Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Mengdi Liu, Qiang Li, Weizhi Nie, Shaopeng Zhang, Yuting Su

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.

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

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.

Paper Structure

This paper contains 12 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Network Architecture and Feature Disentanglement (SMEDL)
  4. Prototype-Anchored UDA Strategy (SE-ASA)
  5. Domain Knowledge-Driven Clinical Feature Extraction
  6. Anatomical Constraint Loss Functions
  7. Experiments
  8. Experimental Setup and Datasets
  9. Evaluation Metrics
  10. Cross-Institutional Segmentation Performance
  11. Clinical Reader Study and Utility Validation
  12. Conclusion

Figures (2)

  • Figure 1: Overview of the proposed UDA-driven framework for automated TAAD clinical feature extraction. The pipeline addresses current clinical limitations by adapting from a labeled source domain to an unlabeled target domain, enabling the robust cross-institutional extraction of key clinical features (LOT, TLC, FLAR, and BVI) to support surgical planning.
  • Figure 2: Detailed architecture of the proposed integrated framework. (1) Network Architecture & Feature Disentanglement: The SMEDL module decomposes inputs into domain-invariant content and domain-specific style features via Style Mixup. (2) Prototype-Anchored UDA (SE-ASA): A self-training loop uses uncertainty evaluation to generate reliable pseudo-labels, aligning class-level semantics across domains. (3) Clinical Feature Extraction: The segmentation output is constrained by anatomical losses and processed to quantify key surgical metrics (LOT, TLC, FLAR, BVI).