Bio


Dr. Syed is a member of the divisions of Pediatric Radiology and Body MRI and serves as the Director of MRI for Stanford Medicine Children's Health. His clinical interests include MR imaging of pediatric and adult hepatobiliary disorders, inflammatory bowel disease, gynecologic pathology, and congenital heart disease. He is also an active researcher, collaborating with fellow engineers and scientists at Stanford to translate technical innovations in MRI into improved patient care. His recent work focuses on translation of machine learning techniques for rapid, robust MRI in children and adults.

Clinical Focus


  • Diagnostic Radiology

Professional Education


  • Board Certification: American Board of Radiology, Diagnostic Radiology (2021)
  • Fellowship: Stanford University Radiology Fellowships (2020) CA
  • Residency: Thomas Jefferson University Radiology Residency (2019) PA
  • Internship: Crozer Chester Medical Center Transitional Year Program (2015) PA
  • Medical Education: Temple University School of Medicine Registrar (2014) PA

All Publications


  • MR and Ultrasound Elastography for Fibrosis Assessment in Children: Practical Implementation and Supporting Evidence-AJR Expert Panel Narrative Review. AJR. American journal of roentgenology Serai, S. D., Franchi-Abella, S., Syed, A. B., Tkach, J. A., Toso, S., Ferraioli, G. 2024

    Abstract

    Quantitative MRI and ultrasound biomarkers of liver fibrosis have become important tools in the diagnosis and clinical management of children with chronic liver disease (CLD). In particular, MR elastography (MRE) is now routinely performed in clinical practice to evaluate the liver for fibrosis. Ultrasound shear-wave elastography has also become widely performed for this purpose, especially in young children. These noninvasive methods are increasingly used to replace liver biopsy for the diagnosis, quantitative staging, and treatment monitoring of patients with CLD. Although ultrasound has advantages of portability and lower equipment cost, available evidence indicates that MRI may have greater reliability and accuracy in liver fibrosis evaluation. In this AJR Expert Panel Narrative Review, we describe how, why, and when to use MRI- and ultrasound-based elastography methods for liver fibrosis assessment in children. Practical approaches are discussed for adapting and optimizing these methods in children, with consideration of clinical indications, patient preparation, equipment requirements, acquisition technique, as well as pitfalls and confounding factors. Guidance is provided for interpretation and reporting, and representative case examples are presented.

    View details for DOI 10.2214/AJR.23.30506

    View details for PubMedID 38170833

  • Abbreviated cardiac magnetic resonance imaging versus echocardiography for interval assessment of systolic function in Duchenne muscular dystrophy: patient satisfaction, clinical utility, and image quality. The international journal of cardiovascular imaging Chandrasekar, H., Kaufman, B. D., Beattie, M. J., Ennis, D. B., Syed, A. B., Zucker, E. J., Maskatia, S. A. 2023

    Abstract

    Poor acoustic windows make interval assessment of systolic function in patients with (Duchenne Muscular Dystrophy) DMD by echocardiography (echo) difficult. Cardiac magnetic resonance imaging (CMR) can be challenging in DMD patients due to study duration and patient discomfort. We developed an abbreviated CMR (aCMR) protocol and hypothesized that aCMR would compare favorably to echo in image quality and clinical utility without significant differences in exam duration, patient satisfaction, and functional measurements.DMD patients were recruited prospectively to undergo echo and aCMR. Modalities were compared with a global quality assessment score (GQAS), clinical utility score (CUS), and patient satisfaction score (PSS). Results were compared using Wilcoxon signed-rank tests, Spearman correlations, intraclass correlations, and Bland-Altman analyses.Nineteen DMD patients were included. PSS scores and exam duration were equivalent between modalities, while CUS and GQAS scores favored aCMR. ACMR scored markedly higher than echo in RV visualization and assessment of atrial size. Older age was negatively correlated with echo GQAS and CUS scores, as well as aCMR PSS scores. Higher BMI was positively correlated with aCMR GQAS scores. Nighttime PPV requirement and non-ambulatory status were correlated with worse echo CUS scores. Poor image quality precluding quantification existed in five (26%) echo and zero (0%) aCMR studies. There was moderate correlation between aCMR and echo for global circumferential strain and left ventricular four chamber global longitudinal strain.The aCMR protocol resulted in improved clinical relevance and quality scores relative to echo, without significant detriment to patient satisfaction or exam duration.

