Voxelwise Detection of Cerebral Microbleed in CADASIL Patients by Genetic Algorithm and Back Propagation Neural Network

DOI

10.2991/cimns-18.2018.23How to use a DOI?

Keywords

voxelwise detection; CADASIL; genetic algorithm; back propagation neural network

Abstract

In this study, we proposed an application of voxelwise detection of cerebral microbleed in CADASIL patients by genetic algorithm (GA) and back propagation neural network (BPNN).We collected in total 20 subjects, and obtained 69,356 CMB voxels, and 124,063,981 non-CMB voxels. We employed BPNN as the classification tool. For BPNN has better prediction, we used GA to optimize BPNN. Finally, we used 10-fold cross validation to verify classifier performance. Our method obtained a sensitivity of 72.90±1.38%, a specificity of 72.89±1.18%, and an accuracy of 72.90±1.28%.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanyuan Tao
AU  - Rayan S Cloutie
PY  - 2018/11
DA  - 2018/11
TI  - Voxelwise Detection of Cerebral Microbleed in CADASIL Patients by Genetic Algorithm and Back Propagation Neural Network
BT  - Proceedings of the 2018 3rd International Conference on Communications, Information Management and Network Security (CIMNS 2018)
PB  - Atlantis Press
SP  - 101
EP  - 105
SN  - 2352-538X
UR  - https://doi.org/10.2991/cimns-18.2018.23
DO  - 10.2991/cimns-18.2018.23
ID  - Tao2018/11
ER  -