Name
Abstract | ||
|---|---|---|
In this paper we propose a new method to segment a breast image into several regions. Tumor detection region is constrained to the region only in glandular tissue because the tumors usually occur at glandular tissue in the breast anatomy. We extract texture feature for each point and classify them as several layers using a random forest classifier. Classified points are merged into a large region and small regions are removed by postprocessing. The accuracy of glandular tissue detection rate was about 90%. We applied the conventional tumor detection method in this segmented glandular tissue. After several tests we obtained that tumor detection accuracy improved for 14% and detection time was also reduced. With this method, we can achieve the improvement both on tumor detection accuracy and on the processing time. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1117/12.911695 | Proceedings of SPIE |
Keywords | Field | DocType |
Tumor detection,Ultrasound breast CAD,breast region segmentation | CAD,Computer vision,Ultrasonography,Ultrasound breast,Breast anatomy,Artificial intelligence,Random forest,Physics | Conference |
Volume | ISSN | Citations |
8315 | 0277-786X | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yeong Kyeong Seong | 1 | 22 | 6.38 |
| Moon Ho Park | 2 | 0 | 1.01 |
| eun young ko | 3 | 1 | 1.36 |
| Kyoung-Gu Woo | 4 | 97 | 10.37 |
| Bram van Ginneken | 5 | 4979 | 307.23 |
| carol l novak | 6 | 0 | 1.01 |