Automated prognosis analysis for traumatic brain injury CT images

Abstract

Traumatic brain injury (TBI) is a major cause of deaths worldwide. In this paper, we propose a framework for automatic brain CT image analysis and Glasgow Outcome Scale (GOS) prediction for TBI cases. For each TBI case, we first select a fixed number of images to represent the case, then we extract Gabor features from these images and form a feature vector. As a large number of features are extracted from the images, we use PCA to select the features for training and testing. We then use random forest for training and testing of our prognosis model. The overall accuracy of binary GOS classification is between 73% and 75% for different GOS dichotomizations.

A machine learning model for predicting favorable outcome in severe traumatic brain injury patients after 6 months

“…Several prediction models using machine learning tools were developed to predict GOS based on medical image modalities [5][6][7][8]. Focusing on a specific age group, Hale et al [5,6] used imaging techniques that display many strengths, such as consistency of CT or ubiquitous usage of magnetic resonance imaging, as well as the multimodal techniques based on this imaging techniques.…”