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

TL;DR

This paper introduces a weakly supervised 3D multi-task UNet model with vesselness priors for improved intracranial aneurysm detection and segmentation in MR angiography, addressing challenges of small size and low contrast.

Contribution

It presents a novel multi-task deep learning framework that leverages vesselness priors for joint aneurysm detection and segmentation with limited annotations.

Findings

Outperforms state-of-the-art methods in aneurysm segmentation (Dice=0.614)

Achieves high sensitivity (92.9%) in aneurysm detection

Demonstrates good generalizability on external datasets

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%).