Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior

2025-07-31

AI Summary

Intracranial aneurysms (IAs) pose significant challenges for detection and segmentation in time-of-flight magnetic resonance angiography (TOF-MRA) due to their small size and low contrast, compounded by the absence of large-scale public datasets with voxel-wise annotations. To address this, we propose a weakly supervised multi-task 3D U-Net that innovatively incorporates Frangi vesselness filtering to generate soft vascular priors—jointly guiding network input, channel-wise attention, and an auxiliary detection branch—enabling end-to-end co-optimization of detection and segmentation. The method requires only coarse-grained annotations for training. On an internal test set, it achieves a Dice score of 0.614, 95% Hausdorff distance of 1.38 mm, detection sensitivity of 92.9%, and a false positive rate of 1.47 per volume. External validation confirms strong generalizability. This work establishes a novel paradigm for weakly supervised, precise analysis of small, low-contrast vascular lesions.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Intracranial aneurysms (IAs) are abnormal dilations of cerebral blood vessels that, if ruptured, can lead to life-threatening consequences. However, their small size and soft contrast in radiological scans often make it difficult to perform accurate and efficient detection and morphological analyses, which are critical in the clinical care of the disorder. Furthermore, the lack of large public datasets with voxel-wise expert annotations pose challenges for developing deep learning algorithms to address the issues. Therefore, we proposed a novel weakly supervised 3D multi-task UNet that integrates vesselness priors to jointly perform aneurysm detection and segmentation in time-of-flight MR angiography (TOF-MRA). Specifically, to robustly guide IA detection and segmentation, we employ the popular Frangi's vesselness filter to derive soft cerebrovascular priors for both network input and an attention block to conduct segmentation from the decoder and detection from an auxiliary branch. We train our model on the Lausanne dataset with coarse ground truth segmentation, and evaluate it on the test set with refined labels from the same database. To further assess our model's generalizability, we also validate it externally on the ADAM dataset. Our results demonstrate the superior performance of the proposed technique over the SOTA techniques for aneurysm segmentation (Dice = 0.614, 95%HD =1.38mm) and detection (false positive rate = 1.47, sensitivity = 92.9%).

Problem

• Detecting small intracranial aneurysms in MR angiography scans
• Segmenting aneurysms with weak supervision and limited annotations
• Improving accuracy using vesselness priors and multi-task learning

Innovation

• Weakly supervised 3D multi-task UNet model
• Integrates vesselness priors for detection
• Uses Frangi's filter for cerebrovascular attention