Construction of Probabilistic Atlas and Its Application to Detection of Lacunar Infarcts

DOI

10.2991/aiie-15.2015.93How to use a DOI?

Keywords

lacunar infarcts; probabilistic atlas; computer aided diagnosis; magnetic resonance image

Abstract

In this paper, we propose using probabilistic atlas of lacunar infarcts to improve accuracy of lacunar infarcts detection. The cerebral vascular disease is responsible for about 10% of all death in Japan. Therefore, Brain dock is popular method to take preventive measures in Japan. In this Brain dock, there are two common diseases that are found. One is lacunar infarct and other is Enlarged Virchow-Robin space. Lacunar infarcts have the risk for developing stroke. On the other hand, Enlarged Virchow-Robin space is low-risk disease. Distinguishing these two diseases is important task of Brain dock. However these two diseases have similar appearance on Magnetic Resonance (MR) images. Thus, doctors raise expectations for Computer Aided Diagnosis (CAD) of lacunar infarcts. We focused on favorite site of lacunar infarcts and made the probabilistic atlas for one of the feature of machine learning. The experimental results validate that the probabilistic atlas can improve the accuracy of lacunar infarcts.

Copyright

© 2015, 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  - H. Tanaka
AU  - A. Shiino
AU  - T. Tateyama
AU  - X.H. Han
AU  - X. Wei
AU  - Y.W. Chen
PY  - 2015/07
DA  - 2015/07
TI  - Construction of Probabilistic Atlas and Its Application to Detection of Lacunar Infarcts
BT  - Proceedings of the 2015 International Conference on Artificial Intelligence and Industrial Engineering
PB  - Atlantis Press
SP  - 334
EP  - 336
SN  - 1951-6851
UR  - https://doi.org/10.2991/aiie-15.2015.93
DO  - 10.2991/aiie-15.2015.93
ID  - Tanaka2015/07
ER  -