Evaluation of Hue Saturation Value Thresholded Breast Cancer Histopathological Image Detection on Ensemble Models

Anik, Baris (2023) Evaluation of Hue Saturation Value Thresholded Breast Cancer Histopathological Image Detection on Ensemble Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (5MB) | Preview
Preview	PDF (Configuration manual) Download (859kB) | Preview

Abstract

Breast cancer is currently the most common type of cancer in the world. Current studies show that computer-assisted detection and diagnosis of breast cancer may be helpful. Developing algorithms to operate in this area helps reduce human errors in the diagnostic process and shortens this process. Convolutional neural networks (CNN) based models are frequently used for visual processing in breast cancer diagnosis. For this reason, in this study, CNN-based transfer learning models with potential success were first compared, and then various ensemble models were established with successful individual models. Hue saturation value (HSV) is a frequently preferred color space in medical visual processing studies. It was preferred in this study because it is closest to human perception and easier to manipulate. This study specifically examines the effect of images thresholded in HSV color space on ensemble models. The study results show that HSV thresholding negatively affects performance in individual models. However, HSV is secondary in ensemble models but shows results very close to not-thresholded ensemble models. In addition, HSV models have been observed to perform better than the original models in all magnification factors except 40X.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer) T Technology > Biomedical engineering Q Science > Life sciences > Medical sciences > Pathology > Tumors > Cancer
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	21 Oct 2024 12:41
Last Modified:	21 Oct 2024 12:41
URI:	https://norma.ncirl.ie/id/eprint/7110

Actions (login required)

View Item