of 30%-60% were tested for Cos4 motion, while the same gating window was reproduced for each patient's breathing trace.Scan times for gCBCT ranged from 1.8 to 5 min, influenced by the gating duty cycle, breathing period, and waveform periodicity. In contrast, ngCBCT consistently achieved scan times of approximately 1 min. The imaging dose (CBDIw) for ngCBCT was reduced to 26.7%-60.1% of that for gCBCT, closely matching the respective gating duty cycles.This study demonstrates that ngCBCT acquisition is feasible on C-arm LINAC and offers substantial improvements in scan time and dose reduction compared to current clinical gCBCT. This novel technique has the potential to enhance patient comfort and broaden access to respiratory gating radiotherapy.

  View details for DOI 10.1002/mp.70065

  View details for PubMedID 41058469

• Nonstop gated CBCT for respiratory gating lung SBRT: A feasibility study. Medical physics Yu, M., Berry, S., Fu, Y., Harris, W., Cai, W., Ziegenfus, M., Xie, H., Wang, A., Gelblum, D., Mueller, B., Cervino, L., Li, T., Li, X., Moran, J., Zhang, H. 2025; 52 (9): e18084

  Abstract

  Free-breathing gated cone-beam computed tomography (gCBCT), which captures a specific anatomy coinciding with a preset gating window in the breathing cycle, is routinely prescribed to gating lung SBRT patients for pretreatment setup verification. However, a half-fan gCBCT scan can take 2-8 min (for a typical gating duty cycle of 30%-60% and patient breathing period of 3-6 s) on a C-arm linear accelerator because the gantry movement is interrupted and resumed by the respiratory gating signal multiple times over the scan. The long scan time increases patient on-table time, leading to discomfort and a higher likelihood of patient movement. Meanwhile, extra kV projections are acquired while the gantry is accelerating for the gCBCT scan, resulting in a higher imaging dose compared to 3D CBCT.To investigate the feasibility of a novel imaging paradigm named "nonstop gated CBCT (ngCBCT)" that improves upon current clinical gCBCT by substantially reducing the scan time and imaging dose while retaining high-quality images.The ngCBCT is implemented by allowing the gantry to rotate continuously, with the kV x-ray beam activated only when the breathing signal falls within the preset gating window. Raw gCBCT projections of two gating lung SBRT patients were retrospectively retrieved and intentionally sampled based on each patient's breathing cycle to emulate the ngCBCT acquisitions. The datasets include both half-fan and full-fan acquisitions, representing the primary clinical scan geometries. Three reconstruction algorithms-Feldkamp-Davis-Kress (FDK), penalized likelihood iterative reconstruction (PL), and prior-image-based iterative reconstruction (PIBR)-were applied to these ngCBCT emulations to evaluate reconstruction performances on the non-uniform and under-sampled projections resulting from this acquisition strategy.The FDK reconstructions of ngCBCT are degraded with streak artifacts and have insufficient quality for clinical use. While PL yields improved reconstructions over FDK, the PIBR method consistently delivers the best visual and quantitative results with the aid of patient-specific prior images.The proposed ngCBCT technique addresses the key limitations of current clinical gCBCT by substantially reducing data acquisition time and imaging dose. The ngCBCT with PIBR achieves adequate image quality and offers a promising opportunity for pretreatment setup verification in gating lung SBRT.

  View details for DOI 10.1002/mp.18084

  View details for PubMedID 40891133

• Super-resolution CBCT on a new generation flat panel imager of a C-arm gantry linear accelerator. Medical physics Kuo, L., Li, F., Fu, Y., Zhang, H., Cervino, L. A., Moran, J. M., Li, X., Li, T. 2025; 52 (7): e18000

  Abstract

  Kilovoltage cone-beam computed tomography (kV CBCT) is vital for image-guided radiotherapy (IGRT). The new RTI4343iL panel on the Varian TrueBeam LINAC offers higher resolution but requires binning to achieve practical frame rates, leading to projection resolution loss. Existing super-resolution (SR) techniques have been applied to enhance CBCT image quality but primarily operate in the image domain, struggling to restore resolution loss in the projection domain.This study aimed to evaluate the feasibility of a deep learning (DL) SR model, based on a conditional Generative Adversarial Networks (cGANs) architecture, for enhancing the spatial resolution of CBCT acquired with the new RTI4343iL panel in the projection domain. We hypothesize that projection-domain deblurring will primarily depend on the detector and minimally on patient anatomy, enhancing primary signal resolution without significantly altering scatter distribution. The study quantitatively assessed the impact of SR-enhanced projections on the quality of reconstructed CBCT images.A DLSR model was developed to enhance CBCT resolution in the projection domain.  For data acquisition, a Varian TrueBeam system equipped with the RTI4343iL panel was used, which features a native high-resolution image size of 2848 × 2144 pixels, but operates in 2 × 8 binning mode (1424 × 268 pixels) during CBCT scans to mitigate data readout speed limitations. Following thorax CBCT protocols, 576 pairs of CBCT projections were acquired at two resolutions using Rando, Longman, and Steeve phantoms. Of these, 460 pairs were allocated for model training, while 116 were reserved for validation. Model testing involved 144 Dynamic Thorax projections and CBCT reconstructions utilizing Catphan 604 phantoms. The DL SR model was built on a cGANs framework with a U-Net generator. Image enhancement was quantitatively evaluated with metrics including peak signal-to-noise ratio (PSNR), mean square error (MSE), structural similarity index measure (SSIM), feature similarity index measure (FSIM), and mean absolute percentage error (MAPE).The DL SR model effectively enhanced image resolution, producing SR projections with greater detail and improved structural clarity. Quantitative analysis showed that the SR-enhanced projections outperformed upscaled low-resolution (LR) projections with higher PSNR (44.4 vs. 43.7, p < 0.001), lower MSE (187,083.7 vs. 205,364.4, p < 0.001), and improved MAPE (7.6% vs. 13.5%, p < 0.001). While SSIM and FSIM values were similar for both methods, the SR-enhanced projections demonstrated a slight advantage, achieving an FSIM of 0.998. Reconstructed CBCT images from SR-enhanced projections exhibited improved spatial resolution as well, increasing from 0.6 lp/mm to 0.9 lp/mm on the Catphan 604 phantom image. Enhanced structural detail and sharper intensity profiles in SR CBCT images further validated the model's potential to restore resolution lost during the acquisition process.This study underscores the efficacy of a projection-domain DL SR method for CBCT enhancement. The developed model presents a promising avenue for attaining high-resolution CBCT, potentially benefiting for many clinical applications.

  View details for DOI 10.1002/mp.18000

  View details for PubMedID 40665524

  View details for PubMedCentralID PMC12270334

• Evaluation of model uncertainty in AI-based synthetic CT generation from CBCT for abdominal adaptive radiotherapy. Medical physics Quintero, P., Cerviño, L., Zhang, H., Harris, W. 2025; 52 (6): 4054-4067

  Abstract

  The synthesis of CT from CBCT images using AI methods has been explored in radiotherapy to improve adaptive workflows. However, the model training process can be particularly challenging for the abdominal region due to dataset disparities between CT and CBCT images caused by organ motion, low soft tissue contrast, and inconsistencies in air volumes. These factors might impact the implicit prediction uncertainties, which are not actively considered on the synthetized images, overlooking poorly predicted image regions that might lead to inaccuracies in the dose calculation.To evaluate the impact of the model uncertainty on the predicted Hounsfield Units (HU) and dose calculation on synthetic CT (sCT) for abdominal patients.CBCT images from 65 abdominal patients were retrospectively used to generate sCT images. Rigid image registration (RIR) and deformable image registration (DIR) were individually implemented to create two datasets (D1 and D2) to train (80%), validate (10%), and test (10%) three models (M1: Unet, M2: Bayes-Unet, M3: cycle-GAN). Treatment plans were made on the ground truth CT (GTCT) and the sCTs for dose calculation comparison. The model performance was evaluated with mean absolute error (MAE) and root mean square error (RMSE), and the sCT quality was verified with structural similarity index measure (SSIM). Gamma index (2%/2  mm), D95% of PTV, and Dmean of liver were evaluated and compared between the plans calculated on the GTCT and the sCT. The voxel-wise uncertainty map for M1 and M3 were generated by calculating the standard variation of each voxel from training the model independently ten times. For M2 the Monte Carlo DropConnect method was implemented with 100 iterations. Finally, the uncertainty was associated with the accuracy of CT numbers and dose calculation.Across the three models {M1, M2, M3} trained with D1 and D2, the MAE were {50.9 ± 13.3} and {40.9 ± 11.5}, respectively, the RMSE were {68.3 ± 13.5} and {62.2 ± 10.7}, respectively, and the SSIM were {0.89 ± 0.05} and {0.94 ± 0.05}, respectively. For D1 and D2, the gamma rates were {96.3 ± 1.04} and {97.3 ± 0.2}, respectively. No major differences in DVH were noticed between GTCT and sCT (p < 00.1). The correlation between the whole sCT uncertainty maps and gamma index was statistically significant (Spearman's coefficient = 0.84, p < 0.001) and weak between the target volume uncertainty and gamma index (Spearman's coefficient = 0.01, p = 0.89).Using DIR resulted in improved performance across all three models. Metrics used to evaluate synthetic image accuracy might not reflect the uncertainty implications in image quality and dose calculations, which suggests the benefit of displaying uncertainty errors in AI generated sCT as a potential strategy to improve the evaluation of intra-fraction changes used for adaptive abdominal radiotherapy.

