Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography
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." Yet whether these explanations are faithful both spatially and temporally is unaudited. Because EF is defined by the end-systolic (ES) and end-diastolic (ED) frames, a faithful explanation must localize the
Record details
Published: 15 July 2026
Source: arXiv cs.AI
Category: Research
Topics: Transparency
Retrieved: 16 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Explaining Reinforcement Learning Agents via Inductive Logic Programming
arXiv · 15 July 2026
Plausible Deniability Guarantees for Whistleblowers
arXiv cs.LG · 15 July 2026
Behavior Change Content and Implementation of Large Language Model–Driven Conversational Agents in Cardiometabolic Care: Scoping Review
JMIR (Journal of Medical Internet Research) · 15 July 2026
Traccia: An OpenTelemetry-Based Governance Platform for AI Systems
arXiv · 15 July 2026
AAAI-26 Dual Submissions: Novel Challenges
arXiv cs.CY · 15 July 2026
Comparative Analysis of Expert, Clinician, and Health Care User Interactions With Summary of Findings Tables: Usability Study
JMIR (Journal of Medical Internet Research) · 15 July 2026
How to cite this record
ethics.ai (15 July 2026), “Anatomically Faithful but Temporally Blind: Auditing Attribution for Left-Ventricular Ejection-Fraction Estimation from Echocardiography,” evidence record 10908, https://ethics.ai/record/10908 (originally published by arXiv cs.AI).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.