Towards automated brain aneurysm detection in TOF-MRA: open data, weak labels, and anatomical knowledge

TL;DR

This paper introduces a deep learning model for brain aneurysm detection in TOF-MRA that uses weak labels and anatomical priors, reducing annotation effort and maintaining high performance, validated on in-house and public datasets.

Contribution

The study presents a novel DL approach leveraging weak labels and anatomical knowledge, achieving competitive detection sensitivity with significantly less annotation effort.

Findings

Achieved 83% sensitivity with 0.8 FP per patient on in-house data.

Ranked 4th out of 18 in a public challenge with 68% sensitivity.

Weak labels are four times faster to generate than voxel-wise annotations.

Abstract

Brain aneurysm detection in Time-Of-Flight Magnetic Resonance Angiography (TOF-MRA) has undergone drastic improvements with the advent of Deep Learning (DL). However, performances of supervised DL models heavily rely on the quantity of labeled samples, which are extremely costly to obtain. Here, we present a DL model for aneurysm detection that overcomes the issue with ''weak'' labels: oversized annotations which are considerably faster to create. Our weak labels resulted to be four times faster to generate than their voxel-wise counterparts. In addition, our model leverages prior anatomical knowledge by focusing only on plausible locations for aneurysm occurrence. We frst train and evaluate our model through cross-validation on an in-house TOF-MRA dataset comprising 284 subjects (170 females / 127 healthy controls / 157 patients with 198 aneurysms). On this dataset, our best model achieved a sensitivity of 83%, with False Positive (FP) rate of 0.8 per patient. To assess model generalizability, we then participated in a challenge for aneurysm detection with TOF-MRA data (93 patients, 20 controls, 125 aneurysms). On the public challenge, sensitivity was 68% (FP rate=2.5), ranking 4th/18 on the open leaderboard. We found no signifcant diference in sensitivity between aneurysm risk-of-rupture groups (p=0.75), locations (p=0.72), or sizes (p=0.15). Data, code and model weights are released under permissive licenses. We demonstrate that weak labels and anatomical knowledge can alleviate the necessity for prohibitively expensive voxel-wise annotations.