  View details for DOI 10.1002/mp.17721

  View details for PubMedID 40012107

• Real-time 3D synthetic MRI based on kV imaging for motion monitoring of abdominal radiotherapy in a conventional LINAC. Physics in medicine and biology Quintero, P., Wu, C., Zhang, H., Otazo, R., Cerviño, L., Harrys, W. 2025; 70 (7)

  Abstract

  Introduction.Real-time 2D-kV-triggered images used to evaluate intra-fraction motion during abdominal radiotherapy only provides 2D information with poor soft-tissue contrast. The main goal of this research is to evaluate a novel method that generates synthetic 3D-MRI from single 2D-kV images for online motion monitoring in abdominal radiotherapy.Methods.Deformable image registration (DIR) is performed between one 4D-MRI reference phase and all other phases, and principal-component-analysis (PCA) is implemented on their respective deformation vectors. By sampling 1000 times the PCA eigenvalues and applying the new deformations over a reference CT, 1000 digital reconstructed radiographs (DRRs) were generated to train a convolutional neural network to predict their respective eigenvalues. The method was implemented and tested using a digital phantom (XCAT) and an MRI-compatible phantom (ZEUS) with five DRR angles (0°, 45°, 90°, 135°, 180°). Seven motion scenarios were tested. For model performance, mean absolute error (MAE) and root mean square error (RMSE) were reported. Image quality was evaluated with structure similarity index (SSIM) and normalized RMSE (nRMSE), and target-volume variations were evaluated with volumetric dice coefficient (VDC) and Hausdorff-distance (HD).Results.The model performance across the evaluated angles were MAE(XCAT, ZEUS)= (0.053 ± 0.003, 0.094 ± 0.003), and RMSE(XCAT, ZEUS)= (0.054 ± 0.007, 0.103 ± 0.002). Similarly, SSIM(XCAT, ZEUS)= (0.994 ± 0.001, 0.96 ± 0.02), and nRMSE(XCAT, ZEUS)= (0.13 ± 0.01, 0.17 ± 0.03). For all motion scenarios for XCAT and ZEUS, SSIM were 0.98 ± 0.01 and 0.84 ± 0.02, nRMSE were 0.14 ± 0.01 and 0.27 ± 0.02, VDC were 0.98 ± 0.01 and 0.90 ± 0.01, and HD were 0.24 ± 0.02 mm and 2.3 ± 0.8 mm, respectively, averaged across all angles. Finally, SSIM, nRMSE, VDC and HU values for ZEUS using thedeformedimages as ground truth, presented an improvement of 13%, 28%, 4%, and 76%, respectively.Conclusions. Results from a digital and physical phantom demonstrate a novel approach to generate real-time 3D synthetic MRI from onboard kV images on a conventional LINAC for intra-fraction monitoring in abdominal radiotherapy.

  View details for DOI 10.1088/1361-6560/adbeb5

  View details for PubMedID 40064117

  View details for PubMedCentralID PMC12036502

• Machine Learned Texture Prior From Full-Dose CT Database via Multi-Modality Feature Selection for Bayesian Reconstruction of Low-Dose CT. IEEE transactions on medical imaging Gao, Y., Tan, J., Shi, Y., Zhang, H., Lu, S., Gupta, A., Li, H., Reiter, M., Liang, Z. 2023; 42 (11): 3129-3139

  Abstract

  In our earlier study, we proposed a regional Markov random field type tissue-specific texture prior from previous full-dose computed tomography (FdCT) scan for current low-dose CT (LdCT) imaging, which showed clinical benefits through task-based evaluation. Nevertheless, two assumptions were made for early study. One assumption is that the center pixel has a linear relationship with its nearby neighbors and the other is previous FdCT scans of the same subject are available. To eliminate the two assumptions, we proposed a database assisted end-to-end LdCT reconstruction framework which includes a deep learning texture prior model and a multi-modality feature based candidate selection model. A convolutional neural network-based texture prior is proposed to eliminate the linear relationship assumption. And for scenarios in which the concerned subject has no previous FdCT scans, we propose to select one proper prior candidate from the FdCT database using multi-modality features. Features from three modalities are used including the subjects' physiological factors, the CT scan protocol, and a novel feature named Lung Mark which is deliberately proposed to reflect the z-axial property of human anatomy. Moreover, a majority vote strategy is designed to overcome the noise effect from LdCT scans. Experimental results showed the effectiveness of Lung Mark. The selection model has accuracy of 84% testing on 1,470 images from 49 subjects. The learned texture prior from FdCT database provided reconstruction comparable to the subjects having corresponding FdCT. This study demonstrated the feasibility of bringing clinically relevant textures from available FdCT database to perform Bayesian reconstruction of any current LdCT scan.

  View details for DOI 10.1109/TMI.2021.3139533

  View details for PubMedID 34968178

  View details for PubMedCentralID PMC9243192

• Exploring Dual-Energy CT Spectral Information for Machine Learning-Driven Lesion Diagnosis in Pre-Log Domain. IEEE transactions on medical imaging Chang, S., Gao, Y., Pomeroy, M. J., Bai, T., Zhang, H., Lu, S., Pickhardt, P. J., Gupta, A., Reiter, M. J., Gould, E. S., Liang, Z. 2023; 42 (6): 1835-1845

  Abstract

  In this study, we proposed a computer-aided diagnosis (CADx) framework under dual-energy spectral CT (DECT), which operates directly on the transmission data in the pre-log domain, called CADxDE, to explore the spectral information for lesion diagnosis. The CADxDE includes material identification and machine learning (ML) based CADx. Benefits from DECT's capability of performing virtual monoenergetic imaging with the identified materials, the responses of different tissue types (e.g., muscle, water, and fat) in lesions at each energy can be explored by ML for CADx. Without losing essential factors in the DECT scan, a pre-log domain model-based iterative reconstruction is adopted to obtain decomposed material images, which are then used to generate the virtual monoenergetic images (VMIs) at selected n energies. While these VMIs have the same anatomy, their contrast distribution patterns contain rich information along with the n energies for tissue characterization. Thus, a corresponding ML-based CADx is developed to exploit the energy-enhanced tissue features for differentiating malignant from benign lesions. Specifically, an original image-driven multi-channel three-dimensional convolutional neural network (CNN) and extracted lesion feature-based ML CADx methods are developed to show the feasibility of CADxDE. Results from three pathologically proven clinical datasets showed 4.01% to 14.25% higher AUC (area under the receiver operating characteristic curve) scores than the scores of both the conventional DECT data (high and low energy spectrum separately) and the conventional CT data. The mean gain >9.13% in AUC scores indicated that the energy spectral-enhanced tissue features from CADxDE have great potential to improve lesion diagnosis performance.

  View details for DOI 10.1109/TMI.2023.3240847

  View details for PubMedID 37022248

  View details for PubMedCentralID PMC10238622

• A Joint-Parameter Estimation and Bayesian Reconstruction Approach to Low-Dose CT. Sensors (Basel, Switzerland) Gao, Y., Lu, S., Shi, Y., Chang, S., Zhang, H., Hou, W., Li, L., Liang, Z. 2023; 23 (3)

  Abstract

  Most penalized maximum likelihood methods for tomographic image reconstruction based on Bayes' law include a freely adjustable hyperparameter to balance the data fidelity term and the prior/penalty term for a specific noise-resolution tradeoff. The hyperparameter is determined empirically via a trial-and-error fashion in many applications, which then selects the optimal result from multiple iterative reconstructions. These penalized methods are not only time-consuming by their iterative nature, but also require manual adjustment. This study aims to investigate a theory-based strategy for Bayesian image reconstruction without a freely adjustable hyperparameter, to substantially save time and computational resources. The Bayesian image reconstruction problem is formulated by two probability density functions (PDFs), one for the data fidelity term and the other for the prior term. When formulating these PDFs, we introduce two parameters. While these two parameters ensure the PDFs completely describe the data and prior terms, they cannot be determined by the acquired data; thus, they are called complete but unobservable parameters. Estimating these two parameters becomes possible under the conditional expectation and maximization for the image reconstruction, given the acquired data and the PDFs. This leads to an iterative algorithm, which jointly estimates the two parameters and computes the to-be reconstructed image by maximizing a posteriori probability, denoted as joint-parameter-Bayes. In addition to the theoretical formulation, comprehensive simulation experiments are performed to analyze the stopping criterion of the iterative joint-parameter-Bayes method. Finally, given the data, an optimal reconstruction is obtained without any freely adjustable hyperparameter by satisfying the PDF condition for both the data likelihood and the prior probability, and by satisfying the stopping criterion. Moreover, the stability of joint-parameter-Bayes is investigated through factors such as initialization, the PDF specification, and renormalization in an iterative manner. Both phantom simulation and clinical patient data results show that joint-parameter-Bayes can provide comparable reconstructed image quality compared to the conventional methods, but with much less reconstruction time. To see the response of the algorithm to different types of noise, three common noise models are introduced to the simulation data, including white Gaussian noise to post-log sinogram data, Poisson-like signal-dependent noise to post-log sinogram data and Poisson noise to the pre-log transmission data. The experimental outcomes of the white Gaussian noise reveal that the two parameters estimated by the joint-parameter-Bayes method agree well with simulations. It is observed that the parameter introduced to satisfy the prior's PDF is more sensitive to stopping the iteration process for all three noise models. A stability investigation showed that the initial image by filtered back projection is very robust. Clinical patient data demonstrated the effectiveness of the proposed joint-parameter-Bayes and stopping criterion.

