Exploring Large Context for Cerebral Aneurysm Segmentation

TL;DR

This paper presents a 3D U-Net based method with large context for cerebral aneurysm segmentation from CT scans, achieving high accuracy in a MICCAI challenge.

Contribution

The novel approach configures a 3D U-Net with a large patch size to incorporate extensive context for improved segmentation performance.

Findings

Ranked second in MICCAI 2020 CADA challenge

Achieved average Jaccard of 0.7593

Method code and models are publicly available

Abstract

Automated segmentation of aneurysms from 3D CT is important for the diagnosis, monitoring, and treatment planning of the cerebral aneurysm disease. This short paper briefly presents the main technique details of the aneurysm segmentation method in the MICCAI 2020 CADA challenge. The main contribution is that we configure the 3D U-Net with a large patch size, which can obtain the large context. Our method ranked second on the MICCAI 2020 CADA testing dataset with an average Jaccard of 0.7593. Our code and trained models are publicly available at \url{https://github.com/JunMa11/CADA2020}.