Share Email Print

Journal of Medical Imaging • new

BrainSegNet: a convolutional neural network architecture for automated segmentation of human brain structures
Author(s): Raghav Mehta; Aabhas Majumdar; Jayanthi Sivaswamy
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Automated segmentation of cortical and noncortical human brain structures has been hitherto approached using nonrigid registration followed by label fusion. We propose an alternative approach for this using a convolutional neural network (CNN) which classifies a voxel into one of many structures. Four different kinds of two-dimensional and three-dimensional intensity patches are extracted for each voxel, providing local and global (context) information to the CNN. The proposed approach is evaluated on five different publicly available datasets which differ in the number of labels per volume. The obtained mean Dice coefficient varied according to the number of labels, for example, it is 0.844 ± 0.031 and 0.743 ± 0.019 for datasets with the least (32) and the most (134) number of labels, respectively. These figures are marginally better or on par with those obtained with the current state-of-the-art methods on nearly all datasets, at a reduced computational time. The consistently good performance of the proposed method across datasets and no requirement for registration make it attractive for many applications where reduced computational time is necessary.

Paper Details

Date Published: 20 April 2017
PDF: 11 pages
J. Med. Img. 4(2) 024003 doi: 10.1117/1.JMI.4.2.024003
Published in: Journal of Medical Imaging Volume 4, Issue 2
Show Author Affiliations
Raghav Mehta, Centre for Visual Information Technology (CVIT) (India)
Aabhas Majumdar, Ctr. for Visual Information Technology (India)
Jayanthi Sivaswamy, Ctr. for Visual Information Technology (India)

© SPIE. Terms of Use
Back to Top