Research on Automatic Detection of Breast Mass
Houjin Chen · Jisuanji fangzhen · 2013
A method to detect mass based on Adaptive Kernel Learning Relevance Vector Machine(AKLRVM) was proposed in this paper.In the proposed method,kernel parameters can be adjusted adaptively,and a sparser model was used,which can greatly improve the detection efficiency.The proposed method was evaluated with mammograms from the Mammographic Image Analysis Society(Mini-MIAS) and from the breast cancer of Peking University People's Hospital.The results show that compared with methods based on SVM,the proposed method achieves better detection accuracy,but it does so with much higher speed of detection and more robust for breasts of different characteristics,which makes it more suitable for clinical application.