Computer-Aided Detection of Benign Tumors of the Female Breast

Breast cancer is considered one of the leading causes of women mortality in the world. The key to improving breast cancer is the early diagnosis of tumors through the use of mammography. Screen-film mammography (SFM) is the most commonly used method in Sudan for the detection of breast cancer. However, SFM has limitations due to the variability among screening radiologists in interpreting mammographic images. In order to overcome these limitations, digital mammography (DM) was introduced. An intelligent computer-aided detection (CAD) system can be very helpful for radiologist in detecting and diagnosing benign tumors earlier and faster than typical screening programs. In this study, a data set of 10 digital mammograms containing benign tumors was presented to four radiologists for diagnosis in order to prove the variability between them. Then, we investigated several statistical features and their combinations in order to determine the best combination for diagnosis. We found that a combination of the mean and median in a MATLAB algorithm is the best combination for mammographic benign tumor detection. Results demonstrate that the CAD algorithms showed more sensitivity than the radiologists in terms of diagnosing benign tumors in digital mammograms.