A novel ROI extracting technique based on wavelet transform for the detection of micro-calcifications in mammograms.
- Author:
Shunan LI
1
;
Baikun WAN
;
Zhenhe MA
;
Ruiping WANG
Author Information
1. Department of Biomedical Engineering, Tianjin University, Tianjin 300072, China.
- Publication Type:Journal Article
- MeSH:
Breast Diseases;
diagnostic imaging;
pathology;
Breast Neoplasms;
diagnostic imaging;
pathology;
Calcinosis;
diagnostic imaging;
Diagnosis, Computer-Assisted;
Humans;
Mammography
- From:
Journal of Biomedical Engineering
2005;22(2):360-362
- CountryChina
- Language:Chinese
-
Abstract:
In order to preprocess mammograms for diagnosing the early cases of breast cancer and improving the computational efficiency in the computer-aided detection of micro-calcifications in mammograms, we have advanced a novel processing technique for the extraction of micro-calcification region of interest (MROI). The proposed method is based on a three-step procedure: (1) the mammogram is divided into sub-images of the same size; (2) the wavelet multi-resolution method is conducted on the sub-images, and the parameters related to wavelet transform and threshold T are discussed according to rho; (3) the classification of sub-images is determined by T. It is tested with 20 mammograms and the results show that the method can achieve a true positive rate as high as 89.7% with a false positive rate as low as 2.1%.
