MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome

2024-06-07

arXiv.org

AI Summary

May-Thurner syndrome (MTS) poses significant clinical diagnostic challenges due to subtle and highly variable iliac vein compression patterns in CT imaging. To address this, we propose the first end-to-end 3D deep learning framework for early, precise MTS diagnosis. Our method introduces a dual-enhanced positional encoding mechanism that jointly optimizes attention weights and residual connections; integrates a 3D CNN backbone with a custom DEP-MHSA (Dual-Enhanced Positional Multi-Head Self-Attention) module; and employs a multi-scale 3D voxel feature fusion strategy. We also construct and release the first public, MTS-specific CT dataset comprising 747 cases. Evaluated on this benchmark, our model achieves state-of-the-art performance—98.2% accuracy and 0.991 AUC—demonstrating superior capability in modeling fine-grained spatial compression patterns. This work provides a robust, non-invasive technical foundation for large-scale MTS screening.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

May-Thurner Syndrome (MTS), also known as iliac vein compression syndrome or Cockett's syndrome, is a condition potentially impacting over 20 percent of the population, leading to an increased risk of iliofemoral deep venous thrombosis. In this paper, we present a 3D-based deep learning approach called MTS-Net for diagnosing May-Thurner Syndrome using CT scans. To effectively capture the spatial-temporal relationship among CT scans and emulate the clinical process of diagnosing MTS, we propose a novel attention module called the dual-enhanced positional multi-head self-attention (DEP-MHSA). The proposed DEP-MHSA reconsiders the role of positional embedding and incorporates a dual-enhanced positional embedding in both attention weights and residual connections. Further, we establish a new dataset, termed MTS-CT, consisting of 747 subjects. Experimental results demonstrate that our proposed approach achieves state-of-the-art MTS diagnosis results, and our self-attention design facilitates the spatial-temporal modeling. We believe that our DEP-MHSA is more suitable to handle CT image sequence modeling and the proposed dataset enables future research on MTS diagnosis. We make our code and dataset publicly available at: https://github.com/Nutingnon/MTS_dep_mhsa.

Problem

• Diagnosing May-Thurner Syndrome from 3D CT scans accurately
• Detecting subtle anatomical venous compression variations across patients
• Addressing clinical challenges in early MTS diagnosis automation

Innovation

• Dual-enhanced positional multi-head self-attention module
• Multi-scale convolution with positional embeddings
• 3D deep learning framework for CT diagnosis