Current Role at Stanford
Research and Development Scientist at Engineer at Urologic Cancer Innovation Lab, Urology Department.
Honors & Awards
Second Place in the Learn2Reg Grand Challenge, MICCAI (2021)
Second Place in the Multi-sequence Cardiac MR Segmentation Challenge (MS-CMRSeg), MICCAI-STACOM (2019)
Second Place in the Atrial Segmentation Challenge, MICCAI-STACOM (2018)
Graduate School Scholarship Programme (GSSP) Recipient, German Academic Exchange Service (DAAD) (2016)
SAARC India Silver Jubilee Scholarships Recipient, SARRC (2011)
Education & Certifications
PhD, Friedrich-Alexander-Universität Erlangen-Nürnberg, Medical Engineering (Pending) (2021)
M.Sc., South Asian University, Computer Science (2013)
B.Sc., Kabul University, Computer Science (2010)
Research Data Scientist, University of California San Francisco (UCSF) (8/1/2020 - 2/28/2021)
San Francisco, CA
- The Learn2Reg 2021 MICCAI Grand Challenge (PIMed Team) SPRINGER INTERNATIONAL PUBLISHING AG. 2022: 168-173
Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy Minimisation for Multi-modal Cardiac Image Segmentation.
IEEE transactions on medical imaging
Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly because the data distribution between the two domains is different. Moreover, creating annotation for every new modality is a tedious and time-consuming task, which also suffers from high inter- and intra- observer variability. Unsupervised domain adaptation (UDA) methods intend to reduce the gap between source and target domains by leveraging source domain labelled data to generate labels for the target domain. However, current state-of-the-art (SOTA) UDA methods demonstrate degraded performance when there is insufficient data in source and target domains. In this paper, we present a novel UDA method for multi-modal cardiac image segmentation. The proposed method is based on adversarial learning and adapts network features between source and target domain in different spaces. The paper introduces an end-to-end framework that integrates: a) entropy minimisation, b) output feature space alignment and c) a novel point-cloud shape adaptation based on the latent features learned by the segmentation model. We validated our method on two cardiac datasets by adapting from the annotated source domain, bSSFP-MRI (balanced Steady-State Free Procession-MRI), to the unannotated target domain, LGE-MRI (Late-gadolinium enhance-MRI), for the multi-sequence dataset; and from MRI (source) to CT (target) for the cross-modality dataset. The results highlighted that by enforcing adversarial learning in different parts of the network, the proposed method delivered promising performance, compared to other SOTA methods.
View details for DOI 10.1109/TMI.2021.3066683
View details for PubMedID 33729930
A global benchmark of algorithms for segmenting the left atrium from late gadolinium-enhanced cardiac magnetic resonance imaging.
Medical image analysis
2021; 67: 101832
Segmentation of medical images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) used for visualizing diseased atrial structures, is a crucial first step for ablation treatment of atrial fibrillation. However, direct segmentation of LGE-MRIs is challenging due to the varying intensities caused by contrast agents. Since most clinical studies have relied on manual, labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the 2018 Left Atrium Segmentation Challenge using 154 3D LGE-MRIs, currently the world's largest atrial LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show that the top method achieved a Dice score of 93.2% and a mean surface to surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved superior results than traditional methods and machine learning approaches containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for atrial LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field. Furthermore, the findings from this study can potentially be extended to other imaging datasets and modalities, having an impact on the wider medical imaging community.
View details for DOI 10.1016/j.media.2020.101832
View details for PubMedID 33166776
Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification.
IEEE journal of biomedical and health informatics
Quantitative assessment of cardiac left ventricle (LV) morphology is essential to assess cardiac function and improve the diagnosis of different cardiovascular diseases. In current clinical practice, LV quantification depends on the measurement of myocardial shape indices, which is usually achieved by manual delineation. However, this process is time-consuming and subject to inter and intra-observer variability. In this paper, we propose a Spatio-temporal multi-task learning approach to obtain a complete set of measurements quantifying cardiac LV morphology, regional-wall thickness (RWT), and additionally detecting the cardiac phase cycle (systole and diastole) for a given 3D Cine-magnetic resonance (MR) image sequence. We first segment cardiac LVs using an encoder-decoder network and then introduce a multitask framework to regress 11 LV indices and classify the cardiac phase, as parallel tasks during model optimization. The proposed deep learning model is based on the 3D Spatio-temporal convolutions, which extract spatial and temporal features from MR images. We demonstrate the efficacy of the proposed method using cine-MR sequences of 145 subjects and comparing the performance with other state-of-the-art quantification methods. The proposed method achieved high prediction accuracy, with an average mean absolute error (MAE) of 129 mm2, 1.23 mm, 1.76 mm, Pearson correlation coefficient (PCC) of 96.4%, 87.2%, and 97.5% for LV and myocardium (Myo) cavity regions, 6 RWTs, 3 LV dimensions, and an error rate of 9.0% for phase classification. The experimental results highlight the robustness of the proposed method, despite varying degrees of cardiac morphology, image appearance, and low contrast in the cardiac MR sequences.
View details for DOI 10.1109/JBHI.2020.3046449
View details for PubMedID 33351771
- Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks JOURNAL OF IMAGING 2020; 6 (7)
Implementation of machine learning into clinical breast MRI: Potential for objective and accurate decision-making in suspicious breast masses.
2020; 15 (1): e0228446
We investigated whether the integration of machine learning (ML) into MRI interpretation can provide accurate decision rules for the management of suspicious breast masses. A total of 173 consecutive patients with suspicious breast masses upon complementary assessment (BI-RADS IV/V: n = 100/76) received standardized breast MRI prior to histological verification. MRI findings were independently assessed by two observers (R1/R2: 5 years of experience/no experience in breast MRI) using six (semi-)quantitative imaging parameters. Interobserver variability was studied by ICC (intraclass correlation coefficient). A polynomial kernel function support vector machine was trained to differentiate between benign and malignant lesions based on the six imaging parameters and patient age. Ten-fold cross-validation was applied to prevent overfitting. Overall diagnostic accuracy and decision rules (rule-out criteria) to accurately exclude malignancy were evaluated. Results were integrated into a web application and published online. Malignant lesions were present in 107 patients (60.8%). Imaging features showed excellent interobserver variability (ICC: 0.81-0.98) with variable diagnostic accuracy (AUC: 0.65-0.82). Overall performance of the ML algorithm was high (AUC = 90.1%; BI-RADS IV: AUC = 91.6%). The ML algorithm provided decision rules to accurately rule-out malignancy with a false negative rate <1% in 31.3% of the BI-RADS IV cases. Thus, integration of ML into MRI interpretation can provide objective and accurate decision rules for the management of suspicious breast masses, and could help to reduce the number of potentially unnecessary biopsies.
View details for DOI 10.1371/journal.pone.0228446
View details for PubMedID 31999755
View details for PubMedCentralID PMC6992224
- Classification of Breast Cancer Histology Images Using Transfer Learning SPRINGER INTERNATIONAL PUBLISHING AG. 2018: 812–19
- A Multi-task Framework for Skin Lesion Detection and Segmentation SPRINGER INTERNATIONAL PUBLISHING AG. 2018: 285–93