EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors created EchoRisk, a collection of heart ultrasound videos from breast cancer patients to help detect heart damage caused by cancer treatments early. They gathered data from 422 patients over time and set up three tasks: measuring heart function, spotting heart problems as they develop, and predicting heart damage before treatment starts. They tested a computer model that works well for measuring heart function and spotting issues but found that early prediction of heart damage is still difficult. The dataset and tools are shared for others to improve heart monitoring during cancer therapy.
echocardiographycardiotoxicityleft ventricular ejection fractionbreast cancermachine learninglongitudinal studycardio-oncologyvideo analysisLSTMrisk prediction
Authors
Grigorios Kalliatakis, Georgia Karanasiou, Georgios Manikis, Manolis Tsiknakis, Dimitrios Fotiadis, Dorothea Tsekoura, Kalliopi Keramida, Vasileios Bouratzis, Lampros Lakkas, Katerina Naka, Andri Papakonstantinou, Anastasia Constantinidou, Kostas Marias
Abstract
Therapy-induced cardiotoxicity is the leading non-oncological cause of treatment interruption in breast cancer patients, yet early, automated risk stratification from routine cardiac imaging remains an unsolved problem. We present EchoRisk, the first curated, multicentre, longitudinal echocardiography dataset with explicit cardiotoxicity labels, released as the primary technical reference for the EchoRisk-MICCAI 2026 challenge. The dataset comprises 422 patients enrolled in the EU-funded CARDIOCARE prospective study across five European sites, yielding 2,159 echocardiography videos across 1,123 clinical exams acquired at up to five longitudinal timepoints, alongside a dedicated cohort of 280 patients with baseline imaging for early cardiotoxicity prediction. Three clinically grounded tasks are defined: automated estimation of left ventricular ejection fraction from cine video (Task 1), classification of LV dysfunction from longitudinal imaging (Task 2), and early prediction of therapy-induced cardiotoxicity from pre-therapy baseline echocardiography alone (Task 3). For each task we specify the evaluation protocol, primary and secondary metrics, and ranking procedure. We establish baseline performance using an R(2+1)D video backbone with LSTM aggregation trained from Kinetics-400 pretrained weights, demonstrating strong discriminative performance for cardiac functional assessment and LV dysfunction classification, while early cardiotoxicity prediction from a single pre-therapy video remains a significant open problem for the community. The dataset, evaluation code, and baseline implementations are publicly available to serve as a benchmark for further collaboration, comparison, and the creation of task-specific architectures in cardio-oncology.