Segmentation masks mini-MIAS

This dataset provides manually created segmentation masks of the images in the mini-MIAS dataset by J Suckling et al[1] (available at http://peipa.essex.ac.uk/info/mias.html). The masks are saved as nrrd files with pixel-wise ground truth for background (0), breast (1), and pectoral muscle (2) (when present). This dataset is created for the development of a mammogram segmentation model[2].

Segmentation masks were created in three steps, first initialization of the breast boundary by Otsu thresholding[3], second a pectoral muscle initialization with Otsu thresholding, and lastly a manual adjustment of the mask. The pectoral muscle initialization was done by re-applying the Otsu thresholding method after excluding the background. Finally, each segmentation mask was checked visually and adjusted manually using ITK-SNAP 3.6.013[4] by one of four medical imaging scientists with experience in mammography. 

[1] J Suckling et al, "The Mammographic Image Analysis Society Digital Mammogram Database" Exerpta Medica. International Congress Series 1069, 375-378 (1994)[2] S.D. Verboom et al., "Deep learning-based breast region segmentation in raw and processed digital mammograms: generalization across views and vendors", Journal of Medical Imaging, 11(1), 014001 (2023)[2] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Trans. Syst. Man. Cybern. 9(1), 62–66 (1979)[3] P. A. Yushkevich et al., "User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability," Neuroimage 31(3), 1116–1128 (2006)