Multi-Task Deep Learning Framework for Real-Time Quality Assessment and Probe Guidance in Echocardiography.
TL;DR
A multi-task guidance framework that jointly performs supervised view classification and cardiac structure segmentation and reuses their outputs to enable label-efficient, structure-specific image quality scoring through entropy-based metrics without additional quality annotations can assist novice or trainee users in consistently acquiring acceptable echocardiographic views with minimal additional annotation.
Abstract
Transthoracic echocardiography is a widely used, noninvasive tool for cardiac imaging, but the quality of image acquisition remains highly operator-dependent. Existing artificial intelligence-based systems often require large amounts of labeled data and provide only global quality scores, limiting their utility in real-time clinical applications. We propose a multi-task guidance framework that jointly performs supervised view classification and cardiac structure segmentation, and reuses their outputs to enable label-efficient, structure-specific image quality scoring through entropy-based metrics without additional quality annotations. A lightweight maneuver predictor then uses these features to suggest one of seven corrective probe maneuvers in real-time. To train and validate the system, we constructed a 43-case maneuver-tagged dataset capturing intentional transitions from standard to nonstandard views. The proposed quality metric successfully distinguished standard from nonstandard views across multiple cardiac structures (AUC: 0.901-0.987). The maneuver predictor achieved a top-1 accuracy of 85.1% (mAP: 0.904) and inference time of 17 ms per frame, supporting its feasibility for real-time use. This system can assist novice or trainee users in consistently acquiring acceptable echocardiographic views with minimal additional annotation, which can improve clinical efficiency and reliability.