echocardiography

[JAMA] "Complete AI-Enabled Echocardiography Interpretation with Multitask Deep Learning" by Gregory Holste, Evangelos K. Oikonomou, Márton Tokodi, Attila Kovács, Zhangyang Wang, & Rohan Khera

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

Transthoracic echocardiography and mortality in sepsis: analysis of the MIMIC-III database

Official repository for EchoFM: Foundation Model for Generalizable Echocardiogram Analysis

Myocardial Infarction Detection

[ NeurIPS 2022 ] Official Codebase for "ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography"

EchoNet-LVH is a deep learning model that quantifies ventricular hypertrophy and predicts etiologies of increased wall thickness and LVH (amyloidosis, HCM, etc).

[Communications Medicine] "Efficient deep learning-based automated diagnosis from echocardiography with contrastive self-supervised learning" by Gregory Holste, Evangelos Oikonomou, Bobak Mortazavi, Zhangyang Wang, and Rohan Khera

[MedIA 2026] MedSapiens: Taking a Pose to Rethink Medical Imaging Landmark Detection

PyTorch implementation of the two U-Net-based architectures described in "Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography"

Official repository for the paper "ProtoASNet: Dynamic Prototypes for Inherently Interpretable and Uncertainty-Aware Aortic Stenosis Classification in Echocardiography" in MICCAI 2023 Conference

Exploring 3D reconstruction of the heart from 2D echocardiography and other imaging (CT, MRI, ultrasound).

[European Heart Journal] "Severe aortic stenosis detection by deep learning applied to echocardiography" by Gregory Holste et al.

Official repository for MediViSTA SAM Adaptation

Official codebase for the paper: EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis

[Pattern Recognition 2026] UltraSeP: Sequence-aware Pre-training for Echocardiography Probe Guidance

Fine-tune MedGemma-1.5-4B-it (via QLoRA) to output polygon coordinates for tracing the cardiac chambers on echocardiographic frames. More info at: https://discuss.ai.google.dev/t/atria-echotrace-fine-tuning-medgemma-1-5-for-polygon-based-heart-structure-contouring/172907 and https://atria.theadimension.com/

Official implementation of Echo-DND: A Dual Noise Diffusion Model for Robust and Precise Left Ventricle Segmentation in Echocardiography

We propose a scalable Temporal Attention Module (TAM) to inject cardiac motion information into segmentation models. TAM captures dynamic changes across temporal frames using multi-headed, cross-temporal attention. It is adaptable across imaging modalities, scalable from 2D to 3D, and adds minimal computational overhead.