    View details for DOI 10.1007/s10554-023-02977-w

    View details for PubMedID 37831292

    View details for PubMedCentralID 8756173

  • "Percutaneous" technique for direct external access to and stenting of obstructed pediatric ventricular assist device inflow cannula. JTCVS techniques Taylor, A., Lee, K. J., Felmly, L., Syed, A., Almond, C., Shuttleworth, P., Issapour, A., Babb, A., Ma, M., Martin, E. 2023; 21: 195-198

    View details for DOI 10.1016/j.xjtc.2023.07.024

    View details for PubMedID 37854820

    View details for PubMedCentralID PMC10580173

  • Magnetic resonance neurography techniques in the pediatric population. Pediatric radiology Jayapal, P., Alharthi, O., Young, V., Obi, C., Syed, A. B., Sandberg, J. K. 2023

    Abstract

    The use of magnetic resonance imaging (MRI) in the evaluation of the central extracranial nervous system, namely the brachial and lumbosacral plexuses, is well established and has been performed for many years. Only recently after numerous advances in MRI, has image quality been sufficient to properly visualize small structures, such as nerves in the extremities. Despite the advances, peripheral MR Neurography remains a complex and difficult examination to perform, especially in the pediatric patient population, in which the risk for motion artifact and compliance is always of concern. Thus, technical aspects of the MR imaging protocol must be flexible but robust, to balance image quality with scan time, in a patient population of varying sizes. An additional important step for reliably performing a successful MR Neurography examination is the non-technical pre-imaging preparation, which includes patient/family education and open communication with referring teams. This paper will discuss in detail the individual technical and non-technical/operational aspects of peripheral MR Neurography, to help guide in building a successful program in the pediatric population.

    View details for DOI 10.1007/s00247-023-05759-7

    View details for PubMedID 37710037

  • Cancer Therapy-related Hepatic Injury in Children: Imaging Review from the Pediatric LI-RADS Working Group. Radiographics : a review publication of the Radiological Society of North America, Inc Morin, C. E., Kolbe, A. B., Alazraki, A., Chavhan, G. B., Gill, A., Infante, J., Khanna, G., Nguyen, H. N., O'Neill, A. F., Rees, M. A., Sharma, A., Squires, J. E., Squires, J. H., Syed, A. B., Tang, E. R., Towbin, A. J., Schooler, G. R. 2023; 43 (9): e230007

    Abstract

    The liver is the primary organ for the metabolism of many chemotherapeutic agents. Treatment-induced liver injury is common in children undergoing cancer therapy. Hepatic injury occurs due to various mechanisms, including biochemical cytotoxicity, hepatic vascular injury, radiation-induced cytotoxicity, and direct hepatic injury through minimally invasive and invasive surgical treatments. Treatment-induced liver injury can be seen contemporaneous with therapy and months to years after therapy is complete. Patients can develop a combination of hepatic injuries manifesting during and after treatment. Acute toxic effects of cancer therapy in children include hepatitis, steatosis, steatohepatitis, cholestasis, hemosiderosis, and vascular injury. Longer-term effects of cancer therapy include hepatic fibrosis, chronic liver failure, and development of focal liver lesions. Quantitative imaging techniques can provide useful metrics for disease diagnosis and monitoring, especially in treatment-related diffuse liver injury such as hepatic steatosis and steatohepatitis, hepatic iron deposition, and hepatic fibrosis. Focal liver lesions, including those developing as a result of treatment-related vascular injury such as focal nodular hyperplasia-like lesions and hepatic perfusion anomalies, as well as hepatic infections occurring as a consequence of immune suppression, can be anxiety provoking and confused with recurrent malignancy or hepatic metastases, although there often are imaging features that help elucidate the correct diagnosis. Radiologic evaluation, in conjunction with clinical and biochemical screening, is integral to diagnosing and monitoring hepatic complications of cancer therapy in pediatric patients during therapy and after therapy completion for long-term surveillance. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material See the invited commentary by Ferraciolli and Gee in this issue.

    View details for DOI 10.1148/rg.230007

    View details for PubMedID 37616168

  • 4D Flow cardiovascular magnetic resonance consensus statement: 2023 update. Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance Bissell, M. M., Raimondi, F., Ait Ali, L., Allen, B. D., Barker, A. J., Bolger, A., Burris, N., Carhäll, C. J., Collins, J. D., Ebbers, T., Francois, C. J., Frydrychowicz, A., Garg, P., Geiger, J., Ha, H., Hennemuth, A., Hope, M. D., Hsiao, A., Johnson, K., Kozerke, S., Ma, L. E., Markl, M., Martins, D., Messina, M., Oechtering, T. H., van Ooij, P., Rigsby, C., Rodriguez-Palomares, J., Roest, A. A., Roldán-Alzate, A., Schnell, S., Sotelo, J., Stuber, M., Syed, A. B., Töger, J., van der Geest, R., Westenberg, J., Zhong, L., Zhong, Y., Wieben, O., Dyverfeldt, P. 2023; 25 (1): 40