  View details for DOI 10.3390/s23031374

  View details for PubMedID 36772417

  View details for PubMedCentralID PMC9921255

• CBCT/CT-Based Image Synthesis Medical Image Synthesis: Methods and Clinical Applications Zhang, H. CRC Press. 2023; 1: 11
• Artificial Intelligence in Radiation Therapy. IEEE transactions on radiation and plasma medical sciences Fu, Y., Zhang, H., Morris, E. D., Glide-Hurst, C. K., Pai, S., Traverso, A., Wee, L., Hadzic, I., Lønne, P. I., Shen, C., Liu, T., Yang, X. 2022; 6 (2): 158-181

  Abstract

  Artificial intelligence (AI) has great potential to transform the clinical workflow of radiotherapy. Since the introduction of deep neural networks, many AI-based methods have been proposed to address challenges in different aspects of radiotherapy. Commercial vendors have started to release AI-based tools that can be readily integrated to the established clinical workflow. To show the recent progress in AI-aided radiotherapy, we have reviewed AI-based studies in five major aspects of radiotherapy including image reconstruction, image registration, image segmentation, image synthesis, and automatic treatment planning. In each section, we summarized and categorized the recently published methods, followed by a discussion of the challenges, concerns, and future development. Given the rapid development of AI-aided radiotherapy, the efficiency and effectiveness of radiotherapy in the future could be substantially improved through intelligent automation of various aspects of radiotherapy.

  View details for DOI 10.1109/TRPMS.2021.3107454

  View details for PubMedID 35992632

  View details for PubMedCentralID PMC9385128

• Prior-image-based CT reconstruction using attenuation-mismatched priors. Physics in medicine and biology Zhang, H., Capaldi, D., Zeng, D., Ma, J., Xing, L. 2021; 66 (6): 064007

  Abstract

  Prior-image-based reconstruction (PIBR) methods are powerful tools for reducing radiation doses and improving the image quality of low-dose computed tomography (CT). Apart from anatomical changes, prior and current images can also have different attenuations because they originated from different scanners or from the same scanner but with different x-ray beam qualities (e.g., kVp settings, beam filters) during data acquisition. In such scenarios, with attenuation-mismatched priors, PIBR is challenging. In this work, we investigate a specific PIBR method, called statistical image reconstruction, using normal-dose image-induced nonlocal means regularization (SIR-ndiNLM), to address PIBR with such attenuation-mismatched priors and achieve quantitative low-dose CT imaging. We propose two corrective schemes for the original SIR-ndiNLM method, (1) a global histogram-matching approach and (2) a local attenuation correction approach, to account for the attenuation differences between the prior and current images in PIBR. We validate the efficacy of the proposed schemes using images acquired from dual-energy CT scanners to simulate attenuation mismatches. Meanwhile, we utilize different CT slices to simulate anatomical mismatches or changes between the prior and the current low-dose image. We observe that the original SIR-ndiNLM introduces artifacts to the reconstruction when an attenuation-mismatched prior is used. Furthermore, we find that a larger attenuation mismatch between the prior and current images results in more severe artifacts in the SIR-ndiNLM reconstruction. Our two proposed corrective schemes enable SIR-ndiNLM to effectively handle the attenuation mismatch and anatomical changes between the two images and successfully eliminate the artifacts. We demonstrate that the proposed techniques permit SIR-ndiNLM to leverage the attenuation-mismatched prior and achieve quantitative low-dose CT reconstruction from both low-flux and sparse-view data acquisitions. This work permits robust and reliable PIBR for CT data acquired using different beam settings.

  View details for DOI 10.1088/1361-6560/abe760

  View details for PubMedID 33729997

• Direct reconstruction of anatomical change in low-dose lung nodule surveillance. Journal of medical imaging (Bellingham, Wash.) Flores, J. D., Gang, G. J., Zhang, H., Lin, C. T., Fung, S. K., Stayman, J. W. 2021; 8 (2): 023503

  Abstract

  Purpose: In sequential imaging studies, there exists rich information from past studies that can be used in prior-image-based reconstruction (PIBR) as a form of improved regularization to yield higher-quality images in subsequent studies. PIBR methods, such as reconstruction of difference (RoD), have demonstrated great improvements in the image quality of subsequent anatomy reconstruction even when CT data are acquired at very low-exposure settings. Approach: However, to effectively use information from past studies, two major elements are required: (1) registration, usually deformable, must be applied between the current and prior scans. Such registration is greatly complicated by potential ambiguity between patient motion and anatomical change-which is often the target of the followup study. (2) One must select regularization parameters for reliable and robust reconstruction of features. Results: We address these two major issues and apply a modified RoD framework to the clinical problem of lung nodule surveillance. Specifically, we develop a modified deformable registration approach that enforces a locally smooth/rigid registration around the change region and extend previous analytic expressions relating reconstructed contrast to the regularization parameter and other system dependencies for reliable representation of image features. We demonstrate the efficacy of this approach using a combination of realistic digital phantoms and clinical projection data. Performance is characterized as a function of the size of the locally smooth registration region of interest as well as x-ray exposure. Conclusions: This modified framework is effectively able to separate patient motion and anatomical change to directly highlight anatomical change in lung nodule surveillance.

  View details for DOI 10.1117/1.JMI.8.2.023503

  View details for PubMedID 33846692

  View details for PubMedCentralID PMC8033535

• A robotically assisted 3D printed quality assurance lung phantom for Calypso. Physics in medicine and biology Capaldi, D. P., Skinner, L. B., Dubrowski, P. n., Zhang, H. n., Xing, L. n., Chuang, C. F., Loo, B. W., Bush, K. K., Fahimian, B. P., Yu, A. S. 2021

  Abstract

  Purpose:Radiation dose delivered to targets located near the upper-abdomen or in the thorax are significantly affected by respiratory-motion. Relatively large-margins are commonly added to compensate for this motion, limiting radiation-dose-escalation. Internal-surrogates of target motion, such as a radiofrequency (RF) tracking system, i.e. Calypso® System, are used to overcome this challenge and improve normal-tissue sparing. RF tracking systems consist of implanting transponders in the vicinity of the tumor to be tracked using radiofrequency-waves. Unfortunately, although the manufacture provides a universal quality-assurance (QA) phantom, QA-phantoms specifically for lung-applications are limited, warranting the development of alternative solutions to fulfil the tests mandated by AAPM's TG142. Accordingly, our objective was to design and develop a motion-phantom to evaluate Calypso for lung-applications that allows the Calypso® Beacons to move in different directions to better simulate true lung-motion.Methods and Materials:A Calypso lung QA-phantom was designed, and 3D-printed. The design consists of three independent arms where the transponders were attached. A pinpoint-chamber with a buildup-cap was also incorporated. A 4-axis robotic arm was programmed to drive the motion-phantom to mimic breathing. After acquiring a four-dimensional-computed-tomography (4DCT) scan of the motion-phantom, treatment-plans were generated and delivered on a Varian TrueBeam® with Calypso capabilities. Stationary and gated-treatment plans were generated and delivered to determine the dosimetric difference between gated and non-gated treatments. Portal cine-images were acquired to determine the temporal-accuracy of delivery by calculating the difference between the observed versus expected transponders locations with the known speed of the transponders' motion.Results:Dosimetric accuracy is better than TG142 tolerance of 2%. Temporal accuracy is greater than, TG142 tolerance of 100ms for beam-on, but less than 100ms for beam-hold.Conclusions:The robotic QA-phantom designed and developed in this study provides an independent phantom for performing Calypso lung-QA for commissioning and acceptance testing of Calypso for lung treatments.

  View details for DOI 10.1088/1361-6560/abebaa

  View details for PubMedID 33657537

• Characterization of tissue-specific pre-log Bayesian CT reconstruction by texture-dose relationship. Medical physics Gao, Y., Liang, Z., Xing, Y., Zhang, H., Pomeroy, M., Lu, S., Ma, J., Lu, H., Moore, W. 2020; 47 (10): 5032-5047

  Abstract

  Tissue textures have been recognized as biomarkers for various clinical tasks. In computed tomography (CT) image reconstruction, it is important but challenging to preserve the texture when lowering x-ray exposure from full- toward low-/ultra-low dose level. Therefore, this paper aims to explore the texture-dose relationship within one tissue-specific pre-log Bayesian CT reconstruction algorithm.To enhance the texture in ultra-low dose CT (ULdCT) reconstruction, this paper presents a Bayesian type algorithm. A shifted Poisson model is adapted to describe the statistical properties of pre-log data, and a tissue-specific Markov random field prior (MRFt) is used to incorporate tissue texture from previous full-dose CT, thus called SP-MRFt algorithm. Utilizing the SP-MRFt algorithm, we investigated tissue texture degradation as a function of x-ray dose levels from full dose (100 mAs/120 kVp) to ultralow dose (1 mAs/120 kVp) by using quantitative texture-based evaluation metrics.Experimental results show the SP-MRFt algorithm outperforms conventional filtered back projection (FBP) and post-log domain penalized weighted least square MRFt (PWLS-MRFt) in terms of noise suppression and texture preservation. Comparable results are also obtained with shifted Poisson model with 7 × 7 Huber MRF weights (SP-Huber7). The investigation on texture-dose relationship shows that the quantified texture measures drop monotonically as dose level decreases, and interestingly a turning point is observed on the texture-dose response curve.This important observation implies that there exists a minimum dose level, at which a given CT scanner (hardware configuration and image reconstruction software) can achieve without compromising clinical tasks. Moreover, the experiment results show that the variance of electronic noise has higher impact than the mean to the texture-dose relationship.

