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

cs.CVMar 27, 2026

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

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

Organizations: Tianjin University

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.

Figures & tables

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).

Loss Term	Physical Meaning	Target Clinical Feature
DiceCE Loss	Global voxel overlap	Basic lumen morphology
Boundary Loss	Intimal flap edge clarity	LOT (Tear location)
Anatomical Reg	Branch vessel spatial consistency	BVI (Branch involvement)
Entropy Reg	Prediction confidence consistency	Cross-center generalization

Table 1: Analysis of Loss Functions and Target Clinical Features

Method	True Lumen (TL)		False Lumen (FL)		Intimal Flap (IF)
Method	DSC ( $\uparrow$ )	HD95 ( $\downarrow$ )	DSC ( $\uparrow$ )	HD95 ( $\downarrow$ )	DSC ( $\uparrow$ )	HD95 ( $\downarrow$ )
Source-Only (nnU-Net)	0.782	12.4	0.765	14.1	0.412	22.3
DANN (Adversarial)	0.814	9.8	0.801	11.2	0.485	18.6
Entropy Minimization	0.825	8.5	0.810	10.4	0.510	16.4
Ours (SMEDL+SE-ASA)	0.891	4.2	0.884	5.1	0.673	8.9

Table 2: Quantitative comparison of cross-institutional segmentation performance. DSC denotes the Dice Similarity Coefficient, and HD95 denotes the 95% Hausdorff Distance in millimeters.

Clinical Feature Extracted	Anatomical Fidelity	Support for Surgical Planning
Location of Tear (LOT)	$4.6\pm 0.4$	$4.8\pm 0.3$
True Lumen Collapse (TLC)	$4.5\pm 0.5$	$4.6\pm 0.4$
False Lumen Area Ratio (FLAR)	$4.7\pm 0.3$	$4.5\pm 0.5$
Branch Vessel Involvement (BVI)	$4.4\pm 0.6$	$4.7\pm 0.4$

Table 3: Clinical Utility Assessment (5-Point Likert Scale). Scores range from 1 (Poor/No Utility) to 5 (Excellent/Crucial for Decision).

Medical Image Analysis

Medical image analysis uses computational methods to interpret clinical images, measure anatomy and disease, and support diagnosis and treatment.

See all 292 papers

Mar 23, 2026

SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation

Unsupervised Domain Adaptation (UDA) is essential for deploying medical segmentation models across diverse clinical environments. Existing methods are fundamentally limited, suffering from semantically unaware feature alignment that results in poor distributional fidelity and from pseudo-label validation that disregards global anatomical constraints, thus failing to prevent the formation of globally implausible structures. To address these issues, we propose SHAPE (Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation), a framework that reframes adaptation towards global anatomical plausibility. Built on a DINOv3 foundation, its Hierarchical Feature Modulation (HFM) module first generates features with both high fidelity and class-awareness. This shifts the core challenge to robustly validating pseudo-labels. To augment conventional pixel-level validation, we introduce Hypergraph Plausibility Estimation (HPE), which leverages hypergraphs to assess the global anatomical plausibility that standard graphs cannot capture. This is complemented by Structural Anomaly Pruning (SAP) to purge remaining artifacts via cross-view stability. SHAPE significantly outperforms prior methods on cardiac and abdominal cross-modality benchmarks, achieving state-of-the-art average Dice scores of 90.08% (MRI->CT) and 78.51% (CT->MRI) on cardiac data, and 87.48% (MRI->CT) and 86.89% (CT->MRI) on abdominal data. The code is available at https://github.com/BioMedIA-repo/SHAPE.

