Segmentation Masks for the Mini-Mammographic Image Analysis Society (mini-MIAS) Database

Computer-aided diagnosis is a fast-developing area in medical practice and relies on the appropriate preprocessing of images from two dominant acquisition technologies, analog or film-based, and digital. Preprocessing consists of intensity equalization and segmentation of various objects in images. Here, we propose a methodology for the extraction of masks from manually segmented mammograms using affordable consumer electronic devices to provide manual segmentation performed by medical professionals. The result of this work is a database of hand-drawn segmentation masks for usage with the (mini)-MIAS database mammograms. This database can be used as a benchmarking tool for testing the accuracy of automatic breast tissue, pectoral muscle, and dense tissue segmentation algorithms.