  View details for DOI 10.1002/mp.14449

  View details for PubMedID 32786070

  View details for PubMedCentralID PMC7721985

• Full-Spectrum-Knowledge-Aware Tensor Model for Energy-Resolved CT Iterative Reconstruction IEEE TRANSACTIONS ON MEDICAL IMAGING Zeng, D., Yao, L., Ge, Y., Li, S., Xie, Q., Zhang, H., Bian, Z., Zhao, Q., Li, Y., Xu, Z., Meng, D., Ma, J. 2020; 39 (9): 2831–43

  Abstract

  Energy-resolved computed tomography (ErCT) with a photon counting detector concurrently produces multiple CT images corresponding to different photon energy ranges. It has the potential to generate energy-dependent images with improved contrast-to-noise ratio and sufficient material-specific information. Since the number of detected photons in one energy bin in ErCT is smaller than that in conventional energy-integrating CT (EiCT), ErCT images are inherently more noisy than EiCT images, which leads to increased noise and bias in the subsequent material estimation. In this work, we first deeply analyze the intrinsic tensor properties of two-dimensional (2D) ErCT images acquired in different energy bins and then present a F ull- S pectrum-knowledge-aware Tensor analysis and processing (FSTensor) method for ErCT reconstruction to suppress noise-induced artifacts to obtain high-quality ErCT images and high-accuracy material images. The presented method is based on three considerations: (1) 2D ErCT images obtained in different energy bins can be treated as a 3-order tensor with three modes, i.e., width, height and energy bin, and a rich global correlation exists among the three modes, which can be characterized by tensor decomposition. (2) There is a locally piecewise smooth property in the 3-order ErCT images, and it can be captured by a tensor total variation regularization. (3) The images from the full spectrum are much better than the ErCT images with respect to noise variance and structural details and serve as external information to improve the reconstruction performance. We then develop an alternating direction method of multipliers algorithm to numerically solve the presented FSTensor method. We further utilize a genetic algorithm to tackle the parameter selection in ErCT reconstruction, instead of manually determining parameters. Simulation, preclinical and synthesized clinical ErCT results demonstrate that the presented FSTensor method leads to significant improvements over the filtered back-projection, robust principal component analysis, tensor-based dictionary learning and low-rank tensor decomposition with spatial-temporal total variation methods.

  View details for DOI 10.1109/TMI.2020.2976692

  View details for Web of Science ID 000566339800011

  View details for PubMedID 32112677

• Second window near-infrared dosimeter (NIR2D) system for radiation dosimetry. Physics in medicine and biology Kim, T. J., Cheng, K., Zhang, H., Liu, S., Skinner, L., Xing, L. 2020; 65 (17): 175013

  Abstract

  Fiber-coupled scintillation dosimeters are a cost-effective alternative to the conventional ion chambers in radiation dosimetry. However, stem effects from optical fibers such as Cerenkov radiation incur significant errors in the readout signal. Here we introduce a second near-infrared window dosimeter, dubbed as NIR2D, that can potentially be used as real-time radiation detector for clinical megavoltage beams. Lanthanide-based rare-earth NaYF4 nano-phosphors doped with both erbium and cerium elements were synthesized, and a compact 3D printed reader device integrated with a photodetector and data acquisition system was designed. The performance of the NIR2D was tested using a pre-clinical orthovoltage radiation source and a clinical megavoltage radiation source. The system was tested for dose linearity (100, 200, 600 MU), dose rate dependency (100, 200, 400, 600 MU min-1), and energy dependency (6, 10, 15 MV). Test results with the clinical linear accelerator demonstrated excellent dose linearity and dose rate independency when exposed to 6 MV linac beams-both data follows a linear trendline with R2 > 0.99. On the other hand, the NIR2D was energy dependent, where the readout dropped by 9% between 6 and 15 MV. For stem effects, we observed a finite Cerenkov contribution of 1%-3% when exposed between 100-600 MU min-1 (6 MV) and 3%-6% when exposed between 5-15 MV (600 MU min-1). While the stem effects were still observable, we expect that enhancing the current optical setup will simultaneously improve the scintillation signal and reduce the stem effects.

  View details for DOI 10.1088/1361-6560/ab9b56

  View details for PubMedID 32869751

• A Task-Dependent Investigation on Dose and Texture in CT Image Reconstruction IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES Gao, Y., Liang, Z., Zhang, H., Yang, J., Ferretti, J., Bilfinger, T., Yaddanapudi, K., Schweitzer, M., Bhattacharji, P., Moore, W. 2020; 4 (4): 441–49

  View details for DOI 10.1109/TRPMS.2019.2957459

  View details for Web of Science ID 000545568600001

• Technical Note: Evaluation of Audiovisual Biofeedback Smartphone Application for Respiratory Monitoring in Radiation Oncology. Medical physics Capaldi, D. P., Nano, T. F., Zhang, H. n., Skinner, L. B., Xing, L. n. 2020

  Abstract

  Radiation dose delivered to targets located near the upper abdomen or thorax are significantly affected by respiratory motion, necessitating large margins, limiting dose escalation. Surrogate motion management devices, such as the Real-time Position Management (RPM™) system (Varian Medical Systems, Palo Alto, CA), are commonly used to improve normal tissue sparing. Alternative to current solutions, we have developed and evaluated the feasibility of a real-time position management system that leverages the motion data from the onboard hardware of Apple iOS devices to provide patients with visual coaching with the potential to improve the reproducibility of breathing as well as improve patient compliance and reduce treatment delivery time.The iOS application, coined the Instant Respiratory Feedback (IRF) system, was developed in Swift (Apple Inc., Cupertino, CA) using the Core-Motion library and implemented on an Apple iPhone® devices. Operation requires an iPhone®, a 3D printed arm, and a radiolucent projector screen system for feedback. Direct comparison between IRF, which leverages sensor fusion data from the iPhone®, and RPM™, an optical based system, was performed on multiple respiratory motion phantoms and volunteers. The IRF system and RPM™ camera tracking marker were placed on the same location allowing for simultaneous data acquisition. The IRF surrogate measurement of displacement was compared to the signal trace acquired using RPM™ with univariate linear regressions and Bland-Altman analysis.Periodic motion shows excellent agreement between both systems, and subject motion shows good agreement during regular and irregular breathing motion. Comparison of IRF and RPM™ show very similar signal traces that were significantly related across all phantoms, including those motion with different amplitude and frequency, and subjects' waveforms (all r>0.9, p<0.0001). We demonstrate the feasibility of four-dimensional cone beam computed tomography reconstruction using IRF can acquire dynamic phantom images with similar image quality as RPM™.Feasibility of an iOS application to provide real-time respiratory motion is demonstrated. This system generated comparable signal traces to a commercially available system and offers an alternative method to monitor respiratory motion.

  View details for DOI 10.1002/mp.14484

  View details for PubMedID 32969075

• Contrast-Medium Anisotropy-Aware Tensor Total Variation Model for Robust Cerebral Perfusion CT Reconstruction With Low-Dose Scans IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING Zhang, Y., Peng, J., Zeng, D., Xie, Q., Li, S., Bian, Z., Wang, Y., Zhang, Y., Zhao, Q., Zhang, H., Liang, Z., Lu, H., Meng, D., Ma, J. 2020; 6: 1375–88

  View details for DOI 10.1109/TCI.2020.3023598

  View details for Web of Science ID 000573760200001

• A Feasibility Study of Extracting Tissue Textures From a Previous Full-Dose CT Database as Prior Knowledge for Bayesian Reconstruction of Current Low-Dose CT Images IEEE TRANSACTIONS ON MEDICAL IMAGING Gao, Y., Liang, Z., Moore, W., Zhang, H., Pomeroy, M. J., Ferretti, J. A., Bilfinger, T., Ma, J., Lu, H. 2019; 38 (8): 1981–92

  Abstract

  Markov random field (MRF) has been widely used to incorporate a priori knowledge as penalty or regularizer to preserve edge sharpness while smoothing the region enclosed by the edge for pieces-wise smooth image reconstruction. In our earlier study, we proposed a type of MRF reconstruction method for low-dose CT (LdCT) scans using tissue-specific textures extracted from the same patient's previous full-dose CT (FdCT) scans as prior knowledge. It showed advantages in clinical applications. This paper aims to remove the constraint of using previous data of the same patient. We investigated the feasibility of extracting the tissue-specific MRF textures from an FdCT database to reconstruct a LdCT image of another patient. This feasibility study was carried out by experiments designed as follows. We constructed a tissue-specific MRF-texture database from 3990 FdCT scan slices of 133 patients who were scheduled for lung nodule biopsy. Each patient had one FdCT scan (120 kVp/100 mAs) and one LdCT scan (120 kVp/20 mAs) prior to biopsy procedure. When reconstructing the LdCT image of one patient among the 133 patients, we ranked the closeness of the MRF-textures from the other 132 patients saved in the database and used them as the a prior knowledge. Then, we evaluated the reconstructed image quality using Haralick texture measures. For any patient within our database, we found more than eighteen patients' FdCT MRF texures can be used without noticeably changing the Haralick texture measures on the lung nodules (to be biopsied). These experimental outcomes indicate it is promising that a sizable FdCT texture database could be used to enhance Bayesian reconstructions of any incoming LdCT scans.

