Semi-supervised learning and integration of multi-sequence MR-images for carotid vessel wall and plaque segmentation

2025-07-10

AI Summary

To address the challenges of limited labeled data and complex plaque morphology in carotid MRI—leading to low segmentation accuracy—this paper proposes a semi-supervised framework for vascular wall and plaque segmentation across multi-sequence MRI. Methodologically, it employs a dual-network architecture (coarse localization followed by fine segmentation) and introduces a multi-level, multi-sequence U-Net fusion module to enhance cross-modal feature collaboration. Additionally, input-transformation-based consistency regularization is incorporated to effectively leverage unlabeled data. Experiments on multi-sequence MRI from 52 patients demonstrate statistically significant improvements in Dice score and boundary accuracy (p < 0.01), with expert evaluation confirming clinical reliability. This work represents the first integration of hierarchical multi-sequence feature fusion with consistency-regularized semi-supervised learning for carotid plaque segmentation, establishing a generalizable technical paradigm for low-resource medical image analysis.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Web data integration and cleaning

Abstract

The analysis of carotid arteries, particularly plaques, in multi-sequence Magnetic Resonance Imaging (MRI) data is crucial for assessing the risk of atherosclerosis and ischemic stroke. In order to evaluate metrics and radiomic features, quantifying the state of atherosclerosis, accurate segmentation is important. However, the complex morphology of plaques and the scarcity of labeled data poses significant challenges. In this work, we address these problems and propose a semi-supervised deep learning-based approach designed to effectively integrate multi-sequence MRI data for the segmentation of carotid artery vessel wall and plaque. The proposed algorithm consists of two networks: a coarse localization model identifies the region of interest guided by some prior knowledge on the position and number of carotid arteries, followed by a fine segmentation model for precise delineation of vessel walls and plaques. To effectively integrate complementary information across different MRI sequences, we investigate different fusion strategies and introduce a multi-level multi-sequence version of U-Net architecture. To address the challenges of limited labeled data and the complexity of carotid artery MRI, we propose a semi-supervised approach that enforces consistency under various input transformations. Our approach is evaluated on 52 patients with arteriosclerosis, each with five MRI sequences. Comprehensive experiments demonstrate the effectiveness of our approach and emphasize the role of fusion point selection in U-Net-based architectures. To validate the accuracy of our results, we also include an expert-based assessment of model performance. Our findings highlight the potential of fusion strategies and semi-supervised learning for improving carotid artery segmentation in data-limited MRI applications.

Problem

• Segmentation of carotid artery vessel wall and plaque using multi-sequence MRI
• Integration of complementary information from different MRI sequences
• Addressing limited labeled data with semi-supervised learning approach

Innovation

• Semi-supervised deep learning for plaque segmentation
• Multi-level multi-sequence U-Net architecture
• Coarse-to-fine two-network segmentation approach