TBI Contusion Segmentation from MRI using Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based method for segmenting TBI lesions from MRI images, achieving higher accuracy than existing methods and aiding in better understanding of TBI progression.

Contribution

A novel CNN architecture based on Google's Inception model for improved TBI lesion segmentation from MRI images.

Findings

Median Dice score of 0.75, significantly better than competing methods.

Improved segmentation accuracy on 18 TBI patient images.

Outperforms CNN-based DeepMedic and random forest methods.

Abstract

Traumatic brain injury (TBI) is caused by a sudden trauma to the head that may result in hematomas and contusions and can lead to stroke or chronic disability. An accurate quantification of the lesion volumes and their locations is essential to understand the pathophysiology of TBI and its progression. In this paper, we propose a fully convolutional neural network (CNN) model to segment contusions and lesions from brain magnetic resonance (MR) images of patients with TBI. The CNN architecture proposed here was based on a state of the art CNN architecture from Google, called Inception. Using a 3-layer Inception network, lesions are segmented from multi-contrast MR images. When compared with two recent TBI lesion segmentation methods, one based on CNN (called DeepMedic) and another based on random forests, the proposed algorithm showed improved segmentation accuracy on images of 18 patients with mild to severe TBI. Using a leave-one-out cross validation, the proposed model achieved a median Dice of 0.75, which was significantly better (p<0.01) than the two competing methods.