Deep Learning Models for Breast Cancer Classification Using Thermal Images

Abstract

Breast cancer is one of the most common and fatal diseases affecting women worldwide. Despite advancements in medical imaging technology, early detection remains difficult, typically constrained by the reliability and accuracy of diagnostic equipment. Thermography, a non-invasive imaging method, has the ability to identify abnormal thermal patterns linked with breast cancer. However, its general adoption has been limited by difficulties such as precise Region of Interest (ROI) segmentation, effective feature extraction, and reliable classification algorithms. The purpose of this thesis is to solve these issues by proposing advanced methodologies for improving breast cancer classification using thermograms. This thesis utilizes the publicly available Database for Mastology Research with Infrared Image (DMR-IR) dataset, which contains infrared breast thermograms.

Description

Keywords

Citation

item.page.endorsement

item.page.review

item.page.supplemented

item.page.referenced