    Abstract

    Hemodynamic assessment is an integral part of the diagnosis and management of cardiovascular disease. Four-dimensional cardiovascular magnetic resonance flow imaging (4D Flow CMR) allows comprehensive and accurate assessment of flow in a single acquisition. This consensus paper is an update from the 2015 '4D Flow CMR Consensus Statement'. We elaborate on 4D Flow CMR sequence options and imaging considerations. The document aims to assist centers starting out with 4D Flow CMR of the heart and great vessels with advice on acquisition parameters, post-processing workflows and integration into clinical practice. Furthermore, we define minimum quality assurance and validation standards for clinical centers. We also address the challenges faced in quality assurance and validation in the research setting. We also include a checklist for recommended publication standards, specifically for 4D Flow CMR. Finally, we discuss the current limitations and the future of 4D Flow CMR. This updated consensus paper will further facilitate widespread adoption of 4D Flow CMR in the clinical workflow across the globe and aid consistently high-quality publication standards.

    View details for DOI 10.1186/s12968-023-00942-z

    View details for PubMedID 37474977

    View details for PubMedCentralID PMC10357639

  • Assessment of T2-weighted Image Quality at Prostate MRI in Patients with and Those without Intramuscular Injection of Glucagon. Radiology. Imaging cancer Sundaram, K. M., Rosenberg, J., Syed, A. B., Chang, S. T., Loening, A. M. 2023; 5 (3): e220070

    Abstract

    Purpose To assess whether administration of intramuscular (IM) glucagon improves T2-weighted image quality at multiparametric MRI (mpMRI) of the prostate. Materials and Methods In this Health Insurance Portability and Accountability Act-compliant single-center study, the authors retrospectively analyzed radiology reports from 3960 mpMRI examinations (2495 after exclusions) performed between September 2013 and September 2019 and performed outcome comparisons and semiquantitative image assessment of axial T2-weighted images from 120 consecutive mpMRI examinations performed between May 2015 and February 2016. Three experienced radiologists blinded to administration of IM glucagon assessed images using a five-point Likert scale (5 = no motion or blur) for overall image quality, anatomic delineation (prostate capsule, rectum, and lymph nodes), and identification of benign prostatic hyperplasia nodules. Wilcoxon rank sum and χ2 tests were used to assess quantitative parameters. Results The number of mpMRI radiology reports (599 examinations performed with glucagon; 1896, without glucagon) mentioning blur or motion were similar between groups (P = .82). Regression analysis of semiquantitative image quality assessments of T2-weighted images from mpMRI examinations (60 performed with glucagon; 60, without glucagon) demonstrated that images with glucagon were more likely to receive higher scores (4 or 5 rating) than those without glucagon only when the rectum (P = .001) and lymph nodes (P = .01) were evaluated, not when the prostatic capsule, benign prostatic hyperplasia nodules, or overall image quality was evaluated. No evidence of differences was found in identified Prostate Imaging Reporting and Data System (PI-RADS) lesions or targeted-biopsy Gleason scores. Conclusion Administration of IM glucagon did not improve T2-weighted image quality in prostate MRI examinations and showed similar PI-RADS scores and biopsy yields compared with examinations without glucagon. Keywords: MRI, Genital/Reproductive, Urinary, Prostate, Oncology, Observer Performance © RSNA, 2023 Online supplemental material is available for this article. See also commentary by Eberhardt in this issue.

    View details for DOI 10.1148/rycan.220070

    View details for PubMedID 37171269

  • Case Series of Precision Delivery of Methylprednisolone in Pediatric Inflammatory Bowel Disease: Feasibility, Clinical Outcomes, and Identification of a Vasculitic Transcriptional Program. Journal of clinical medicine Levitte, S., Yarani, R., Ganguly, A., Martin, L., Gubatan, J., Nadel, H. R., Franc, B., Gugig, R., Syed, A., Goyal, A., Park, K. T., Thakor, A. S. 2023; 12 (6)

