A Review on Computer Aided Diagnosis of Breast Cancer Using Image Processing and Pattern Recognition Techniques
Breast cancer has been the main cause for high mortality rate in women. To improve the survival rate, regular screening and early diagnosis of breast cancer is essential. Mammography imaging reveals the presence of calcifications if present. These calcifications can be classified as benign and malignant, out of which malignant ones need serious attention. Manual investigation of these images is time consuming and error-prone. Computer based approaches are sought for this purpose. Image processing and pattern recognition based techniques have been widely adopted in this regard. This work reviews the existing approaches owing to image processing and pattern recognition towards breast tumour identification. The approaches are divided into filtering based, morphology based, multi-scale based, model based and pattern recognition based approaches to facilitate a clear understanding. The work suggests that opportunities still exists in various aspects to improve the detection accuracy of breast cancer.
Keywords - Breast cancer; Mammogram; Image Processing; Pattern Recognition; Morphology; Filtering; Multi-scale.