Accurate characterization of microcalcifications (MCs) in 2D full-field digital screening mammography is a necessary step towards reducing diagnostic uncertainty associated with the callback of women with suspicious MCs. Quantitative analysis of MCs has the potential to better identify MCs that have a higher likelihood of corresponding to invasive cancer. However, automated identification and segmentation of MCs remains a challenging task with high false positive rates. We present Hessian Difference of Gaussians Regression (HDoGReg), a two stage multi-scale approach to MC segmentation. Candidate high optical density objects are first delineated using blob detection and Hessian analysis. A regression convolutional network, trained to output a function with higher response near MCs, chooses the objects which constitute actual MCs. The method is trained and validated on 435 mammograms from two separate datasets. HDoGReg achieved a mean intersection over the union of 0.670±0.121 per image, intersection over the union per MC object of 0.607±0.250 and true positive rate of 0.744 at 0.4 false positive detections per cm2. The results of HDoGReg perform better when compared to state-of-the-art MC segmentation and detection methods.
@article{arxiv.2102.00754,
title = {Segmentation of Breast Microcalcifications: A Multi-Scale Approach},
author = {Chrysostomos Marasinou and Bo Li and Jeremy Paige and Akinyinka Omigbodun and Noor Nakhaei and Anne Hoyt and William Hsu},
journal= {arXiv preprint arXiv:2102.00754},
year = {2021}
}