    Abstract

    Systemic steroid exposure, while useful for the treatment of acute flares in inflammatory bowel disease (IBD), is associated with an array of side effects that are particularly significant in children. Technical advancements have enabled locoregional intraarterial steroid delivery directly into specific segments of the gastrointestinal tract, thereby maximizing tissue concentration while limiting systemic exposure. We investigated the feasibility of intraarterial steroid administration into the bowel in a cohort of nine pediatric patients who had IBD. This treatment approach provided symptom relief in all patients, with sustained relief (>2 weeks) in seven out of nine; no serious adverse effects occurred in any patient. In addition, we identified patterns of vascular morphologic changes indicative of a vasculopathy within the mesenteric circulation of inflamed segments of the bowel in pediatric patients with Crohn's disease, which correlated with disease activity. An analysis of publicly available transcriptomic studies identified vasculitis-associated molecular pathways activated in the endothelial cells of patients with active Crohn's disease, suggesting a possible shared transcriptional program between vasculitis and IBD. Intraarterial corticosteroid treatment is safe and has the potential to be widely accepted as a locoregional approach for therapy delivery directly into the bowel; however, this approach still warrants further consideration as a short-term "bridge" between therapy transitions for symptomatic IBD patients with refractory disease, as part of a broader steroid-minimizing treatment strategy.

    View details for DOI 10.3390/jcm12062386

    View details for PubMedID 36983386

  • Automated MRI Field of View Prescription from Region of Interest Prediction by Intra-Stack Attention Neural Network. Bioengineering (Basel, Switzerland) Lei, K., Syed, A. B., Zhu, X., Pauly, J. M., Vasanawala, S. V. 2023; 10 (1)

    Abstract

    Manual prescription of the field of view (FOV) by MRI technologists is variable and prolongs the scanning process. Often, the FOV is too large or crops critical anatomy. We propose a deep learning framework, trained by radiologists' supervision, for automating FOV prescription. An intra-stack shared feature extraction network and an attention network are used to process a stack of 2D image inputs to generate scalars defining the location of a rectangular region of interest (ROI). The attention mechanism is used to make the model focus on a small number of informative slices in a stack. Then, the smallest FOV that makes the neural network predicted ROI free of aliasing is calculated by an algebraic operation derived from MR sampling theory. The framework's performance is examined quantitatively with intersection over union (IoU) and pixel error on position and qualitatively with a reader study. The proposed model achieves an average IoU of 0.867 and an average ROI position error of 9.06 out of 512 pixels on 80 test cases, significantly better than two baseline models and not significantly different from a radiologist. Finally, the FOV given by the proposed framework achieves an acceptance rate of 92% from an experienced radiologist.

    View details for DOI 10.3390/bioengineering10010092

    View details for PubMedID 36671663

  • Pancreatic Fluid Leak Causing Mediastinal Shift JOURNAL OF PEDIATRIC GASTROENTEROLOGY AND NUTRITION Herdes, R. E., Syed, A. B., Gugig, R. 2023; 76 (1): E20
  • Deep Learning-Based Water-Fat Separation from Dual-Echo Chemical Shift-Encoded Imaging. Bioengineering (Basel, Switzerland) Wu, Y., Alley, M., Li, Z., Datta, K., Wen, Z., Sandino, C., Syed, A., Ren, H., Xing, L., Lustig, M., Pauly, J., Vasanawala, S. 2022; 9 (10)

    Abstract

    Conventional water-fat separation approaches suffer long computational times and are prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual-echo water-fat separation method. With IRB approval, raw data from 68 pediatric clinically indicated dual echo scans were analyzed, corresponding to 19382 contrast-enhanced images. A densely connected hierarchical convolutional network was constructed, in which dual-echo images and corresponding echo times were used as input and water/fat images obtained using the projected power method were regarded as references. Models were trained and tested using knee images with 8-fold cross validation and validated on out-of-distribution data from the ankle, foot, and arm. Using the proposed method, the average computational time for a volumetric dataset with ~400 slices was reduced from 10 min to under one minute. High fidelity was achieved (correlation coefficient of 0.9969, l1 error of 0.0381, SSIM of 0.9740, pSNR of 58.6876) and water/fat swaps were mitigated. I is of particular interest that metal artifacts were substantially reduced, even when the training set contained no images with metallic implants. Using the models trained with only contrast-enhanced images, water/fat images were predicted from non-contrast-enhanced images with high fidelity. The proposed water-fat separation method has been demonstrated to be fast, robust, and has the added capability to compensate for metal artifacts.

