MixLacune: Segmentation of lacunes of presumed vascular origin

TL;DR

This paper introduces an automatic two-stage deep learning approach combining Mask R-CNN and U-Net for accurate segmentation of lacunes in brain MRI, improving over manual and semi-automatic methods.

Contribution

The work presents a novel two-stage deep learning pipeline specifically designed for lacune segmentation, with publicly available code and high accuracy metrics.

Findings

Mean DICE score of 0.84 on validation set

Effective two-stage detection and segmentation pipeline

Source code and Docker container available for reproducibility

Abstract

Lacunes of presumed vascular origin are fluid-filled cavities of between 3 - 15 mm in diameter, visible on T1 and FLAIR brain MRI. Quantification of lacunes relies on manual annotation or semi-automatic / interactive approaches; and almost no automatic methods exist for this task. In this work, we present a two-stage approach to segment lacunes of presumed vascular origin: (1) detection with Mask R-CNN followed by (2) segmentation with a U-Net CNN. Data originates from Task 3 of the "Where is VALDO?" challenge and consists of 40 training subjects. We report the mean DICE on the training set of 0.83 and on the validation set of 0.84. Source code is available at: https://github.com/hjkuijf/MixLacune . The docker container hjkuijf/mixlacune can be pulled from https://hub.docker.com/r/hjkuijf/mixlacune .