  View details for DOI 10.1109/TMI.2018.2890788

  View details for Web of Science ID 000478942200019

  View details for PubMedID 30605098

  View details for PubMedCentralID PMC6610633

• An Efficient Iterative Cerebral Perfusion CT Reconstruction via Low-Rank Tensor Decomposition With Spatial-Temporal Total Variation Regularization. IEEE transactions on medical imaging Li, S., Zeng, D., Peng, J., Bian, Z., Zhang, H., Xie, Q., Wang, Y., Liao, Y., Zhang, S., Huang, J., Meng, D., Xu, Z., Ma, J. 2019; 38 (2): 360-370

  Abstract

  Cerebrovascular diseases, i.e., acute stroke, are a common cause of serious long-term disability. Cerebral perfusion computed tomography (CPCT) can provide rapid, high-resolution, quantitative hemodynamic maps to assess and stratify perfusion in patients with acute stroke symptoms. However, CPCT imaging typically involves a substantial radiation dose due to its repeated scanning protocol. Therefore, in this paper, we present a low-dose CPCT image reconstruction method to yield high-quality CPCT images and high-precision hemodynamic maps by utilizing the great similarity information among the repeated scanned CPCT images. Specifically, a newly developed low-rank tensor decomposition with spatial-temporal total variation (LRTD-STTV) regularization is incorporated into the reconstruction model. In the LRTD-STTV regularization, the tensor Tucker decomposition is used to describe global spatial-temporal correlations hidden in the sequential CPCT images, and it is superior to the matricization model (i.e., low-rank model) that fails to fully investigate the prior knowledge of the intrinsic structures of the CPCT images after vectorizing the CPCT images. Moreover, the spatial-temporal TV regularization is used to characterize the local piecewise smooth structure in the spatial domain and the pixels' similarity with the adjacent frames in the temporal domain, because the intensity at each pixel in CPCT images is similar to its neighbors. Therefore, the presented LRTD-STTV model can efficiently deliver faithful underlying information of the CPCT images and preserve the spatial structures. An efficient alternating direction method of multipliers algorithm is also developed to solve the presented LRTD-STTV model. Extensive experimental results on numerical phantom and patient data are clearly demonstrated that the presented model can significantly improve the quality of CPCT images and provide accurate diagnostic features in hemodynamic maps for low-dose cases compared with the existing popular algorithms.

  View details for DOI 10.1109/TMI.2018.2865198

  View details for PubMedID 30106716

• Optimizing a Parameterized Plug-and-Play ADMM for Iterative Low-Dose CT Reconstruction. IEEE transactions on medical imaging He, J., Yang, Y., Wang, Y., Zeng, D., Bian, Z., Zhang, H., Sun, J., Xu, Z., Ma, J. 2019; 38 (2): 371-382

  Abstract

  Reducing the exposure to X-ray radiation while maintaining a clinically acceptable image quality is desirable in various CT applications. To realize low-dose CT (LdCT) imaging, model-based iterative reconstruction (MBIR) algorithms are widely adopted, but they require proper prior knowledge assumptions in the sinogram and/or image domains and involve tedious manual optimization of multiple parameters. In this paper, we propose a deep learning (DL)-based strategy for MBIR to simultaneously address prior knowledge design and MBIR parameter selection in one optimization framework. Specifically, a parameterized plug-and-play alternating direction method of multipliers (3pADMM) is proposed for the general penalized weighted least-squares model, and then, by adopting the basic idea of DL, the parameterized plug-and-play (3p) prior and the related parameters are optimized simultaneously in a single framework using a large number of training data. The main contribution of this paper is that the 3p prior and the related parameters in the proposed 3pADMM framework can be supervised and optimized simultaneously to achieve robust LdCT reconstruction performance. Experimental results obtained on clinical patient datasets demonstrate that the proposed method can achieve promising gains over existing algorithms for LdCT image reconstruction in terms of noise-induced artifact suppression and edge detail preservation.

  View details for DOI 10.1109/TMI.2018.2865202

  View details for PubMedID 30106717

• Regularization Analysis and Design for Prior-Image-Based X-Ray CT Reconstruction. IEEE transactions on medical imaging Zhang, H., Gang, G. J., Dang, H., Stayman, J. W. 2018; 37 (12): 2675-2686

  Abstract

  Prior-image-based reconstruction (PIBR) methods have demonstrated great potential for radiation dose reduction in computed tomography applications. PIBR methods take advantage of shared anatomical information between sequential scans by incorporating a patient-specific prior image into the reconstruction objective function, often as a form of regularization. However, one major challenge with PIBR methods is how to optimally determine the prior image regularization strength which balances anatomical information from the prior image with data fitting to the current measurements. Too little prior information yields limited improvements over traditional model-based iterative reconstruction, while too much prior information can force anatomical features from the prior image not supported by the measurement data, concealing true anatomical changes. In this paper, we develop quantitative measures of the bias associated with PIBR. This bias exhibits as a fractional reconstructed contrast of the difference between the prior image and current anatomy, which is quite different from traditional reconstruction biases that are typically quantified in terms of spatial resolution or artifacts. We have derived an analytical relationship between the PIBR bias and prior image regularization strength and illustrated how this relationship can be used as a predictive tool to prospectively determine prior image regularization strength to admit specific kinds of anatomical change in the reconstruction. Because bias is dependent on local statistics, we further generalized shift-variant prior image penalties that permit uniform (shift invariant) admission of anatomical changes across the imaging field of view. We validated the mathematical framework in phantom studies and compared bias predictions with estimates based on brute force exhaustive evaluation using numerous iterative reconstructions across regularization values. The experimental results demonstrate that the proposed analytical approach can predict the bias-regularization relationship accurately, allowing for prospective determination of the prior image regularization strength in PIBR. Thus, the proposed approach provides an important tool for controlling image quality of PIBR methods in a reliable, robust, and efficient fashion.

  View details for DOI 10.1109/TMI.2018.2847250

  View details for PubMedID 29994249

  View details for PubMedCentralID PMC6295916

• Statistical CT reconstruction using region-aware texture preserving regularization learning from prior normal-dose CT image PHYSICS IN MEDICINE AND BIOLOGY Jia, X., Liao, Y., Zeng, D., Zhang, H., Zhang, Y., He, J., Bian, Z., Wang, Y., Tao, X., Liang, Z., Huang, J., Ma, J. 2018; 63 (22): 225020

  Abstract

  In some clinical applications, prior normal-dose CT (NdCT) images are available, and the valuable textures and structure features in them may be used to promote follow-up low-dose CT (LdCT) reconstruction. This study aims to learn texture information from the NdCT images and leverage it for follow-up LdCT image reconstruction to preserve textures and structure features. Specifically, the proposed reconstruction method first learns the texture information from those patches with similar structures in NdCT image, and the similar patches can be clustered by searching context features efficiently from the surroundings of the current patch. Then it utilizes redundant texture information from the similar patches as a priori knowledge to describe specific regions in the LdCT image. The advanced region-aware texture preserving prior is termed as 'RATP'. The main advantage of the PATP prior is that it can properly learn the texture features from available NdCT images and adaptively characterize the region-specific structures in the LdCT image. The experiments using patient data were performed to evaluate the performance of the proposed method. The proposed RATP method demonstrated superior performance in LdCT imaging compared to the filtered back projection (FBP) and statistical iterative reconstruction (SIR) methods using Gaussian regularization, Huber regularization and the original texture preserving regularization.

  View details for DOI 10.1088/1361-6560/aaebc9

  View details for Web of Science ID 000450813200003

  View details for PubMedID 30457116

• Iterative quality enhancement via residual-artifact learning networks for low-dose CT. Physics in medicine and biology Wang, Y., Liao, Y., Zhang, Y., He, J., Li, S., Bian, Z., Zhang, H., Gao, Y., Meng, D., Zuo, W., Zeng, D., Ma, J. 2018; 63 (21): 215004

  Abstract

  Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.

  View details for DOI 10.1088/1361-6560/aae511

  View details for PubMedID 30265251

• Regularization strategies in statistical image reconstruction of low-dose X-ray CT: A review. Medical physics Zhang, H., Wang, J., Zeng, D., Tao, X., Ma, J. 2018

  Abstract

  Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose X-ray computed tomography (CT) as compared to the conventional filtered back-projection (FBP) method. According to the maximum a posteriori (MAP) estimation, the SIR methods are typically formulated by an objective function consisting of two terms: (1) a data-fidelity term that models imaging geometry and physical detection processes in projection data acquisition, and (2) a regularization term that reflects prior knowledge or expectations of the characteristics of the to-be-reconstructed image. SIR desires accurate system modeling of data acquisition, while the regularization term also has a strong influence on the quality of reconstructed images. A variety of regularization strategies have been proposed for SIR in the past decades, based on different assumptions, models and prior knowledge. In this paper, we review the conceptual and mathematical bases of these regularization strategies and briefly illustrate their efficacies in SIR of low-dose CT. This article is protected by copyright. All rights reserved.

