Classification Of Microcalcifications Research Articles

Classification of microcalcifications in radiographs of pathologic specimens for the diagnosis of breast cancer

Early detection of breast cancer depends on accurate classification of microcalcifications. We have developed a computer vision system that has the potential to classify microcalcifications objectively and consistently to aid radiologists in diagnosing breast cancer. A convolution neural network (CNN) was used to classify benign and malignant microcalcifications in radiographs of pathologic specimens. Digital images were acquired by digitizing radiographs at a high resolution of 21 microns x 21 microns. Eighty regions of interest selected from digitized radiographs of pathologic specimens were used for training and testing of the neural network system. The CNN achieved an Az value (area under the receiver operating characteristic curve) of 0.90 in classifying clusters of microcalcifications associated with benign and malignant processes. Classification of microcalcifications in pathologic specimens for diagnosis of breast cancer was achieved at a high level in our computer vision system, which consists of high-resolution digitization of mammograms and a CNN.

ARTIFICIAL NEURAL NETWORK BASED CLASSIFICATION OF MAMMOGRAPHIC MICROCALCIFICATIONS USING IMAGE STRUCTURE FEATURES

Mammography associated with clinical breast examination and breast self-examination is the only effective and viable method for mass breast screening. Most of the minimal breast cancers are detected by the presence of microcalcifications. It is however difficult to distinguish between benign and malignant microcalcifications associated with breast cancer. Most of the techniques used in the computerized analysis of mammographic microcalcifications segment the digitized grey-level image into regions representing microcalcifications. Since mammographic images usually suffer from poorly defined microcalcification features, the extraction of microcalcification features based on segmentation process is not reliable and accurate. We present a second-order grey-level histogram based feature extraction approach which does not require the segmentation of microcalcifications into binary regions to extract features to be used in classification. The image structure features, computed from the second-order grey-level histogram statistics, are used for classification of microcalcifications. Several image structure features were computed for 100 cases of “difficult to diagnose” microcalcification cases with known biopsy results. These features were analyzed in a correlation study which provided a set of five best image structure features. A feedforward backpropagation neural network was used to classify mammographic microcalcifications using the image structure features. Four networks were trained for different combinations of training and test cases, and number of nodes in hidden layers. False Positive (FP) and True Positive (TP) rates for microcalcification classification were computed to compare the performance of the trained networks. The results of the neural network based classification were compared with those obtained using multivariate Baye’s classifiers, and the k-nearest neighbor classifier. The neural network yielded good results for classification of “difficult-to-diagnose” micro-calcifications into benign and malignant categories using the selected image structure features.

Determination of the features used in classification of mammographic microcalcification

Determination of the features used in classification of mammographic microcalcification

Clustered microcalcification in the breast: a prospective study

127 women attending the Edinburgh Breast Screening Centre were found to have small clusters of microcalcifications (maximum diameter 1 cm) of a potentially malignant nature. Using criteria previously postulated, 1 they were classified into three groups: uniform localised, non-uniform widespread, and non-uniform localised, using hand-held magnification. In each group, the risk of malignancy was assessed in the short and long-term. The cancer detection rate of the uniform localised calcification, 67 women, 16 (24%) biopsied, was 0% immediately and 1.5% when a further biopsy was carried out after 2 years. For non-uniform widespread calcification, the cancer detection rate, 49 women, 31 (63%) biopsied, was 6 (12%) immediately and 8 (16%) when a further 3 biopsies were carried out up to 2 years later. The cancer detection rate of non-uniform localised calcifications, 11 women, all biopsied, was 7 (64%). The use of this classification of microcalcification provided a significant predictor for identification of breast cancer (p<0.001). Conventional risk factors were also examined, but none markedly improved discrimination with only family history approaching statistical significance (p = 0.09). The utility of the method in the screening situation is discussed.