A Case Study in Feature Invention for Breast Cancer Diagnosis Using X-Ray Scatter Images

摘要: X-ray mammography is the current clinical method for screening breast cancer, and like any technique, has its limitations. Several groups have reported differences in scattering patterns of normal tumour tissue from breast. This gives rise to hope that scatter analysis techniques may lead a more accurate cost effective diagnosing beast cancer which lends itself automation. particularly challenging exercise due inherent complexity information content complex hetrogenous samples. We use simple naive Bayes classier as our classification system. High-level features are extracted low-level pixel data. paper reports some preliminary results ongoing development this can distinguish between diffraction cancerous tissue, with particular emphasis on invention classification.