| Project/Area Number |
16500119
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Chukyo University |
|---|
Principal Investigator |
HASEGAWA Jun-ichi Chukyo univ., School of Life system Science and Technology, Professor, 生命システム工学部, 教授 (30126891)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TORIWAKI Junichiro Chukyo univ., School of Life system Science and Technology, Professor, 生命システム工学部, 教授 (30023138)
MEKADA Yoshito Chukyo univ., School of Life system Science and Technology, Professor, 生命システム工学部, 教授 (00282377)
MURASE Hiroshi Nagoya univ., Graduate School of Information Science, Professor, 大学院情報科学研究科, 教授 (90362293)
MORI Kensaku Nagoya univ., Graduate School of Information Science, Associate Professor, 大学院情報科学研究科, 助教授 (10293664)
|
|---|
| Project Period (FY) |
2004 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,700,000 (Direct Cost: ¥3,700,000)
Fiscal Year 2006: ¥900,000 (Direct Cost: ¥900,000)
Fiscal Year 2005: ¥1,200,000 (Direct Cost: ¥1,200,000)
Fiscal Year 2004: ¥1,600,000 (Direct Cost: ¥1,600,000)
|
|---|
| Keywords | Visualization / Multi-dimensional images / Image features / Medical X-ray images |
|---|
| Research Abstract |
Visualization of complicated 3D surfaces and reorganization of such pattern are very important task for medical image analysis. In this research project, we propose two kinds of research topics. One is analysis of surface pattern, and another is visualization and navigation scheme of such surface.
To analyze 3D surface, we have developed new method for evaluating the concentration of the line figures on the curved surface called "Concentration Index" and its application to extract stomach cancer candidates from abdominal X-ray CT images. In experiment using 2 cases, we show the effectiveness of our method.
To visualization, a method for automated segmentation of gastric segment named Stomap from 3D abdominal X-ray CT images and its application for the navigation-based diagnosis system. The gastric segment enables us to recognize the position in stomach while diagnosing stomach using virtualized endoscope system. It can also be utilized as a criterion of the appropriateness of navigation path. The number of observed time for each segment based on the gastric segment is proposed for the evaluation of navigation path. We applied the proposed method to ten cases of gastric inner surfaces detected from 3-D CT images. In all cases, segmentation results were acceptable except for the pylorus part. Using the proposed navigation options, it was easy to recognize the anatomical location of the observed area during navigated diagnosis. It was also a simple matter to recognize the observed and unobserved areas after the navigated diagnosis. As for the automated generation of the navigation path, in order to obtain an optimal navigation path, it was important to check the region under suspicion precisely by generating various view directions and by the interactive observation environment.
|
