Automatic Rodent Brain MRI Lesion Segmentation with Fully Convolutional Networks

TL;DR

This paper introduces RatLesNet, a deep learning Fully Convolutional Network designed for automatic rodent brain lesion segmentation in MRI scans, outperforming existing methods in accuracy and generalization.

Contribution

The study presents the first deep learning approach specifically tailored for rodent brain lesion segmentation, demonstrating superior performance over existing 3D FCNs.

Findings

RatLesNet achieved an average Dice coefficient of 0.88 in cross-validation.

The method outperformed VoxResNet and 3D-U-Net by 3.7% to 38%.

RatLesNet generalized well across different studies with a Dice of 0.79.

Abstract

Manual segmentation of rodent brain lesions from magnetic resonance images (MRIs) is an arduous, time-consuming and subjective task that is highly important in pre-clinical research. Several automatic methods have been developed for different human brain MRI segmentation, but little research has targeted automatic rodent lesion segmentation. The existing tools for performing automatic lesion segmentation in rodents are constrained by strict assumptions about the data. Deep learning has been successfully used for medical image segmentation. However, there has not been any deep learning approach specifically designed for tackling rodent brain lesion segmentation. In this work, we propose a novel Fully Convolutional Network (FCN), RatLesNet, for the aforementioned task. Our dataset consists of 131 T2-weighted rat brain scans from 4 different studies in which ischemic stroke was induced by transient middle cerebral artery occlusion. We compare our method with two other 3D FCNs originally developed for anatomical segmentation (VoxResNet and 3D-U-Net) with 5-fold cross-validation on a single study and a generalization test, where the training was done on a single study and testing on three remaining studies. The labels generated by our method were quantitatively and qualitatively better than the predictions of the compared methods. The average Dice coefficient achieved in the 5-fold cross-validation experiment with the proposed approach was 0.88, between 3.7% and 38% higher than the compared architectures. The presented architecture also outperformed the other FCNs at generalizing on different studies, achieving the average Dice coefficient of 0.79.