Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis

Zhan Jin, Yu Luo, Yizhou Zhang, Ziyang Cui, Yuqing Wei, Xianchao Liu, Xueying Zeng, Qing Zhang

Abstract

Conventional pixel-wise loss functions fail to enforce topological constraints in coronary vessel segmentation, producing fragmented vascular trees despite high pixel-level accuracy. We present ARIADNE, a two-stage framework coupling preference-aligned perception with RL-based diagnostic reasoning for topologically coherent stenosis detection. The perception module employs DPO to fine-tune the Sa2VA vision-language foundation model using Betti number constraints as preference signals, aligning the policy toward geometrically complete vessel structures rather than pixel-wise overlap metrics. The reasoning module formulates stenosis localization as a Markov Decision Process with an explicit rejection mechanism that autonomously defers ambiguous anatomical candidates such as bifurcations and vessel crossings, shifting from coverage maximization to reliability optimization. On 1,400 clinical angiograms, ARIADNE achieves state-of-the-art centerline Dice of 0.838, reduces false positives by 41% compared to geometric baselines. External validation on multi-center benchmarks ARCADE and XCAD confirms generalization across acquisition protocols. This represents the first application of DPO for topological alignment in medical imaging, demonstrating that preference-based learning over structural constraints mitigates topological violations while maintaining diagnostic sensitivity in interventional cardiology workflows.

ARIADNE: A Perception-Reasoning Synergy Framework for Trustworthy Coronary Angiography Analysis

Abstract

Conventional pixel-wise loss functions fail to enforce topological constraints in coronary vessel segmentation, producing fragmented vascular trees despite high pixel-level accuracy. We present ARIADNE, a two-stage framework coupling preference-aligned perception with RL-based diagnostic reasoning for topologically coherent stenosis detection. The perception module employs DPO to fine-tune the Sa2VA vision-language foundation model using Betti number constraints as preference signals, aligning the policy toward geometrically complete vessel structures rather than pixel-wise overlap metrics. The reasoning module formulates stenosis localization as a Markov Decision Process with an explicit rejection mechanism that autonomously defers ambiguous anatomical candidates such as bifurcations and vessel crossings, shifting from coverage maximization to reliability optimization. On 1,400 clinical angiograms, ARIADNE achieves state-of-the-art centerline Dice of 0.838, reduces false positives by 41% compared to geometric baselines. External validation on multi-center benchmarks ARCADE and XCAD confirms generalization across acquisition protocols. This represents the first application of DPO for topological alignment in medical imaging, demonstrating that preference-based learning over structural constraints mitigates topological violations while maintaining diagnostic sensitivity in interventional cardiology workflows.
Paper Structure (15 sections, 16 equations, 5 figures, 3 tables)

This paper contains 15 sections, 16 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Framework Overview
  4. Anatomy-Aware Perception Module via Preference Alignment
  5. Structure-Guided Reasoning via Reinforcement Learning
  6. Experiments
  7. Datasets and Sampling Strategy
  8. Evaluation Metrics
  9. Implementation Details
  10. Baseline Methods
  11. Results
  12. Segmentation Performance
  13. Stenosis Detection Performance
  14. Discussion
  15. Conclusion

Figures (5)

  • Figure 1: Training framework of Anatomy-Aware Segmentation
  • Figure 2: Training framework of Structure-Guided Reasoning
  • Figure 3: Performance comparison of our model at different stages
  • Figure 4: Qualitative spatiotemporal consistency analysis across the full angiographic sequence. Columns represent different models, while rows illustrate the hemodynamic progression from Wash-in (top) to Peak (middle) and Wash-out (bottom) phases. The foundation model MedSAM3Liu2025MedSAM3 (Column c) exhibits significant topological fragmentation during the low-contrast wash-out phase (red arrows), confirming the semantic-topological gap. In contrast, ARIADNE (Column j) maintains robust structural continuity throughout the sequence (green arrows).
  • Figure 5: Each row represents a different clinical case. Left Column: Original X-ray angiograms. Middle Column: The extracted vascular tree with detected stenosis locations (marked by blue dots for candidates and green dots for final detections) identified by the RL navigation agent. Right Column: Expert annotations highlighting the ground truth stenotic lesions (indicated by red arrows).The alignment between the agent's predictions and expert labels demonstrates the system's capability to accurately localize hemodynamically significant lesions even in complex anatomical configurations.