Detection of Microcalcifications in Digitized Mammograms Based on Bootstrap Classical Machine Learning Method
W. Jai Singh, S. Devaarul · International journal of engineering and future technology · 2016
Computer-Aided mammography is an important and challenging task in automated detection of cancer. It has great potential over traditional interpretation of film-screen mammography in terms of efficiency and accuracy. Microcalcifications are the earliest sign of breast carcinomas and their early detection is one of the key issues for breast cancer growth control. This paper presents an approach for detecting cluster of microcalcifications in digital mammograms employing Bootstrap Classical Machine Learning (BCML) Method. The proposed algorithm is capable of detecting the microcalcifications of varying intensity distribution. The experimental results show that the detection method has a sensitivity of 93.3% at 0.26 false positive clusters per image. A series of clinical mammograms are employed to test the proposed algorithm and the performance is evaluated. The experiments aptly show that the microcalcifications can be accurately detected even in very dense mammograms using the new method.