| Presentation | 2001/7/20 Classification method of mammographic microcalsifications on high resolution digitized images Takeshi Hara, Norimitsu Shinohara, Yoshitaka Ooe, Hiroshi Fujita, Tokiko Endo, Takuji Iwase, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We have been developing a computer-aided diagnosis (CAD) system for mammograms. The system detects clustered area of mammographic microcalcifications based on density gradient analysis, and it is classified according to analyzing the features based on BI-RADS by ANN. Although the image digitized with 100-μm sampling distance (100-μm image) is used now, the image digitized with 50-μm sampling distance (50-μm image) can be used by improvement in apparatus. We propose the technique of classifying mammographic microcalcifications using 50-μm image. Therefore, the re-detection processing by 50-μm image and the flat and smooth-ized processing for noise removal are added to the conventional method. As a result of applying this technique to clinical data 85 case (126 images), 10% of improvement was seen at the rate of a correct answer, and as a result of ROC analysis, the validity of this technique was shown. It is concluded that the classification of mammographic microcalcifications with high accuracy is attained from these results by using a high resolution image (50-μm image) effectively. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | mammograms / computer-aided diagnosis / microcalcifications / classification |
| Paper # | MI2001-30 |
| Date of Issue |
| Conference Information | |
| Committee | MI |
|---|---|
| Conference Date | 2001/7/20(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Medical Imaging (MI) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Classification method of mammographic microcalsifications on high resolution digitized images |
| Sub Title (in English) | |
| Keyword(1) | mammograms |
| Keyword(2) | computer-aided diagnosis |
| Keyword(3) | microcalcifications |
| Keyword(4) | classification |
| 1st Author's Name | Takeshi Hara |
| 1st Author's Affiliation | Department of Information Science, Faculty of Engineering, Gifu University() |
| 2nd Author's Name | Norimitsu Shinohara |
| 2nd Author's Affiliation | Department of Information Science, Faculty of Engineering, Gifu University |
| 3rd Author's Name | Yoshitaka Ooe |
| 3rd Author's Affiliation | Department of Information Science, Faculty of Engineering, Gifu University |
| 4th Author's Name | Hiroshi Fujita |
| 4th Author's Affiliation | Department of Information Science, Faculty of Engineering, Gifu University |
| 5th Author's Name | Tokiko Endo |
| 5th Author's Affiliation | Department of Radiology, National Hospital of Nagoya |
| 6th Author's Name | Takuji Iwase |
| 6th Author's Affiliation | Department of Breast Surgery, Aichi Cancer Center Hospital |
| Date | 2001/7/20 |
| Paper # | MI2001-30 |
| Volume (vol) | vol.101 |
| Number (no) | 239 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |