Cerebral Microbleed Detection by Wavelet Entropy and Naive Bayes Classifier

DOI

10.2991/bbe-17.2017.81How to use a DOI?

Keywords

Wavelet entropy, Cerebral microbleed, Naive Bayesian classifier.

Abstract

(Aim) Current cerebral microbleed detection methods are too complicated, and difficult to train. (Method) We enrolled 10 subjects diagnosed as cerebral microbleed.Our method combined wavelet entropy and naive Bayes classifier. (Results) The simulation results over 10 times of 10-fold cross validation showed that the average sensitivity, average specificity, and average accuracy of our method are 76.90ñ1.81%, 76.91ñ1.58%, and 76.90ñ1.67%, respectively. Our method can identify the CMB areas using only 1.41 seconds. (Conclusion) Our method is effective and rapid.

Copyright

© 2017, 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  - Hai-nan WANG
AU  - Beatrice Gagnon
PY  - 2017/05
DA  - 2017/05
TI  - Cerebral Microbleed Detection by Wavelet Entropy and Naive Bayes Classifier
BT  - Proceedings of the 2nd International Conference on Biomedical and Biological Engineering 2017 (BBE 2017)
PB  - Atlantis Press
SP  - 505
EP  - 510
SN  - 2468-5747
UR  - https://doi.org/10.2991/bbe-17.2017.81
DO  - 10.2991/bbe-17.2017.81
ID  - WANG2017/05
ER  -