    View details for DOI 10.3390/bioengineering9100579

    View details for PubMedID 36290546

  • Pancreatic Fluid Leak Causing Mediastinal Shift. Journal of pediatric gastroenterology and nutrition Herdes, R. E., Syed, A. B., Gugig, R. 2022

    View details for DOI 10.1097/MPG.0000000000003640

    View details for PubMedID 36245077

  • Accelerated two-dimensional phase-contrast for cardiovascular MRI using deep learning-based reconstruction with complex difference estimation. Magnetic resonance in medicine Oscanoa, J. A., Middione, M. J., Syed, A. B., Sandino, C. M., Vasanawala, S. S., Ennis, D. B. 2022

    Abstract

    PURPOSE: To develop and validate a deep learning-based reconstruction framework for highly accelerated two-dimensional (2D) phase contrast (PC-MRI) data with accurate and precise quantitative measurements.METHODS: We propose a modified DL-ESPIRiT reconstruction framework for 2D PC-MRI, comprised of an unrolled neural network architecture with a Complex Difference estimation (CD-DL). CD-DL was trained on 155 fully sampled 2D PC-MRI pediatric clinical datasets. The fully sampled data ( n = 29 $$ n=29 $$ ) was retrospectively undersampled (6-11 * $$ \times $$ ) and reconstructed using CD-DL and a parallel imaging and compressed sensing method (PICS). Measurements of peak velocity and total flow were compared to determine the highest acceleration rate that provided accuracy and precision within ± 5 % $$ \pm 5\% $$ . Feasibility of CD-DL was demonstrated on prospectively undersampled datasets acquired in pediatric clinical patients ( n = 5 $$ n=5 $$ ) and compared to traditional parallel imaging (PI) and PICS.RESULTS: The retrospective evaluation showed that 9 * $$ \times $$ accelerated 2D PC-MRI images reconstructed with CD-DL provided accuracy and precision (bias, [95 % $$ \% $$ confidence intervals]) within ± 5 % $$ \pm 5\% $$ . CD-DL showed higher accuracy and precision compared to PICS for measurements of peak velocity (2.8 % $$ \% $$ [ - 2 . 9 $$ -2.9 $$ , 4.5] vs. 3.9 % $$ \% $$ [ - 11 . 0 $$ -11.0 $$ , 4.9]) and total flow (1.8 % $$ \% $$ [ - 3 . 9 $$ -3.9 $$ , 3.4] vs. 2.9 % $$ \% $$ [ - 7 . 1 $$ -7.1 $$ , 6.9]). The prospective feasibility study showed that CD-DL provided higher accuracy and precision than PICS for measurements of peak velocity and total flow.CONCLUSION: In a retrospective evaluation, CD-DL produced quantitative measurements of 2D PC-MRI peak velocity and total flow with ≤ 5 % $$ \le 5\% $$ error in both accuracy and precision for up to 9 * $$ \times $$ acceleration. Clinical feasibility was demonstrated using a prospective clinical deployment of our 8 * $$ \times $$ undersampled acquisition and CD-DL reconstruction in a cohort of pediatric patients.

    View details for DOI 10.1002/mrm.29441

    View details for PubMedID 36093915

  • Rapid fat-water separated T1 mapping using a single shot radial inversion-recovery spoiled gradient recalled pulse sequence. NMR in biomedicine Li, Z., Mathew, M., Syed, A. B., Feng, L., Brunsing, R., Pauly, J. M., Vasanawala, S. S. 2022

    Abstract

    T1 mapping is increasingly used in clinical practice and research studies. With limited scan time, existing techniques often have limited spatial resolution, contrast resolution, and slice coverage. High fat concentrations yield complex errors in Look-Locker T1 methods. In this study, a dual-echo 2D radial IR T1 (DEradIR-T1) technique was developed for fast fat/water-separated T1 mapping. The DEradIR-T1 technique was tested in phantoms, 5 volunteers and 28 patients using a 3T clinical MRI scanner. In our study, simulations were performed to analyze the composite (fat + water) and water-only T1 under different echo times (TEs). In standardized phantoms, an inversion-recovery spin echo (IR-SE) sequence with and without fat saturation pulses served as a T1 reference. Parameter mapping with DEradIR-T1 was also assessed in vivo and values were compared with modified Look-Locker inversion recovery (MOLLI). Bland-Altman analysis and two-tailed paired t-test were used to compare the parameter maps from DEradIR-T1 with the references. Simulations of the composite and water-only T1 under different TEs and levels of fat matched the in vivo studies. T1 maps from DEradIR-T1 on a NIST phantom (PComp =0.97) and a Calimetrix fat/water phantom (PWater = 0.56) matched with the references. In vivo T1 was compared with that of MOLLI: R Comp 2 = 0.77 ; R water 2 = 0.72 . In this work, intravoxel fat is found to have a variable, echo-time dependent effect on measured T1 values, and this effect may be mitigated using the proposed DRradIR-T1.

