Sanjay Purushotham1, Ashwathy Samivel Sureshkumar1, Li Jiang2, Shiyu Tang2, Steven Roys2, Chandler Sours Rhodes2,3, Rao P. Gullapalli2, and Jiachen Zhuo2
1Department of Information System, University of Maryland, Baltimore County, Baltimore, MD, United States, 2Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States, 3National Intrepid Center of Excellence, Walter Reed National Military Medical Center, Bethesda, MD, United States
1Department of Information System, University of Maryland, Baltimore County, Baltimore, MD, United States, 2Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, United States, 3National Intrepid Center of Excellence, Walter Reed National Military Medical Center, Bethesda, MD, United States
Mild traumatic brain injury (mTBI) patients account for over 70% of all TBI, with some experiencing persistent post concussive symptoms. Here we present a novel method for latent feature extraction from acute volumetric MRI and show how it improved our 18-month symptom prediction in patients.
Figure 1: Graphical Model for the brain region volumetric matrix factorization. C = {Cik} is brain region adjacency matrix, B and Z are latent brain region and factor feature matrices with Bi and Zk representing brain-region specific and factor-specific latent feature vectors. Pj represents patient latent vector for patient j. Rij represents the volumetric observation (value) of brain region i for patient j.
Figure 2: AUROC and Accuracy plots for predicting patient long-term outcome (PCS labels) using different feature sets.