  View details for PubMedID 30098050

• Promote quantitative ischemia imaging via myocardial perfusion CT iterative reconstruction with tensor total generalized variation regularization. Physics in medicine and biology Gu, C., Zeng, D., Lin, J., Li, S., He, J., Zhang, H., Bian, Z., Niu, S., Zhang, Z., Huang, J., Chen, B., Zhao, D., Chen, W., Ma, J. 2018; 63 (12): 125009

  Abstract

  Myocardial perfusion computed tomography (MPCT) imaging is commonly used to detect myocardial ischemia quantitatively. A limitation in MPCT is that an additional radiation dose is required compared to unenhanced CT due to its repeated dynamic data acquisition. Meanwhile, noise and streak artifacts in low-dose cases are the main factors that degrade the accuracy of quantifying myocardial ischemia and hamper the diagnostic utility of the filtered backprojection reconstructed MPCT images. Moreover, it is noted that the MPCT images are composed of a series of 2/3D images, which can be naturally regarded as a 3/4-order tensor, and the MPCT images are globally correlated along time and are sparse across space. To obtain higher fidelity ischemia from low-dose MPCT acquisitions quantitatively, we propose a robust statistical iterative MPCT image reconstruction algorithm by incorporating tensor total generalized variation (TTGV) regularization into a penalized weighted least-squares framework. Specifically, the TTGV regularization fuses the spatial correlation of the myocardial structure and the temporal continuation of the contrast agent intake during the perfusion. Then, an efficient iterative strategy is developed for the objective function optimization. Comprehensive evaluations have been conducted on a digital XCAT phantom and a preclinical porcine dataset regarding the accuracy of the reconstructed MPCT images, the quantitative differentiation of ischemia and the algorithm's robustness and efficiency.

  View details for DOI 10.1088/1361-6560/aac7bd

  View details for PubMedID 29794346

• Iterative reconstruction for low dose dual energy CT using information-divergence constrained spectral redundancy information. Journal of X-ray science and technology Lin, J., Zhang, H., Huang, J., Bian, Z., Zhang, S., Wang, Y., Liao, Y., Li, S., Zhang, H., Zeng, D., Ma, J. 2018; 26 (2): 311-330

  Abstract

  Dual energy computed tomography (DECT) can improve the capability of differentiating different materials compared with conventional CT. However, due to non-negligible radiation exposure to patients, dose reduction has recently become a critical concern in CT imaging field. In this work, to reduce noise at the same time maintain DECT images quality, we present an iterative reconstruction algorithm for low-dose DECT images where in the objective function of the algorithm consists of a data-fidelity term and a regularization term. The former term is based on alpha-divergence to describe the statistical distribution of the DE sinogram data. And the latter term is based on the redundant information to reflect the prior information of the desired DECT images. For simplicity, the presented algorithm is termed as "AlphaD-aviNLM". To minimize the associative objective function, a modified proximal forward-backward splitting algorithm is proposed. Digital phantom, physical phantom, and patient data were utilized to validate and evaluate the presented AlphaD-aviNLM algorithm. The experimental results characterize the performance of the presented AlphaD-aviNLM algorithm. Speficically, in the digital phantom study, the presented AlphaD-aviNLM algorithm performs better than the PWLS-TV, PWLS-aviNLM, and AlphaD-TV with more than 49%, 34%, and 40% gains for the RMSE metric, 1.3%, 0.4%, and 0.7% gains for the FSIM metric and 13%, 8%, and 11% gains for the PSNR metric. In the physical phantom study, the presented AlphaD-aviNLM algorithm performs better than the PWLS-TV, PWLS-aviNLM, and AlphaD-TV with more than 0.55%, 0.07%, and 0.16% gains for the FSIM metric.

  View details for DOI 10.3233/XST-17272

  View details for PubMedID 29562570

• Low-Dose Dynamic Cerebral Perfusion Computed Tomography Reconstruction via Kronecker-Basis-Representation Tensor Sparsity Regularization. IEEE transactions on medical imaging Zeng, D., Xie, Q., Cao, W., Lin, J., Zhang, H., Zhang, S., Huang, J., Bian, Z., Meng, D., Xu, Z., Liang, Z., Chen, W., Ma, J. 2017; 36 (12): 2546-2556

  Abstract

  Dynamic cerebral perfusion computed tomography (DCPCT) has the ability to evaluate the hemodynamic information throughout the brain. However, due to multiple 3-D image volume acquisitions protocol, DCPCT scanning imposes high radiation dose on the patients with growing concerns. To address this issue, in this paper, based on the robust principal component analysis (RPCA, or equivalently the low-rank and sparsity decomposition) model and the DCPCT imaging procedure, we propose a new DCPCT image reconstruction algorithm to improve low-dose DCPCT and perfusion maps quality via using a powerful measure, called Kronecker-basis-representation tensor sparsity regularization, for measuring low-rankness extent of a tensor. For simplicity, the first proposed model is termed tensor-based RPCA (T-RPCA). Specifically, the T-RPCA model views the DCPCT sequential images as a mixture of low-rank, sparse, and noise components to describe the maximum temporal coherence of spatial structure among phases in a tensor framework intrinsically. Moreover, the low-rank component corresponds to the "background" part with spatial-temporal correlations, e.g., static anatomical contribution, which is stationary over time about structure, and the sparse component represents the time-varying component with spatial-temporal continuity, e.g., dynamic perfusion enhanced information, which is approximately sparse over time. Furthermore, an improved nonlocal patch-based T-RPCA (NL-T-RPCA) model which describes the 3-D block groups of the "background" in a tensor is also proposed. The NL-T-RPCA model utilizes the intrinsic characteristics underlying the DCPCT images, i.e., nonlocal self-similarity and global correlation. Two efficient algorithms using alternating direction method of multipliers are developed to solve the proposed T-RPCA and NL-T-RPCA models, respectively. Extensive experiments with a digital brain perfusion phantom, preclinical monkey data, and clinical patient data clearly demonstrate that the two proposed models can achieve more gains than the existing popular algorithms in terms of both quantitative and visual quality evaluations from low-dose acquisitions, especially as low as 20 mAs.

  View details for DOI 10.1109/TMI.2017.2749212

  View details for PubMedID 28880164

  View details for PubMedCentralID PMC5711606

• Assessment of prior image induced nonlocal means regularization for low-dose CT reconstruction: Change in anatomy. Medical physics Zhang, H., Ma, J., Wang, J., Moore, W., Liang, Z. 2017; 44 (9): e264-e278

  Abstract

  Repeated computed tomography (CT) scans are prescribed for some clinical applications such as lung nodule surveillance. Several studies have demonstrated that incorporating a high-quality prior image into the reconstruction of subsequent low-dose CT (LDCT) acquisitions can either improve image quality or reduce data fidelity requirements. Our proposed previous normal-dose image induced nonlocal means (ndiNLM) regularization method for LDCT is an example of such a method. However, one major concern with prior image based methods is that they might produce false information when the prior image and the current LDCT image show different structures (for example, if a lung nodule emerges, grows, shrinks, or disappears over time). This study aims to assess the performance of the ndiNLM regularization method in situations with change in anatomy.We incorporated the ndiNLM regularization into the statistical image reconstruction (SIR) framework for reconstruction of subsequent LDCT images. Because of its patch-based search mechanism, a rough registration between the prior image and the current LDCT image is adequate for the SIR-ndiNLM method. We assessed the performance of the SIR-ndiNLM method in lung nodule surveillance for two different scenarios: (a) the nodule was not found in a baseline exam but appears in a follow-up LDCT scan; (b) the nodule was present in a baseline exam but disappears in a follow-up LDCT scan. We further investigated the effect of nodule size on the performance of the SIR-ndiNLM method.We found that a relatively large search-window (e.g., 33 × 33) should be used for the SIR-ndiNLM method to account for misalignment between the prior image and the current LDCT image, and to ensure that enough similar patches can be found in the prior image. With proper selection of other parameters, experimental results with two patient datasets demonstrated that the SIR-ndiNLM method did not miss true nodules nor introduce false nodules in the lung nodule surveillance scenarios described above. We also found that the SIR-ndiNLM reconstruction shows improved image quality when the prior image is similar to the current LDCT image in anatomy. These gains in image quality might appear small upon visual inspection, but they can be detected using quantitative measures. Finally, the SIR-ndiNLM method also performed well in ultra-low-dose conditions and with different nodule sizes.This study assessed the performance of the SIR-ndiNLM method in situations in which the prior image and the current LDCT image show substantial anatomical differences, specifically, changes in lung nodules. The experimental results demonstrate that the SIR-ndiNLM method does not introduce false lung nodules nor miss true nodules, which relieves the concern that this method might produce false information. However, there is insufficient evidence that these findings will hold true for all kinds of anatomical changes.

