Back to search

University of North Dakota

Microcalcifications Detection Using Image And Signal Processing Techniques For Early Detection Of Breast Cancer

Abstract

dc:description.abstract

Breast cancer has transformed into a severe health problem around the world. Early diagnosis is an important factor to survive this disease. The earliest detection signs of potential breast cancer that is distinguishable by current screening techniques are the presence of microcalcifications (MCs). MCs are small crystals of calcium apatite and their normal size ranges from 0.1mm to 0.5mm single crystals to groups up to a few centimeters in diameter. They are the first indication of breast cancer in more than 40% of all breast cancer cases, making their diagnosis critical. This dissertation proposes several segmentation techniques for detecting and isolating point microcalcifications: Otsu’s Method, Balanced Histogram Thresholding, Iterative Method, Maximum Entropy, Moment Preserving, and Genetic Algorithm. These methods were applied to medical images to detect microcalcifications. In this dissertation, results from the application of these techniques are presented and their efficiency for early detection of breast cancer is explained. This dissertation also explains theories and algorithms related to these techniques that can be used for breast cancer detection.

Degree

thesis:*
Name thesis:degree_name
Doctor of Philosophy (PhD)
Level thesis:degree_level
Dissertation
Discipline thesis:degree_discipline
Electrical Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Islam, Md Shafiul
Contributors dc:contributor
  • Naima Kaabouch

Identifiers

dc:identifier.*
Repository record dc:identifier
https://commons.und.edu/theses/2029

Chain of custody

source
Harvested from
University of North Dakota
Base URL
commons.und.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Islam, Md Shafiul. Microcalcifications Detection Using Image And Signal Processing Techniques For Early Detection Of Breast Cancer. Dissertation thesis, https://commons.und.edu/theses/2029