Linkuan Zhou, Yinghao Xia, Yufei Shen +6

School of Software, Northwestern Polytechnical University · School of Computer Science and Technology, Harbin Institute of Technology · School of Software Engineering, USTC +3

Unsupervised Domain Adaptation Medical Image Segmentation Cross-Modality Medical Image Segmentation

Ask PDF

Aug 12, 2026

A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery

Background: Accurate segmentation of the Left Anterior Descending (LAD) artery in 3D free-breathing, non-contrast CT is critical for cardiac dose sparing in thoracic radiotherapy. The LAD is extremely small, has poor soft-tissue contrast, and varies substantially across patients; even manual contours show limited inter-observer agreement, underscoring the ambiguity of the vessel boundaries. Purpose: To develop a transformer-based framework that improves LAD delineation in low-contrast, imbalanced CT through local-global context modeling and uncertainty-guided optimization. Methods: We propose NA-UNETR, a 3D transformer-based segmentation model whose Neighborhood Attention (NA) and Dilated NA (DiNA) blocks jointly capture fine structural detail and long-range context. Given the scarcity of annotated LAD data, the model is pretrained on 1,000 CTA volumes of general coronary anatomy and fine-tuned with LoRA-based parameter-efficient adaptation on 20 free-breathing institutional CT scans. A composite Dice-Focal and Hausdorff loss, dynamically balanced via homoscedastic uncertainty, improves overlap and boundary accuracy. Results: NA-UNETR reached 45.64% Dice, 38.16 mm HD95, and 10.01 mm ASD, improving Dice by 3.10 percentage points over nnU-Net and reducing HD95 by 2.96 mm relative to Swin UNETR, with the strongest boundary accuracy among all models and improved centerline stability. On ImageCAS it achieved 79.49% Dice, 8.89 mm HD95, and 1.02 mm ASD. Ablations confirmed that residual blocks, variable kernels, and uncertainty-weighted loss each contributed. Conclusions: NA-UNETR balances local precision and global context for thin, low-contrast LAD structures, offering a computationally efficient framework for substructure-level cardiac segmentation in radiotherapy planning.

Rafi Ibn Sultan, Chengyin Li, Yiannos Demetriou +6

Department of Computer Science, Wayne State University, Detroit, MI, 48202, USA · Department of Radiation Oncology, Henry Ford Health, Detroit, MI, 48202, USA · Department of Clinical Oncology, Alexandria University, Alexandria, 21526, Egypt +4

Medical Image Segmentation 3D Medical Image Segmentation Coronary Artery Segmentation

Ask PDF

Mar 5, 2026

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model

Source Free Unsupervised Domain Adaptation (SFUDA) is critical for deploying deep learning models across diverse clinical settings. However, existing methods are typically designed for low-gap, specific domain shifts and cannot generalize into a unified, multi-modalities, and multi-target framework, which presents a major barrier to real-world application. To overcome this issue, we introduce Tell2Adapt, a novel SFUDA framework that harnesses the vast, generalizable knowledge of the Vision Foundation Model (VFM). Our approach ensures high-fidelity VFM prompts through Context-Aware Prompts Regularization (CAPR), which robustly translates varied text prompts into canonical instructions. This enables the generation of high-quality pseudo-labels for efficiently adapting the lightweight student model to target domain. To guarantee clinical reliability, the framework incorporates Visual Plausibility Refinement (VPR), which leverages the VFM's anatomical knowledge to re-ground the adapted model's predictions in target image's low-level visual features, effectively removing noise and false positives. We conduct one of the most extensive SFUDA evaluations to date, validating our framework across 10 domain adaptation directions and 22 anatomical targets, including brain, cardiac, polyp, and abdominal targets. Our results demonstrate that Tell2Adapt consistently outperforms existing approaches, achieving SOTA for a unified SFUDA framework in medical image segmentation. Code are avaliable at https://github.com/derekshiii/Tell2Adapt.

Yulong Shi, Shijie Li, Ziyi Li +1

College of Medicine and Biological Information Engineering, Northeastern University · Engineering Research Center of Medical Imaging and Intelligent Analysis, Ministry of Education · Key Laboratory of Medical Image Computing, Ministry of Education, Northeastern University

Source-Free Domain Adaptation Medical Image Segmentation Vision Foundation Model Adaptation

Ask PDF

Abstract

Medical Image Analysis

Explore similar work

SHAPE: Structure-aware Hierarchical Unsupervised Domain Adaptation with Plausibility Evaluation for Medical Image Segmentation

A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery

Tell2Adapt: A Unified Framework for Source Free Unsupervised Domain Adaptation via Vision Foundation Model