Design and development of the computer vision algorithm for a real-time breast self-examination

Breast cancer is the most common cancer among women worldwide. Early detection of breast cancer is the key to reduce breast cancer mortality. Breast self-examination (BSE) is considered as the most cost-effective approach available for early breast cancer detection. A large fraction of breast cancer...

Full description

Saved in:
Bibliographic Details
Main Author: Eman, Mohammadi Nejad
Format: text
Language:English
Published: Animo Repository 2014
Online Access:https://animorepository.dlsu.edu.ph/etd_masteral/4604
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: De La Salle University
Language: English
Description
Summary:Breast cancer is the most common cancer among women worldwide. Early detection of breast cancer is the key to reduce breast cancer mortality. Breast self-examination (BSE) is considered as the most cost-effective approach available for early breast cancer detection. A large fraction of breast cancers are actually found by patients using this technique today. In BSE, the patient should use a proper search strategy to cover the whole breast region in order to detect all possible tumors and abnormalities. However, the majority of women don't perform the correct BSE due to the lack of confidence and knowledge on BSE performance. Therefore, there is a need for an application to educate and evaluate the BSE performance. So, women can perform the BSE using a webcam, computer, and the stated application that has the ability to evaluate the BSE performance. The general objective of this thesis is to design and develop the computer vision algorithm to evaluate the BSE performance in terms of covering the entire breast region. In this research, three individual algorithms were developed and implemented. The first algorithm focuses on detecting and tracking the nipples in frames while a woman performs BSE the second algorithm focuses on localizing the breast region and blocks of pixels for making palpation on the breast, and the third algorithm focuses on detecting the palpated blocks in the breast region. The palpated blocks are highlighted at the time of BSE performance. Finally, if all areas in the breast region are palpated, the BSE training is considered as a correct performance in terms of covering and palpating the whole breast region. If any abnormality, such as masses, is detected, then this must be reported to a doctor, who will confirm the presence of this abnormality or mass and proceed to do other confirmatory tests.