Publications

Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays

IEEE Transactions on Medical Imaging
A Transformer for weakly supervised disease localization that uses a novel feedback loop between (local) radiomics features and (global) chest X-ray features.
PDF Code
Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays

Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study

MICCAI Workshop on Data Augmentation, Labelling, and Imperfections 2022 Oral
A large-scale benchmark for long-tailed learning of chest X-rays.
PDF Code Video Source Document

Automated detection of severe aortic stenosis using single-view echocardiography: A self-supervised ensemble learning approach

medRxiv Preprint
Accurate detection of severe aortic stenosis based on self-supervised and ensemble learning of single-view echocardiograms.
PDF
Automated detection of severe aortic stenosis using single-view echocardiography: A self-supervised ensemble learning approach

Self-Supervised Learning of Echocardiogram Videos Enables Data-Efficient Clinical Diagnosis

arXiv Preprint
Self-supervised learning method for echocardiogram videos drives label-efficient fine-tuning on aortic stenosis classification. Presented at IMLH 2022, an ICML workshop.
PDF Code Poster
Self-Supervised Learning of Echocardiogram Videos Enables Data-Efficient Clinical Diagnosis

Avalanche decision schemes to improve pediatric rib fracture detection

SPIE Medical Imaging 2022
Domain knowledge-guided method for improved rib fracture localization.
PDF

End-to-End Learning of Fused Image and Non-Image Features for Improved Breast Cancer Classification from MRI

CVAMD 2021 (ICCV Workshop)
Methods for jointly learning from breast imaging and tabular non-image data to predict breast cancer.
PDF Code Poster
End-to-End Learning of Fused Image and Non-Image Features for Improved Breast Cancer Classification from MRI

Deep learning methods for segmentation of lines in pediatric chest radiographs

SPIE Medical Imaging 2020
Segmentation methods for localizing “lines” (catheters, tubes, etc.) in pediatric chest radiographs.
PDF
Deep learning methods for segmentation of lines in pediatric chest radiographs

Multi-class semantic segmentation of pediatric chest radiographs

SPIE Medical Imaging 2020 Oral
Automatic anatomic segmentation of pediatric chest radiographs under severe class imbalance.
PDF
Multi-class semantic segmentation of pediatric chest radiographs