  View details for DOI 10.1002/mp.12378

  View details for PubMedID 28901622

  View details for PubMedCentralID PMC5613294

• Iterative reconstruction for dual energy CT with an average image-induced nonlocal means regularization. Physics in medicine and biology Zhang, H., Zeng, D., Lin, J., Zhang, H., Bian, Z., Huang, J., Gao, Y., Zhang, S., Zhang, H., Feng, Q., Liang, Z., Chen, W., Ma, J. 2017; 62 (13): 5556-5574

  Abstract

  Reducing radiation dose in dual energy computed tomography (DECT) is highly desirable but it may lead to excessive noise in the filtered backprojection (FBP) reconstructed DECT images, which can inevitably increase the diagnostic uncertainty. To obtain clinically acceptable DECT images from low-mAs acquisitions, in this work we develop a novel scheme based on measurement of DECT data. In this scheme, inspired by the success of edge-preserving non-local means (NLM) filtering in CT imaging and the intrinsic characteristics underlying DECT images, i.e. global correlation and non-local similarity, an averaged image induced NLM-based (aviNLM) regularization is incorporated into the penalized weighted least-squares (PWLS) framework. Specifically, the presented NLM-based regularization is designed by averaging the acquired DECT images, which takes the image similarity within the two energies into consideration. In addition, the weighted least-squares term takes into account DECT data-dependent variance. For simplicity, the presented scheme was termed as 'PWLS-aviNLM'. The performance of the presented PWLS-aviNLM algorithm was validated and evaluated on digital phantom, physical phantom and patient data. The extensive experiments validated that the presented PWLS-aviNLM algorithm outperforms the FBP, PWLS-TV and PWLS-NLM algorithms quantitatively. More importantly, it delivers the best qualitative results with the finest details and the fewest noise-induced artifacts, due to the aviNLM regularization learned from DECT images. This study demonstrated the feasibility and efficacy of the presented PWLS-aviNLM algorithm to improve the DECT reconstruction and resulting material decomposition.

  View details for DOI 10.1088/1361-6560/aa7122

  View details for PubMedID 28471750

  View details for PubMedCentralID PMC5497789

• Applications of nonlocal means algorithm in low-dose X-ray CT image processing and reconstruction: A review. Medical physics Zhang, H., Zeng, D., Zhang, H., Wang, J., Liang, Z., Ma, J. 2017; 44 (3): 1168-1185

  Abstract

  Low-dose X-ray computed tomography (LDCT) imaging is highly recommended for use in the clinic because of growing concerns over excessive radiation exposure. However, the CT images reconstructed by the conventional filtered back-projection (FBP) method from low-dose acquisitions may be severely degraded with noise and streak artifacts due to excessive X-ray quantum noise, or with view-aliasing artifacts due to insufficient angular sampling. In 2005, the nonlocal means (NLM) algorithm was introduced as a non-iterative edge-preserving filter to denoise natural images corrupted by additive Gaussian noise, and showed superior performance. It has since been adapted and applied to many other image types and various inverse problems. This paper specifically reviews the applications of the NLM algorithm in LDCT image processing and reconstruction, and explicitly demonstrates its improving effects on the reconstructed CT image quality from low-dose acquisitions. The effectiveness of these applications on LDCT and their relative performance are described in detail.

  View details for DOI 10.1002/mp.12097

  View details for PubMedID 28303644

  View details for PubMedCentralID PMC5381744

• Texture Feature Extraction and Analysis for Polyp Differentiation via Computed Tomography Colonography. IEEE transactions on medical imaging Hu, Y., Liang, Z., Song, B., Han, H., Pickhardt, P. J., Zhu, W., Duan, C., Zhang, H., Barish, M. A., Lascarides, C. E. 2016; 35 (6): 1522-31

  Abstract

  Image textures in computed tomography colonography (CTC) have great potential for differentiating non-neoplastic from neoplastic polyps and thus can advance the current CTC detection-only paradigm to a new level with diagnostic capability. However, image textures are frequently compromised, particularly in low-dose CT imaging. Furthermore, texture feature extraction may vary, depending on the polyp spatial orientation variation, resulting in variable results. To address these issues, this study proposes an adaptive approach to extract and analyze the texture features for polyp differentiation. Firstly, derivative (e.g. gradient and curvature) operations are performed on the CT intensity image to amplify the textures with adequate noise control. Then Haralick co-occurrence matrix (CM) is used to calculate texture measures along each of the 13 directions (defined by the first and second order image voxel neighbors) through the polyp volume in the intensity, gradient and curvature images. Instead of taking the mean and range of each CM measure over the 13 directions as the so-called Haralick texture features, Karhunen-Loeve transform is performed to map the 13 directions into an orthogonal coordinate system so that the resulted texture features are less dependent on the polyp orientation variation. These simple ideas for amplifying textures and stabilizing spatial variation demonstrated a significant impact for the differentiating task by experiments using 384 polyp datasets, of which 52 are non-neoplastic polyps and the rest are neoplastic polyps. By the merit of area under the curve of receiver operating characteristic, the innovative ideas achieved differentiation capability of 0.8016, indicating the CTC diagnostic feasibility.

  View details for DOI 10.1109/TMI.2016.2518958

  View details for PubMedID 26800530

  View details for PubMedCentralID PMC4891231

• Extracting Information From Previous Full-Dose CT Scan for Knowledge-Based Bayesian Reconstruction of Current Low-Dose CT Images. IEEE transactions on medical imaging Zhang, H., Han, H., Liang, Z., Hu, Y., Liu, Y., Moore, W., Ma, J., Lu, H. 2016; 35 (3): 860-70

  Abstract

  Markov random field (MRF) model has been widely employed in edge-preserving regional noise smoothing penalty to reconstruct piece-wise smooth images in the presence of noise, such as in low-dose computed tomography (LdCT). While it preserves edge sharpness, its regional smoothing may sacrifice tissue image textures, which have been recognized as useful imaging biomarkers, and thus it may compromise clinical tasks such as differentiating malignant vs. benign lesions, e.g., lung nodules or colon polyps. This study aims to shift the edge-preserving regional noise smoothing paradigm to texture-preserving framework for LdCT image reconstruction while retaining the advantage of MRF's neighborhood system on edge preservation. Specifically, we adapted the MRF model to incorporate the image textures of muscle, fat, bone, lung, etc. from previous full-dose CT (FdCT) scan as a priori knowledge for texture-preserving Bayesian reconstruction of current LdCT images. To show the feasibility of the proposed reconstruction framework, experiments using clinical patient scans were conducted. The experimental outcomes showed a dramatic gain by the a priori knowledge for LdCT image reconstruction using the commonly-used Haralick texture measures. Thus, it is conjectured that the texture-preserving LdCT reconstruction has advantages over the edge-preserving regional smoothing paradigm for texture-specific clinical applications.

  View details for DOI 10.1109/TMI.2015.2498148

  View details for PubMedID 26561284

  View details for PubMedCentralID PMC4783190

• Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Part II: An adaptive approach. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society Zhang, H., Ma, J., Wang, J., Liu, Y., Han, H., Lu, H., Moore, W., Liang, Z. 2015; 43: 26-35

  Abstract

  To reduce radiation dose in X-ray computed tomography (CT) imaging, one common strategy is to lower the tube current and exposure time settings during projection data acquisition. However, this strategy would inevitably increase the projection data noise, and the resulting image by the conventional filtered back-projection (FBP) method may suffer from excessive noise and streak artifacts. The well-known edge-preserving nonlocal means (NLM) filtering can reduce the noise-induced artifacts in the FBP reconstructed image, but it sometimes cannot completely eliminate the artifacts, especially under the very low-dose circumstance when the image is severely degraded. Instead of taking NLM filtering, we proposed a NLM-regularized statistical image reconstruction scheme, which can effectively suppress the noise-induced artifacts and significantly improve the reconstructed image quality. From our previous investigation on NLM-based strategy, we noted that using a spatially invariant filtering parameter in the regularization was rarely optimal for the entire field of view (FOV). Therefore, in this study we developed a novel strategy for designing spatially variant filtering parameters which are adaptive to the local characteristics of the image to be reconstructed. This adaptive NLM-regularized statistical image reconstruction method was evaluated with low-contrast phantoms and clinical patient data to show (1) the necessity in introducing the spatial adaptivity and (2) the efficacy of the adaptivity in achieving superiority in reconstructing CT images from low-dose acquisitions.

  View details for DOI 10.1016/j.compmedimag.2015.02.008

  View details for PubMedID 25795593

  View details for PubMedCentralID PMC4450134

• Statistical image reconstruction for low-dose CT using nonlocal means-based regularization. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society Zhang, H., Ma, J., Wang, J., Liu, Y., Lu, H., Liang, Z. 2014; 38 (6): 423-35

  Abstract

  Low-dose computed tomography (CT) imaging without sacrifice of clinical tasks is desirable due to the growing concerns about excessive radiation exposure to the patients. One common strategy to achieve low-dose CT imaging is to lower the milliampere-second (mAs) setting in data scanning protocol. However, the reconstructed CT images by the conventional filtered back-projection (FBP) method from the low-mAs acquisitions may be severely degraded due to the excessive noise. Statistical image reconstruction (SIR) methods have shown potentials to significantly improve the reconstructed image quality from the low-mAs acquisitions, wherein the regularization plays a critical role and an established family of regularizations is based on the Markov random field (MRF) model. Inspired by the success of nonlocal means (NLM) in image processing applications, in this work, we propose to explore the NLM-based regularization for SIR to reconstruct low-dose CT images from low-mAs acquisitions. Experimental results with both digital and physical phantoms consistently demonstrated that SIR with the NLM-based regularization can achieve more gains than SIR with the well-known Gaussian MRF regularization or the generalized Gaussian MRF regularization and the conventional FBP method, in terms of image noise reduction and resolution preservation.

