Convolutional neural networks for traumatic brain injury classification and outcome prediction

Abstract

The detection and classification of traumatic brain injury (TBI) by medical professionals can vary due to subjectivity and differences in experience. Thus, a computational approach for detecting and classifying TBI would be invaluable for an objective diagnosis of this injury. In this review paper, various machine learning algorithms used to detect, classify, and predict the severity and outcomes of TBI in a clinical setting are discussed. The most promising of these algorithms is the convolutional neural network (CNN), which is highlighted in the review.