Improved Saliency Detection for Abnormalities in Mammograms

Goal: Mammography is the most effective technique for breast cancer screening, and the detection of abnormalities plays a vital role in Computer Aided Detection (CAD) system. This paper proposes a detection method for abnormal mammograms based on improved saliency detection. Methods: The proposed method comprises three main steps: firstly, enhance abnormal mammograms using dual morphological top-hat operations with a non-flat structuring element, secondly, utilize a simple and efficient saliency detector to obtain the saliency value and then employ the modified Simplified Pulse-Coupled Neural Network (SPCNN) to manipulate these saliency value for obtaining suspicious abnormal area, thirdly, the post processing is done to reduce false positives. Conclusion: The proposed method is implemented on open and common database of MIAS, the results show that this novel method outperforms the current state-of-art algorithms. In addition, this method is verified on the mammograms from Gansu Provincial Cancer Hospital, the detection results reveal that our method can accurately detect the abnormal in clinical application. Contributions: we introduce the improved saliency detection to detect abnormalities in mammograms, and the proposed method not only can detect mass, but also can detect micro-calcifications clusters. Significance: This proposed method is simple and effective, furthermore it can achieve high detection rate, we deem it could be considered to be used in CAD system to assist radiologist for breast cancer diagnosis in the future.