Unsupervised 3-D Feature Learning for Mild Traumatic Brain Injury

• Published in: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries Vol. 10154; pp. 282 - 290
• Main Authors: Kao, Po-Yu, Rojas, Eduardo, Chen, Jefferson W., Zhang, Angela, Manjunath, B. S.
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Adjusted Rand Index; Feature Kernel; Feature Representation; Fractional Anisotropy; Mild Traumatic Brain Injury
• ISBN: 9783319555232; 3319555235
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-55524-9_26

We present an unsupervised three-dimensional feature clustering algorithm to gather the mTOP2016 challenge data into 3 groups. We use the brain MR-T1, diffusion tensor fractional anisotropy, and diffusion tensor mean diffusivity images provided by the mTOP2016 competition. A distance-based size constraint method for data clustering is used. The proposed approach achieves 0.267 adjusted rand index and 0.3556 homogeneity score within the 15 labeled subjects, corresponding to 10 correctly classified data items. Based on visual exploration of the data, we believe that a localized analysis of the lesion regions, using the computed tractography data, is a promising direction to pursue.