A Study on Classification of Masses on Mammograms into Malignancy and Benignacy

概要

論文の詳細を見る
To get the knowledge of the diagnostic process when experts diagnose breast cancers by using mammograms is one of the important subjects in constructing the computer-aided diagnosis(CAD)system for detecting breast cancers. In this study, we investigated the classification flowchart for the diagnosis of breast masses on mammograms in cooperation with an expert radiologist. From many features of the masses such as "sharp outline" and "stellate boundary", we selected 13 features and weighted them by integer values from-1 to 2. The classification was achieved based on the total amount of the weighted values for all features. We examined our classification flowchart by use of 99 mammograms, and found that except the very difficult three cases the classification rate for defining the mass as malignancy or benign was very high, i. e. sensitivity of 84% and spesificity of 96%.
Medical Imaging and Information Sciencesの論文