Unlabeled Cross-Center Automatic Analysis for TAAD: An Integrated Framework from Segmentation to Clinical Features

2026-03-26

AI Summary

This work addresses the performance degradation in cross-center clinical feature extraction for Type A aortic dissection (TAAD) caused by domain shift under the absence of target-domain annotations. To this end, we propose an end-to-end unsupervised domain adaptation (UDA) framework that integrates a multi-class medical image segmentation network with geometric and morphological post-processing. Our method enables stable cross-center segmentation and automatic extraction of quantifiable clinical features without requiring any labels in the target domain, relying solely on limited annotated data from the source domain. Experimental results demonstrate that our approach significantly outperforms current state-of-the-art methods in cross-domain segmentation accuracy. Furthermore, the extracted features have been validated by multiple cardiothoracic surgeons as providing substantial support for preoperative assessment, marking the first fully automated and interpretable pipeline for TAAD clinical metric extraction tailored to real-world emergency settings.

Abstract

Type A Aortic Dissection (TAAD) is a life-threatening cardiovascular emergency that demands rapid and precise preoperative evaluation. While key anatomical and pathological features are decisive for surgical planning, current research focuses predominantly on improving segmentation accuracy, leaving the reliable, quantitative extraction of clinically actionable features largely under-explored. Furthermore, constructing comprehensive TAAD datasets requires labor-intensive, expert level pixel-wise annotations, which is impractical for most clinical institutions. Due to significant domain shift, models trained on a single center dataset also suffer from severe performance degradation during cross-institutional deployment. This study addresses a clinically critical challenge: the accurate extraction of key TAAD clinical features during cross-institutional deployment in the total absence of target-domain annotations. To this end, we propose an unsupervised domain adaptation (UDA)-driven framework for the automated extraction of TAAD clinical features. The framework leverages limited source-domain labels while effectively adapting to unlabeled data from target domains. Tailored for real-world emergency workflows, our framework aims to achieve stable cross-institutional multi-class segmentation, reliable and quantifiable clinical feature extraction, and practical deployability independent of high-cost annotations. Extensive experiments demonstrate that our method significantly improves cross-domain segmentation performance compared to existing state-of-the-art approaches. More importantly, a reader study involving multiple cardiovascular surgeons confirms that the automatically extracted clinical features provide meaningful assistance for preoperative assessment, highlighting the practical utility of the proposed end-to-end segmentation-to-feature pipeline.

Problem

• Type A Aortic Dissection
• cross-institutional deployment
• clinical feature extraction
• unlabeled target domain
• domain shift

Innovation

• unsupervised domain adaptation
• cross-center deployment
• clinical feature extraction
• aortic dissection segmentation
• annotation-free analysis