An automatic method to discriminate malignant masses from normal tissue in digital mammograms¹

Abstract

Specificity levels of automatic mass detection methods in mammography are generally rather low, because suspicious looking normal tissue is often hard to discriminate from real malignant masses. In this work a number of features were defined that are related to image characteristics that radiologists use to discriminate real lesions from normal tissue. An artificial neural network was used to map the computed features to a measure of suspiciousness for each region that was found suspicious by a mass detection method. Two data sets were used to test the method. The first set of 72 malignant cases (132 films) was a consecutive series taken from the Nijmegen screening programme, 208 normal films were added to improve the estimation of the specificity of the method. The second set was part of the new DDSM data set from the University of South Florida. A total of 193 cases (772 films) with 372 annotated malignancies was used. The measure of suspiciousness that was computed using the image characteristics was successful in discriminating tumours from false positive detections. Approximately 75% of all cancers were detected in at least one view at a specificity level of 0.1 false positive per image.

Performance improvement in computerized detection of cerebral aneurysms by retraining classifier using feedback data collected in routine reading environment

“…A classifier ensemble trained by the boosting algorithm [14] is employed to classify lesion candidates into true positives  contrast measures (Contrast1 and Contrast2 in [15] )…”

A pilot study of architectural distortion detection in mammograms based on characteristics of line shadows

“…However, slight differences are sometimes seen between central and marginal regions, which might form a difference in contrast between AD and normal tissue. In our study, the following four features [26] related to contrast were selected:…”

Improvement of performance to discriminate malignant tumors from normal tissue on mammograms by feature selection and evaluation of feature selection criteria

“…Considering that the density values near the center of a tumor are in general higher than those around it, the following 9 features [10] are measured for the inner region shown by white and the surrounding region of gray in Fig. 7.…”

“…Isodensity is a feature considered to be effective for the discrimination of the tumors with low-density values [10] and is measured by the following two equations: …”