Microcalcifications Detection Using Image And Signal Processing Techniques For Early Detection Of Breast Cancer
Date of Award
Doctor of Philosophy (PhD)
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.
Islam, Md Shafiul, "Microcalcifications Detection Using Image And Signal Processing Techniques For Early Detection Of Breast Cancer" (2016). Theses and Dissertations. 2029.