  View details for DOI 10.1016/j.compmedimag.2014.05.002

  View details for PubMedID 24881498

  View details for PubMedCentralID PMC4152958

• Low-mAs X-ray CT image reconstruction by adaptive-weighted TV-constrained penalized re-weighted least-squares. Journal of X-ray science and technology Liu, Y., Ma, J., Zhang, H., Wang, J., Liang, Z. 2014; 22 (4): 437-57

  Abstract

  The negative effects of X-ray exposure, such as inducing genetic and cancerous diseases, has arisen more attentions.This paper aims to investigate a penalized re-weighted least-square (PRWLS) strategy for low-mAs X-ray computed tomography image reconstruction by incorporating an adaptive weighted total variation (AwTV) penalty term and a noise variance model of projection data.An AwTV penalty is introduced in the objective function by considering both piecewise constant property and local nearby intensity similarity of the desired image. Furthermore, the weight of data fidelity term in the objective function is determined by our recent study on modeling variance estimation of projection data in the presence of electronic background noise.The presented AwTV-PRWLS algorithm can achieve the highest full-width-at-half-maximum (FWHM) measurement, for data conditions of (1) full-view 10 mA acquisition and (2) sparse-view 80 mA acquisition. In comparison between the AwTV/TV-PRWLS strategies and the previous reported AwTV/TV-projection onto convex sets (AwTV/TV-POCS) approaches, the former can gain in terms of FWHM for data condition (1), but cannot gain for the data condition (2).In the case of full-view 10 mA projection data, the presented AwTV-PRWLS shows potential improvement. However, in the case of sparse-view 80 mA projection data, the AwTV/TV-POCS shows advantage over the PRWLS strategies.

  View details for DOI 10.3233/XST-140437

  View details for PubMedID 25080113

  View details for PubMedCentralID PMC4141624

• Integration of 3D scale-based pseudo-enhancement correction and partial volume image segmentation for improving electronic colon cleansing in CT colonograpy. Journal of X-ray science and technology Zhang, H., Li, L., Zhu, H., Han, H., Song, B., Liang, Z. 2014; 22 (2): 271-83

  Abstract

  Orally administered tagging agents are usually used in CT colonography (CTC) to differentiate residual bowel content from native colonic structures. However, the high-density contrast agents tend to introduce pseudo-enhancement (PE) effect on neighboring soft tissues and elevate their observed CT attenuation value toward that of the tagged materials (TMs), which may result in an excessive electronic colon cleansing (ECC) since the pseudo-enhanced soft tissues are incorrectly identified as TMs. To address this issue, we integrated a 3D scale-based PE correction into our previous ECC pipeline based on the maximum a posteriori expectation-maximization partial volume (PV) segmentation. The newly proposed ECC scheme takes into account both the PE and PV effects that commonly appear in CTC images. We evaluated the new scheme on 40 patient CTC scans, both qualitatively through display of segmentation results, and quantitatively through radiologists' blind scoring (human observer) and computer-aided detection (CAD) of colon polyps (computer observer). Performance of the presented algorithm has shown consistent improvements over our previous ECC pipeline, especially for the detection of small polyps submerged in the contrast agents. The CAD results of polyp detection showed that 4 more submerged polyps were detected for our new ECC scheme over the previous one.

  View details for DOI 10.3233/XST-140424

  View details for PubMedID 24699352

  View details for PubMedCentralID PMC3979539

• Deriving adaptive MRF coefficients from previous normal-dose CT scan for low-dose image reconstruction via penalized weighted least-squares minimization. Medical physics Zhang, H., Han, H., Wang, J., Ma, J., Liu, Y., Moore, W., Liang, Z. 2014; 41 (4): 041916

  Abstract

  Repeated computed tomography (CT) scans are required for some clinical applications such as image-guided interventions. To optimize radiation dose utility, a normal-dose scan is often first performed to set up reference, followed by a series of low-dose scans for intervention. One common strategy to achieve the low-dose scan is to lower the x-ray tube current and exposure time (mAs) or tube voltage (kVp) setting in the scanning protocol, but the resulted image quality by the conventional filtered back-projection (FBP) method may be severely degraded due to the excessive noise. Penalized weighted least-squares (PWLS) image reconstruction has shown the potential to significantly improve the image quality from low-mAs acquisitions, where the penalty plays an important role. In this work, the authors' explore an adaptive Markov random field (MRF)-based penalty term by utilizing previous normal-dose scan to improve the subsequent low-dose scans image reconstruction.In this work, the authors employ the widely-used quadratic-form MRF as the penalty model and explore a novel idea of using the previous normal-dose scan to obtain the MRF coefficients for adaptive reconstruction of the low-dose images. In the coefficients determination, the authors further explore another novel idea of using the normal-dose scan to obtain a scale map, which describes an optimal neighborhood for the coefficients determination such that a local uniform region has a small spread of frequency spectrum and, therefore, a small MRF window, and vice versa. The proposed penalty term is incorporated into the PWLS image reconstruction framework, and the low-dose images are reconstructed via the PWLS minimization.The presented adaptive MRF based PWLS algorithm was validated by physical phantom and patient data. The experimental results demonstrated that the presented algorithm is superior to the PWLS reconstruction using the conventional Gaussian MRF penalty or the edge-preserving Huber penalty and the conventional FBP method, in terms of image noise reduction and edge/detail/contrast preservation.This study demonstrated the feasibility and efficacy of the proposed scheme in utilizing previous normal-dose CT scan to improve the subsequent low-dose scans.

  View details for DOI 10.1118/1.4869160

  View details for PubMedID 24694147

  View details for PubMedCentralID PMC3971828

• Total variation-stokes strategy for sparse-view X-ray CT image reconstruction. IEEE transactions on medical imaging Liu, Y., Liang, Z., Ma, J., Lu, H., Wang, K., Zhang, H., Moore, W. 2014; 33 (3): 749-63

  Abstract

  Previous studies have shown that by minimizing the total variation (TV) of the to-be-estimated image with some data and/or other constraints, a piecewise-smooth X-ray computed tomography image can be reconstructed from sparse-view projection data. However, due to the piecewise constant assumption for the TV model, the reconstructed images are frequently reported to suffer from the blocky or patchy artifacts. To eliminate this drawback, we present a total variation-stokes-projection onto convex sets (TVS-POCS) reconstruction method in this paper. The TVS model is derived by introducing isophote directions for the purpose of recovering possible missing information in the sparse-view data situation. Thus the desired consistencies along both the normal and the tangent directions are preserved in the resulting images. Compared to the previous TV-based image reconstruction algorithms, the preserved consistencies by the TVS-POCS method are expected to generate noticeable gains in terms of eliminating the patchy artifacts and preserving subtle structures. To evaluate the presented TVS-POCS method, both qualitative and quantitative studies were performed using digital phantom, physical phantom and clinical data experiments. The results reveal that the presented method can yield images with several noticeable gains, measured by the universal quality index and the full-width-at-half-maximum merit, as compared to its corresponding TV-based algorithms. In addition, the results further indicate that the TVS-POCS method approaches to the gold standard result of the filtered back-projection reconstruction in the full-view data case as theoretically expected, while most previous iterative methods may fail in the full-view case because of their artificial textures in the results.

  View details for DOI 10.1109/TMI.2013.2295738

  View details for PubMedID 24595347

  View details for PubMedCentralID PMC3950963

• A unified EM approach to bladder wall segmentation with coupled level-set constraints. Medical image analysis Han, H., Li, L., Duan, C., Zhang, H., Zhao, Y., Liang, Z. 2013; 17 (8): 1192-205

  Abstract

  Magnetic resonance (MR) imaging-based virtual cystoscopy (VCys), as a non-invasive, safe and cost-effective technique, has shown its promising virtue for early diagnosis and recurrence management of bladder carcinoma. One primary goal of VCys is to identify bladder lesions with abnormal bladder wall thickness, and consequently a precise segmentation of the inner and outer borders of the wall is required. In this paper, we propose a unified expectation-maximization (EM) approach to the maximum-a posteriori (MAP) solution of bladder wall segmentation, by integrating a novel adaptive Markov random field (AMRF) model and the coupled level-set (CLS) information into the prior term. The proposed approach is applied to the segmentation of T(1)-weighted MR images, where the wall is enhanced while the urine and surrounding soft tissues are suppressed. By introducing scale-adaptive neighborhoods as well as adaptive weights into the conventional MRF model, the AMRF model takes into account the local information more accurately. In order to mitigate the influence of image artifacts adjacent to the bladder wall and to preserve the continuity of the wall surface, we apply geometrical constraints on the wall using our previously developed CLS method. This paper not only evaluates the robustness of the presented approach against the known ground truth of simulated digital phantoms, but further compares its performance with our previous CLS approach via both volunteer and patient studies. Statistical analysis on experts' scores of the segmented borders from both approaches demonstrates that our new scheme is more effective in extracting the bladder wall. Based on the wall thickness calibrated from the segmented single-layer borders, a three-dimensional virtual bladder model can be constructed and the wall thickness can be mapped onto the model, where the bladder lesions will be eventually detected via experts' visualization and/or computer-aided detection.

  View details for DOI 10.1016/j.media.2013.08.002

  View details for PubMedID 24001932

  View details for PubMedCentralID PMC3795818