Computerized scene segmentation for the discrimination of architectural features in ductal proliferative lesions of the breast.

The distinction between ductal hyperplasia (DH) and ductal carcinoma in situ (DCIS) still remains a problem in the histological diagnosis of non-invasive breast lesions. In this study, a method was developed for the automatic segmentation and quantitative analysis of breast ducts using knowledge-guided machine vision. This permitted duct profiles and intraduct lumina to be identified and their shape, size, and number computed. These were used to derive measures of duct cribriformity and architectural complexity which were examined as an objective tool in the characterization of duct pattern in proliferative lesions. A total of 215 images of ducts were digitally captured from 22 cases of DCIS and 21 cases of DH diagnosed independently by two pathologists. The cribriformity index proved to be a useful measure of duct architecture, showing a nosotonic increase with increasing duct complexity. The number of lumins also increased with increasing overgrowth of ductal epithelium until the duct was filled. Discriminant analysis of the duct characteristics for benign and malignant groups selected the lumen area/duct area ratio and the duct area as significant discriminatory variables and they were combined into a discriminant function. Of the lumens features, the mean area of the lumen and the polar average (mean of the distribution of the number of events with an increasing spiral from the centre of the duct) were combined into a second discriminant function. Plotting cases against these two functions provided good separation of DH and DCIS groups, with correct classification estimated on the training sample as being over 80 per cent. With an increasing incidence of complex proliferative lesions arising from mammography, the ability to diagnose these lesions correctly is more important than ever. The use of expert system-guided machine vision facilitates the quantitative evaluation of breast duct architecture; along with established histological and cytological criteria, it is hoped that this will lead to a more objective means of diagnosis and disease classification.