TBI Contusion Segmentation from MRI using Convolutional Neural Networks
This work addresses the need for accurate lesion quantification in TBI patients, which is crucial for understanding disease progression, but it is incremental as it builds on existing CNN methods.
The authors tackled the problem of segmenting traumatic brain injury (TBI) contusions from MRI scans using a convolutional neural network based on the Inception architecture, achieving a median Dice score of 0.75, which was significantly better than two competing methods.
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.