Mammographic mass detection by adaptive thresholding and region growing

We present an efficient method to detect mass lesions on digitized mammogra ms, which consists of breast region extraction, region partitioning, automa tic seed selection, segmentation by region growing, feature extraction, and neural network classification. The method partitions the breast region int o a fat region, a fatty and glandular region, and a dense region, so that d ifferent threshold values can be applied to each partitioned region during processes of the seed selection and segmentation. The mammographic masses a re classified by using four features representing shape, density, and margi n of the segmented regions. The method detects subtle mass lesions with var ious contrast ranges and can facilitate a procedure of mass detection in co mputer-aided diagnosis systems. (C) 2001 John Wiley & Sons, Inc. Int J Imag ing Syst Technol, 11, 340-346, 2000.