    View details for DOI 10.1002/nbm.4803

    View details for PubMedID 35891586

  • Towards identifying predictors of pediatric heart only versus combined heart liver transplantation Zhang, K., Chen, S., Syed, A., Gallo, A., Esquivel, C., Bonham, A., Hollander, S. A., Ma, M., Han, J., Ebel, N. H. WILEY. 2022
  • Artifact- and content-specific quality assessment for MRI with image rulers. Medical image analysis Lei, K., Syed, A. B., Zhu, X., Pauly, J. M., Vasanawala, S. S. 1800; 77: 102344

    Abstract

    In clinical practice MR images are often first seen by radiologists long after the scan. If image quality is inadequate either patients have to return for an additional scan, or a suboptimal interpretation is rendered. An automatic image quality assessment (IQA) would enable real-time remediation. Existing IQA works for MRI give only a general quality score, agnostic to the cause of and solution to low-quality scans. Furthermore, radiologists' image quality requirements vary with the scan type and diagnostic task. Therefore, the same score may have different implications for different scans. We propose a framework with multi-task CNN model trained with calibrated labels and inferenced with image rulers. Labels calibrated by human inputs follow a well-defined and efficient labeling task. Image rulers address varying quality standards and provide a concrete way of interpreting raw scores from the CNN. The model supports assessments of two of the most common artifacts in MRI: noise and motion. It achieves accuracies of around 90%, 6% better than the best previous method examined, and 3% better than human experts on noise assessment. Our experiments show that label calibration, image rulers, and multi-task training improve the model's performance and generalizability.

    View details for DOI 10.1016/j.media.2021.102344

    View details for PubMedID 35091278

  • Free-breathing R 2 ∗ mapping of hepatic iron overload in children using 3D multi-echo UTE cones MRI. Magnetic resonance in medicine Kee, Y. n., Sandino, C. M., Syed, A. B., Cheng, J. Y., Shimakawa, A. n., Colgan, T. J., Hernando, D. n., Vasanawala, S. S. 2021

    Abstract

    To enable motion-robust, ungated, free-breathing R 2 ∗ mapping of hepatic iron overload in children with 3D multi-echo UTE cones MRI.A golden-ratio re-ordered 3D multi-echo UTE cones acquisition was developed with chemical-shift encoding (CSE). Multi-echo complex-valued source images were reconstructed via gridding and coil combination, followed by confounder-corrected R 2 ∗ (=1/ T 2 ∗ ) mapping. A phantom containing 15 different concentrations of gadolinium solution (0-300 mM) was imaged at 3T. 3D multi-echo UTE cones with an initial TE of 0.036 ms and Cartesian CSE-MRI (IDEAL-IQ) sequences were performed. With institutional review board approval, 85 subjects (81 pediatric patients with iron overload + 4 healthy volunteers) were imaged at 3T using 3D multi-echo UTE cones with free breathing (FB cones), IDEAL-IQ with breath holding (BH Cartesian), and free breathing (FB Cartesian). Overall image quality of R 2 ∗ maps was scored by 2 blinded experts and compared by a Wilcoxon rank-sum test. For each pediatric subject, the paired R 2 ∗ maps were assessed to determine if a corresponding artifact-free 15 mm region-of-interest (ROI) could be identified at a mid-liver level on both images. Agreement between resulting R 2 ∗ quantification from FB cones and BH/FB Cartesian was assessed with Bland-Altman and linear correlation analyses.ROI-based regression analysis showed a linear relationship between gadolinium concentration and R 2 ∗ in IDEAL-IQ (y = 8.83x - 52.10, R2 = 0.995) as well as in cones (y = 9.19x - 64.16, R2 = 0.992). ROI-based Bland-Altman analysis showed that the mean difference (MD) was 0.15% and the SD was 5.78%. However, IDEAL-IQ R 2 ∗ measurements beyond 200 mM substantially deviated from a linear relationship for IDEAL-IQ (y = 5.85x + 127.61, R2 = 0.827), as opposed to cones (y = 10.87x - 166.96, R2 = 0.984). In vivo, FB cones R 2 ∗ had similar image quality with BH and FB Cartesian in 15 and 42 cases, respectively. FB cones R 2 ∗ had better image quality scores than BH and FB Cartesian in 3 and 21 cases, respectively, where BH/FB Cartesian exhibited severe ghosting artifacts. ROI-based Bland-Altman analyses were 2.23% (MD) and 6.59% (SD) between FB cones and BH Cartesian and were 0.21% (MD) and 7.02% (SD) between FB cones and FB Cartesian, suggesting a good agreement between FB cones and BH (FB) Cartesian R 2 ∗ . Strong linear relationships were observed between BH Cartesian and FB cones (y = 1.00x + 1.07, R2 = 0.996) and FB Cartesian and FB cones (y = 0.98x + 1.68, R2 = 0.999).Golden-ratio re-ordered 3D multi-echo UTE Cones MRI enabled motion-robust, ungated, and free-breathing R 2 ∗ mapping of hepatic iron overload, with comparable R 2 ∗ measurements and image quality to BH Cartesian, and better image quality than FB Cartesian.

