Abnormality Detection and Classification in Computer-Aided Diagnosis (CAD) of Breast Cancer Images

作者：Patel Bhagwati Charan^*; Sinha G R

来源：Journal of Medical Imaging and Health Informatics, 2014, 4(6): 881-885.

DOI：10.1166/jmihi.2014.1349

• Breast Cancer
• Mammographic Image
• Segmentation
• Tumor
• Sensitivity
• Specificity
• Accuracy

This paper presents a new approach for abnormality detection and classification of tumour in mammographic breast cancer images. The detection of masses is achieved in terms of their size and shape that can greatly help in early detection of breast tumor in breast images. The objective of the work is to detect the abnormal tumor or tissue inside mammographic breast cancer images using three stages namely pre-processing, segmentation and post processing. Pre-processing is used to reduce the noise signal and then segmentation is applied to detect the masses or abnormalities. Finally, post processing helps to find out the benign and malignant tissue with the affected area in the breast cancer image. The occurrences of cancer nodules are identified clearly and classified too. The algorithm achieves 96.5% sensitivity, 89% specificity and 95.6% accuracy value as compared with the observation by a radiologist.

• 出版日期2014-12