Abstract
Breast cancer causes numerous deaths worldwide; yet the numbers have decreased in the past years as a result of computer-aided diagnosis and proper treatment. The current paper is addressed to the base of such diagnosis system: pre-processing and segmentation. After a robust pre-processing, an unsupervised version of GrowCut is applied to define the location of the abnormality. We present a method to automatically define the foreground seeds used in GrowCut. For experiments, mammograms from mini-MIAS dataset are used and a precision of 93.63% for the foreground seeds masks is achieved, which leads to promising segmentation results.
Citare
@Inproceedings{Moroz-Dubenco2022AnUT,
author = {Cristiana Moroz-Dubenco and Adél Bajcsi and A. Andreica and C. Chira},
booktitle = {International Conference on Knowledge-Based Intelligent Information & Engineering Systems},
title = {An Unsupervised Threshold-based GrowCut Algorithm for Mammography Lesion Detection},
year = {2022}
}