Accession Number : ADA303515
Title : Classification of Microcalcification of the Diagnosis of Breast Cancer using Artificial Neural Networks.
Descriptive Note : Annual rept. 1 Sep 94-31 Aug 95,
Corporate Author : GEORGETOWN UNIV WASHINGTON DC
Personal Author(s) : Wu, Yuzheng C.
PDF Url : ADA303515
Report Date : SEP 1995
Pagination or Media Count : 26
Abstract : Early detection of breast cancer depends on the accurate classification of microcalcifications. We have developed a computer vision system that can classify microcalcifications objectively and consistently to aid radiologists in the diagnosis of breast cancer. A convolution neural network (CNN) was employed to classify benign and malignant microcalcifications in the radiographs of pathological specimen. Digital images were acquired by digitizing radiographs at a high resolution of 21 % m x 21 %m. Eighty regions of interest selected from digitized radiographs of pathological specimen were used for the training and testing of the neural network system. The CNN achieved an Az value of 0.90 in classifying clusters of microcalcifications associated with benign and malignant processes. The classification of microcalcifications for the diagnosis of breast cancer was achieved at a high level in our computer vision system that consists of high resolution digitization of mammograms and a CNN. We have demonstrated the great potential of CNN in classification of microcalcifications for diagnosis of breast cancer.
Descriptors : *NEURAL NETS, *DIAGNOSIS(MEDICINE), *MAMMARY GLANDS, *BREAST CANCER, DIGITAL SYSTEMS, ACCURACY, HIGH RESOLUTION, CLUSTERING, IMAGES, CLASSIFICATION, COMPUTER VISION, ANALOG TO DIGITAL CONVERTERS, CANCER, CONVOLUTION.
Subject Categories : Medicine and Medical Research
Anatomy and Physiology
Medical Facilities, Equipment and Supplies
Distribution Statement : APPROVED FOR PUBLIC RELEASE