An Image processing system using two view mammograms for reading masses
Project/Area Number |
19790907
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Single-year Grants |
Research Field |
Radiation science
|
Research Institution | The University of Shiga Prefecture (2008-2009) Gifu National College of Technology (2007) |
Principal Investigator |
HATANAKA Yuji The University of Shiga Prefecture, 工学部, 准教授 (00353277)
|
Co-Investigator(Renkei-kenkyūsha) |
FUJITA Hiroshi 岐阜大学, 大学院・医学系研究科, 教授 (10124033)
|
Project Period (FY) |
2007 – 2009
|
Project Status |
Completed (Fiscal Year 2009)
|
Budget Amount *help |
¥2,720,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥420,000)
Fiscal Year 2009: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2008: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2007: ¥900,000 (Direct Cost: ¥900,000)
|
Keywords | 画像診断学 / 医用・生体画像 / マンモグラム / コンピュータ支援診断 / 差分処理 / マンモモグラム / 位置合わせ / 自動認識 |
Research Abstract |
It is important for reading mammograms to compare right and left breast tissues. But, right and left mammograms were asymmetry. In this study, both mammograms were aligned automatically by both nipples, which were detected automatically. And then automatic mass detection algorithm of computer-aided diagnosis system was improved by a feature, which was that normal breast tissues on both mammograms were similar. Specifically, the similarity of both mammograms was analyzed by using correlations, the average differential densities on both images, he higher order local autocorrelation feature.
|
Report
(4 results)
Research Products
(6 results)