A Deep Unsupervised Learning Approach Toward MTBI Identification Using Diffusion MRI
This work addresses the need for accurate, concrete measures of MTBI diagnosis, which is a growing public health issue affecting over 1.7 million people annually in the US, by providing an incremental improvement in detection methods using MRI data.
The paper tackles the problem of detecting mild traumatic brain injury (MTBI) by using diffusion MRI images with deep learning, specifically employing a convolutional auto-encoder for unsupervised feature learning and bag-of-words representation to overcome limited data. The results show that this approach significantly outperforms earlier methods based on mean MR metrics in selected brain regions, with performance similar to using raw patch patterns.
Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.