Virtual Brain Segmenter

The USC Stevens Neuroimaging and Informatics Institute in the Laboratory of Neuro Imaging houses one of the largest collections of neuroanatomical MRI data in the world. Segmentation of MRI scans into brain components is a critical part of our workflow before we can further analyze the data. Although there are several automatic tools for segmentation, no segmentation software is perfectly accurate, so manual correction by visually inspecting the segmentation errors is required. The process of correcting these errors is tedious and time consuming, so we have worked to make this process more efficient. The Duncan Lab, together with RareFaction Interactive, has developed a novel method of performing this task in virtual reality with a new software, Virtual Brain Segmenter (VBS). VBS allows for more efficient, intuitive, and engaging segmentation correction alternative compared with the standard computer graphical user interface.

VBS was selected as a finalist at the 2018 Auggie Awards, and showcased at IEEEVR 2017.

This work was funded by the USC Provost’s Postdoctoral Scholar Research Grant and the Southern California Clinical and Translational Science Institute (SC CTSI).