| Project/Area Number |
21300070
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Ritsumeikan University |
|---|
Principal Investigator |
CHEN Yen-wei 立命館大学, 情報理工学部, 教授 (60236841)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TANAKA Hiromi 立命館大学, 情報理工学部, 教授 (10268154)
TANAKA Satoshi 立命館大学, 情報理工学部, 教授 (60251980)
SATO Yoshinobu 大阪大学, 医学系・研究科, 准教授 (70243219)
FURUKAWA Akira 滋賀医科大学, 医学部, 准教授 (80199421)
MORIKAWA Shigehiro 滋賀医科大学, 医学部, 教授 (60220042)
TATEYAMA Tomoko 立命館大学, 情報理工学部, 助手 (90550153)
HAN Shanfa 立命館大学, 立命館グローバルイノベーション研究機構, ポストドクトラルフェロー (60469195)
|
|---|
| Project Period (FY) |
2009 – 2011
|
| Project Status |
Completed (Fiscal Year 2011)
|
| Budget Amount *help |
¥16,510,000 (Direct Cost: ¥12,700,000、Indirect Cost: ¥3,810,000)
Fiscal Year 2011: ¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2010: ¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2009: ¥8,970,000 (Direct Cost: ¥6,900,000、Indirect Cost: ¥2,070,000)
|
|---|
| Keywords | 一般化N次元主成分分析 / 多次元データ / 統計モデリング / CTボリューム / 医用画像データベース / 統計ボリュームモデル / 統計テキスチャモデル / 成分選択 / CT / 肝臓 / 機械学習 / 計算機支援診断 / 肝硬変 / 統計形状モデル / 主成分分析 / CTデータ / 時系列データ / データベース / 診断支援 / 右葉,左葉 / 医用画像 / テンソル / 肝臓分割 / 少数サンプル / 位置あわせ |
|---|
| Research Abstract |
We proposed a novel tensor based learning method called generalized N-dimensional principal component analysis(GND-PCA) for multi-dimensional data analysis. We also proposed a framework based on GND-PCA and a 3D shape normalization technique for statistical volume(texture) modeling of the liver. The 3D shape normalization technique is used for normalizing liver shapes in order to remove the liver shape variability and capture pure texture variations. The GND-PCA is used to overcome overfitting problems when the training samples are too much fewer than the dimension of the data. The preliminary results of leave-one-out experiments show that the statistical texture model of the liver built by our method can represent an untrained liver volume well, even though the mode is trained by fewer samples. We also demonstrate its potential application to classification of normal and abnormal(with tumors) livers.
|
