A desing of a computer-aided diagnosis system for classifying diffuse lung opacities in thin-section computed tomography images
Project/Area Number |
25330357
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Life / Health / Medical informatics
|
Research Institution | Ube National College of Technology |
Principal Investigator |
MITANI YOSHIHIRO 宇部工業高等専門学校, 制御情報工学科, 教授 (30321227)
|
Project Period (FY) |
2013-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2013: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | びまん性陰影 / コンピュータ支援診断 / 胸部高分解能CT / 画像認識 / 組合せ特徴 / 局所ヒストグラム特徴 / 局所スライス特徴 / 胸部高分解能CT画像 / 医用画像処理 / 胸部高分解能CT画像 |
Outline of Final Research Achievements |
The classification of diffuse lung opacities in thin-section computed tomography(HRCT) images is an important step for developing a computer-aided diagnosis(CAD) system. In designing the CAD system for classifying diffuse lung opacities in HRCT images, a local histogram and a local slice feature vector has been proposed and shown to be effective, respectively. We have also developed a combined feature vector of a local histogram and a local slice feature vectors in order to improve the diffuse lung opacities classification. Furthermore, we have examined the combined feature vector with normalization techniques. In effectively classifying diffuse lung opacities in HRCT images, we recommend to use the localization of the feature vector.
|
Report
(4 results)
Research Products
(10 results)