Development of similar image retrieval system for breast cancer diagnostic aid
Project/Area Number |
21791179
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Single-year Grants |
Research Field |
Radiation science
|
Research Institution | Gifu University |
Principal Investigator |
MURAMATSU Chisako 岐阜大学, 大学院・医学系研究科, 特定研究補佐員 (80509422)
|
Project Period (FY) |
2009 – 2012
|
Project Status |
Completed (Fiscal Year 2012)
|
Budget Amount *help |
¥4,657,796 (Direct Cost: ¥3,582,920、Indirect Cost: ¥1,074,876)
Fiscal Year 2012: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2011: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2010: ¥1,407,796 (Direct Cost: ¥1,082,920、Indirect Cost: ¥324,876)
Fiscal Year 2009: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
Keywords | 乳癌 / コンピュータ支援診断 / 画像処理 / 乳がん / 類似画像検索 / ディジタルマンモグラフィ / デジタルマンモグラフィ |
Research Abstract |
The purpose of this study was to develop a computer-aided diagnosis system that searches for similar already-diagnosed images as a reference. First, we have established a new digital mammography database and determined image features by computerized analysis. The gold standard of similarity for selecting reference images was obtained by experts. Using an artificial neural network and multidimensional scaling, we were able to determine similarity measures that correlate well with the gold standard. In the observer study, diagnostic accuracies were slightly improved by the presentation of similar images for both physician and radiological technologist groups.
|
Report
(5 results)
Research Products
(33 results)