Source Themes

Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning

Communications Medicine EchoCLR, a label-efficient self-supervised learning method for echocardiography.

Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound: a multi-center study

medRxiv preprint Automated cardiomyopathy detection in point-of-care ultrasonography (POCUS).

Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge

Medical Image Analysis Overview of the CXR-LT challenge on long-tailed, multi-label disease classification from chest X-ray.

Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling

arXiv preprint Automated eye disease prognosis by survival analysis from longitudinal medical imaging.

High sensitivity methods for automated rib fracture detection in pediatric radiographs

Scientific Reports Ensemble methods for automated pediatric rib fracture detection on chest X-ray.

A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression

JAMA Cardiology An AI biomarker for aortic stenosis (AS) progression based on echocardiography.

Deep Rib Fracture Instance Segmentation and Classification from CT on the RibFrac Challenge

arXiv preprint Overview of the MICCAI 2020 RibFrac Challenge.

Improving Fairness of Automated Chest X-ray Diagnosis by Contrastive Learning

arXiv preprint Contrastive learning method for improved fairness in automated chest X-ray classification.

Biometric contrastive learning for data-efficient deep learning from electrocardiographic images

Journal of the American Medical Informatics Association Label-efficient electrocardiogram (ECG) image classification with contrastive learning.

Improving model fairness in image-based computer-aided diagnosis

Nature Communications A novel loss function for improved group fairness in chest X-ray classification.