Detection of Microcalcifications Using Wavelet Techniques in Mammogram Digital Images and Development of a Software for Evaluation of Radiologist Findings

• Main Author: Hasan Al-Qdah, Majdi Taysir
• Format: Thesis
• Language: English; English
• Published: 2006
• Subjects: Breast - Radigraphy - Malaysia - Case studies
• Online Access: http://psasir.upm.edu.my/id/eprint/6113/1/FK_2006_22.pdf; http://psasir.upm.edu.my/id/eprint/6113/
• Institution: Universiti Putra Malaysia

This thesis describes a method of using wavelets in the detection comparison of breast cancer among the three main races in Malaysia: Chinese, Malays, and Indians followed by a system that records and evaluates the radiologist's findings over a period of time to gauge the radiologist's findings in confirming breast cancer cases. A comparison was carried out among few different wavelets to find out the best filter for detection for all three Malaysian races' mammograms. The detection of three filters was presented to three expert radiologists to confirm the best filter detector. As a result, the db4 wavelet was utilized to detect microcalcifications in mammogram digital images obtained from a Malaysian women sample. The wavelet filter's detection evaluation was done by visual inspection to confirm the detection results of those pixels that corresponded to microcaIcifications. Detection was counted if the wavelet detected pixels corresponded to the radiologically identified microcalcification pixels. The findings suggest that no one race mammograms are easier for wavelets' detections of microcalcifications and for the radiologist confirmation. After the radiologist's detection confirmation a new client-sewer radiologist recording and evaluation system is designed to evaluate the findings of the radiologist over some period of cancer detection working time. It is a system that records the findings of the Malaysian radiologist for the presence of breast cancer in Malaysian patients and provides a way of registering the progress of detecting breast cancer of the radiologist by tracking certain metric values such as the sensitivity, specificity, and Receiver Operator Curve (ROC)