    View details for DOI 10.1002/mrm.28610

    View details for PubMedID 33432613

  • Rosette Trajectories Enable Ungated, Motion-Robust, Simultaneous Cardiac and Liver T2 * Iron Assessment. Journal of magnetic resonance imaging : JMRI Bush, A. M., Sandino, C. M., Ramachandran, S., Ong, F., Dwork, N., Zucker, E. J., Syed, A. B., Pauly, J. M., Alley, M. T., Vasanawala, S. S. 2020: e27196

    Abstract

    BACKGROUND: Quantitative T2 * MRI is the standard of care for the assessment of iron overload. However, patient motion corrupts T2 * estimates.PURPOSE: To develop and evaluate a motion-robust, simultaneous cardiac and liver T2 * imaging approach using non-Cartesian, rosette sampling and a model-based reconstruction as compared to clinical-standard Cartesian MRI.STUDY TYPE: Prospective.PHANTOM/POPULATION: Six ferumoxytol-containing phantoms (26-288mug/mL). Eight healthy subjects and 18 patients referred for clinically indicated iron overload assessment.FIELD STRENGTH/SEQUENCE: 1.5T, 2D Cartesian and rosette gradient echo (GRE) ASSESSMENT: GRE T2 * values were validated in ferumoxytol phantoms. In healthy subjects, test-retest and spatial coefficient of variation (CoV) analysis was performed during three breathing conditions. Cartesian and rosette T2 * were compared using correlation and Bland-Altman analysis. Images were rated by three experienced radiologists on a 5-point scale.STATISTICAL TESTS: Linear regression, analysis of variance (ANOVA), and paired Student's t-testing were used to compare reproducibility and variability metrics in Cartesian and rosette scans. The Wilcoxon rank test was used to assess reader score comparisons and reader reliability was measured using intraclass correlation analysis.RESULTS: Rosette R2* (1/T2 *) was linearly correlated with ferumoxytol concentration (r2 = 1.00) and not significantly different than Cartesian values (P = 0.16). During breath-holding, ungated rosette liver and heart T2 * had lower spatial CoV (liver: 18.4±9.3% Cartesian, 8.8%±3.4% rosette, P = 0.02, heart: 37.7%±14.3% Cartesian, 13.4%±1.7% rosette, P = 0.001) and higher-quality scores (liver: 3.3 [3.0-3.6] Cartesian, 4.7 [4.1-4.9] rosette, P = 0.005, heart: 3.0 [2.3-3] Cartesian, 4.5 [3.8-5.0] rosette, P = 0.005) compared to Cartesian values. During free-breathing and failed breath-holding, Cartesian images had very poor to average image quality with significant artifacts, whereas rosette remained very good, with minimal artifacts (P = 0.001).DATA CONCLUSION: Rosette k-sampling with a model-based reconstruction offers a clinically useful motion-robust T2 * mapping approach for iron quantification.

    View details for DOI 10.1002/jmri.27196

    View details for PubMedID 32452088

  • DIAGNOSTIC IMAGE QUALITY ASSESSMENT AND CLASSIFICATION IN MEDICAL IMAGING: OPPORTUNITIES AND CHALLENGES. Proceedings. IEEE International Symposium on Biomedical Imaging Ma, J. J., Nakarmi, U., Kin, C. Y., Sandino, C. M., Cheng, J. Y., Syed, A. B., Wei, P., Pauly, J. M., Vasanawala, S. S. 2020; 2020: 337-340

    Abstract

    Magnetic Resonance Imaging (MRI) suffers from several artifacts, the most common of which are motion artifacts. These artifacts often yield images that are of non-diagnostic quality. To detect such artifacts, images are prospectively evaluated by experts for their diagnostic quality, which necessitates patient-revisits and rescans whenever non-diagnostic quality scans are encountered. This motivates the need to develop an automated framework capable of accessing medical image quality and detecting diagnostic and non-diagnostic images. In this paper, we explore several convolutional neural network-based frameworks for medical image quality assessment and investigate several challenges therein.

