| Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Outline of Final Research Achievements |
The purpose of this study is to sophisticate two CAD schemes: (1) for the detection of lacunar infarcts on MR images and (2) for the detection of unruptured aneurysms on MRA images. To improve the method for distinguishing between lacunar infarcts and false positives, we developed eigenspace template matching, kernel eigenspace template matching, and AdaBoost template matching. In addition, we developed a novel technique by using gradient concentration filter bank and random forest in order to sophisticate the method for distinguishing between unruptured aneurysms and false positives. By using these proposed method, we could achieve a high detection performance compared with conventional methods.
|
