The paper introduces the "segmentation ceiling," a quantitative criterion that determines when explicit left‑ventricular (LV) segmentation can improve ejection fraction (EF) regression. By deriving how per‑frame segmentation area error propagates into EF error, the authors find that a break‑even error of about 10% per frame is required, whereas typical segmenters exceed this threshold (~14%). Consequently, several strategies that incorporate segmentation or area information fail to outperform a raw‑video baseline, while techniques such as weight averaging with strong augmentation and a heteroscedastic beta‑NLL loss yield competitive EF predictions and well‑calibrated uncertainty estimates.
arXiv:2607. 25748v1 Announce Type: new Abstract: Objective: Concept bottleneck models route prediction through interpretable intermediate variables, and their validity is normally judged by how accurately those variables are predicted.
The paper introduces the first publicly available dataset for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography, comprising over 25,000 labeled videos generated through a novel data‑generation strategy that correlates clinical notes with echocardiographic videos. Using this dataset, the authors train a reproducible PLAX‑EF model that achieves a mean absolute error (MAE) of 6.86%, comparable to the clinical standard of apical four‑chamber (A4C) methods. They further show that combining PLAX and A4C predictions via simple late fusion reduces MAE to 6.37%, highlighting the benefit of multi‑view integration, and they release the dataset, models, and demos for community use.
arXiv:2607. 13738v1 Announce Type: cross Abstract: Background and Objective: Deep video models estimate left-ventricular ejection fraction (EF) from echocardiography with near-expert accuracy, and post-hoc attribution (Chefer relevance for transformers, Grad-CAM for CNNs) is increasingly used to certify that models "look at the right place.
The paper introduces the first publicly available dataset of over 25,000 parasternal long‑axis (PLAX) echocardiography videos labeled for left ventricular ejection fraction (EF), created through a novel data‑generation strategy that links clinical notes to video data. Using this dataset, the authors train a reproducible PLAX‑based EF model that achieves a mean absolute error (MAE) of 6.86%, comparable to the clinical standard of apical four‑chamber (A4C) methods. They further show that simple late fusion of PLAX and A4C predictions reduces MAE to 6.37%, highlighting the benefit of multi‑view integration, and release the dataset, models, and demos publicly.
arXiv:2605. 16427v2 Announce Type: replace-cross Abstract: Deep learning models for echocardiography segmentation often struggle to generalise across institutions, scanners, and patient populations, where collecting large, consistently annotated datasets is infeasible.
arXiv:2608. 10903v1 Announce Type: cross Abstract: Reliable clinical deployment of machine learning requires models that know when they are likely to fail, particularly for subgroups underrepresented in training data.
arXiv:2607. 13738v2 Announce Type: replace-cross Abstract: Deep video models estimate left-ventricular ejection fraction (EF) from echocardiography with near-expert accuracy, and post-hoc attribution is increasingly used to certify that such models look at the right place.
Echo-E$^3$Net is an anatomy‑guided spatio‑temporal neural network designed to estimate left ventricular ejection fraction (LVEF) from ultrasound images. It uses a dual‑phase Endocardial Border Detector to locate end‑diastole and end‑systole landmarks and an Endocardial Feature Aggregator to fuse these landmarks with global deep‑feature descriptors for EF regression. The model achieves competitive accuracy on EchoNet‑Dynamic and EchoNet‑Pediatric datasets while using only 1.55 M parameters and 8.05 GFLOPs, enabling real‑time deployment on limited‑resource devices.
The paper introduces a framework that distinguishes two causes of saturation in clinical prediction: a learner gap, where the model fails to use available information, and a measurement‑channel ceiling, where the recorded variables limit performance. It provides theoretical characterizations, finite‑sample diagnostics, and empirical audits across three large cohorts, showing that well‑tuned models approach the frontier while deficient learners leave large gaps. A PRISMA‑guided synthesis across 104 tasks reveals consistent channel‑level patterns, suggesting that improving the learner or the measurement channel can audit and potentially lift performance.
arXiv:2607. 11287v1 Announce Type: cross Abstract: Comprehensive quantification of cardiac structures from computed tomography (CT) remains limited not by data availability but by the scalability of measurements, which makes routine use impractical.
The paper introduces SV-Cine, a cardiac MRI segmentation framework tailored for single ventricle physiology (SVP). It combines a generative data augmentation pipeline that creates synthetic 3D cardiac meshes and MRI, with a diagnosis-conditioned adaptation of the CineMA foundation model that uses patient-level diagnostic information to improve segmentation. Evaluations on an internal cohort show high Dice scores for left and right ventricles, outperforming nnU-Net, and demonstrate that incorporating diagnosis priors can adapt a pretrained model to specialized SVP tasks.
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.