Generative Regression for Left Ventricular Ejection Fraction Estimation from Echocardiography Video

2026-02-09

AI Summary

Estimating left ventricular ejection fraction (LVEF) from echocardiographic videos is an ill-posed inverse problem, significantly challenged by noise, artifacts, limited imaging views, and pronounced multimodal uncertainty. To address this, this work proposes the Multimodal Conditional Score-based Diffusion Regression (MCSDR) model—the first to introduce score-based diffusion mechanisms into medical regression tasks. By modeling the conditional posterior distribution of LVEF, MCSDR enables probabilistic, generative prediction that captures multimodal uncertainty while integrating echocardiographic video data with patient demographic priors. The approach further offers diagnostic interpretability through its generative trajectory. Evaluated on EchoNet-Dynamic, EchoNet-Pediatric, and CAMUS datasets, MCSDR achieves state-of-the-art performance, demonstrating superior robustness and clinical utility, particularly in high-noise or high-variability cases.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Multi-modal Vision
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Estimating Left Ventricular Ejection Fraction (LVEF) from echocardiograms constitutes an ill-posed inverse problem. Inherent noise, artifacts, and limited viewing angles introduce ambiguity, where a single video sequence may map not to a unique ground truth, but rather to a distribution of plausible physiological values. Prevailing deep learning approaches typically formulate this task as a standard regression problem that minimizes the Mean Squared Error (MSE). However, this paradigm compels the model to learn the conditional expectation, which may yield misleading predictions when the underlying posterior distribution is multimodal or heavy-tailed -- a common phenomenon in pathological scenarios. In this paper, we investigate the paradigm shift from deterministic regression toward generative regression. We propose the Multimodal Conditional Score-based Diffusion model for Regression (MCSDR), a probabilistic framework designed to model the continuous posterior distribution of LVEF conditioned on echocardiogram videos and patient demographic attribute priors. Extensive experiments conducted on the EchoNet-Dynamic, EchoNet-Pediatric, and CAMUS datasets demonstrate that MCSDR achieves state-of-the-art performance. Notably, qualitative analysis reveals that the generation trajectories of our model exhibit distinct behaviors in cases characterized by high noise or significant physiological variability, thereby offering a novel layer of interpretability for AI-aided diagnosis.

Problem

• Left Ventricular Ejection Fraction
• Echocardiography
• Ill-posed Inverse Problem
• Multimodal Distribution
• Generative Regression

Innovation

• generative regression
• score-based diffusion model
• left ventricular ejection fraction
• multimodal posterior
• echocardiography