    View details for DOI 10.1109/isbi45749.2020.9098735

    View details for PubMedID 33274013

    View details for PubMedCentralID PMC7710391

  • DIAGNOSTIC IMAGE QUALITY ASSESSMENT AND CLASSIFICATION IN MEDICAL IMAGING: OPPORTUNITIES AND CHALLENGES Ma, J. J., Nakarmi, U., Kin, C., Sandino, C. M., Cheng, J. Y., Syed, A. B., Wei, P., Pauly, J. M., Vasanawala, S. S., IEEE IEEE. 2020: 337–40
  • Near-Silent and Distortion-Free Diffusion MRI in Pediatric Musculoskeletal Disorders: Comparison With Echo Planar Imaging Diffusion. Journal of magnetic resonance imaging : JMRI Sandberg, J. K., Young, V. A., Syed, A. B., Yuan, J. n., Hu, Y. n., Sandino, C. n., Menini, A. n., Hargreaves, B. n., Vasanawala, S. n. 2020

    Abstract

    Diffusion-weighted imaging (DWI) is common for evaluating pediatric musculoskeletal lesions, but suffers from geometric distortion and intense acoustic noise.To investigate the performance of a near-silent and distortion-free DWI sequence (DW-SD) relative to standard echo-planar DWI (DW-EPI) in pediatric extremity MRI.Prospective validation study.Thirty-nine children referred for extremity MRI.DW-EPI and DW-SD, based on a rotating ultrafast sequence modified with sinusoidal diffusion preparation gradients, at 3T.DW-SD image quality (Sanat ) was assessed from 0 (nondiagnostic) to 5 (outstanding) and comparative image quality (Scomp ) (from -2 = DW-EPI more delineated to +2 = DW-SD more delineated, 0 = same). ADC measured by DW-SD and DW-EPI were compared in bone marrow, muscle, and lesions.Wilcoxon rank-sum test and confidence interval of proportions (CIOP) were calculated for Scomp , Student's t-test, coefficient of variation (COV), and Bland-Altman analysis for ADC values, and intraclass correlation coefficient (ICC) for interreader agreement.DW-SD and DW-EPI ADC values for bone marrow, muscle, and lesions were not significantly different (P = 0.3, P = 0.2, and P = 0.27, respectively) and had an overall ADC COV of 14.8% (95% confidence interval: 12.3%, 16.9%) and no significant proportional bias on Bland-Altman analysis. Sanat CIOP was rated diagnostic or better (score of 3, 4, or 5) in 72-98% of cases for bone marrow, muscle, and soft tissues. DW-SD was equivalent to or preferred over DW-EPI in muscles and soft tissues, with CIOP 86-93% and 93%, respectively. Lesions were equally visualized on DW-SD and DW-EPI in 40-51%, with DW-SD preferred in 44-56% of cases. DW-SD was rated significantly better than DW-EPI across all comparative variables that included bone marrow, muscle, soft tissue, cartilage, and lesions (P < 0.05). Readers had moderate to near-perfect (ICC range = 0.45-0.85).DW-SD of the extremities provided similar ADC values and improved image quality compared with conventional DW-EPI.2 TECHNICAL EFFICACY STAGE: 2.

    View details for DOI 10.1002/jmri.27330

    View details for PubMedID 32815203

  • AI Accelerated Human-in-the-loop Structuring of Radiology Reports. AMIA ... Annual Symposium proceedings. AMIA Symposium Wu, J. T., Syed, A., Ahmad, H., Pillai, A., Gur, Y., Jadhav, A., Gruhl, D., Kato, L., Moradi, M., Syeda-Mahmood, T. 2020; 2020: 1305–14

    Abstract

    Rule-based Natural Language Processing (NLP) pipelines depend on robust domain knowledge. Given the long tail of important terminology in radiology reports, it is not uncommon for standard approaches to miss items critical for understanding the image. AI techniques can accelerate the concept expansion and phrasal grouping tasks to efficiently create a domain specific lexicon ontology for structuring reports. Using Chest X-ray (CXR) reports as an example, we demonstrate that with robust vocabulary, even a simple NLP pipeline can extract 83 directly mentioned abnormalities (Ave. recall=93.83%, precision=94.87%) and 47 abnormality/normality descriptions of key anatomies. The richer vocabulary enables identification of additional label mentions in 10 out of 13 labels (compared to baseline methods). Furthermore, it captures expert insight into critical differences between observed and inferred descriptions, and image quality issues in reports. Finally, we show how the CXR ontology can be used to anatomically structure labeled output.

    View details for PubMedID 33936507