Use of artificial neural networks (computer analysis) in the diagnosis of microcalcifications on mammography

Introduction/objective: the purpose of this study was to evaluate a compute r based method for differentiating malignant from benign clustered microcal cifications, comparing it with the performance of three physicians. Methods and material: materials for the study are 240 suspicious microcalcificatio ns on mammograms from 220 female patients who underwent breast biopsy, foll owing hook wire localization under mammographic guidance. The histologic fi ndings were malignant in 108 cases (45%) and benign in 132 cases (55%). Tho se clusters were analyzed by a computer program and eight features of the c alcifications (density, number, area, brightness, diameter average, distanc e average, proximity average, perimeter compacity average) were quantitativ ely estimated by a specific artificial neural network. Human input was limi ted to initial identification of the calcifications. Three physicians-obser vers were also evaluated for the malignant or benign nature of the clustere d microcalcifications. Results: the performance of the artificial network w as evaluated by receiver operating characteristics (ROC) curves. ROC curves were also generated for the performance of each observer and for the three observers as a group. The ROC curves for the computer and for the physicia ns were compared and the results are:area under the curve (AUC) value for c omputer is 0.937, for physician-1 is 0.746, for physician-2 is 0.785, for p hysician-3 is 0.835 and for physicians as a group is 0.810. The results of the Student's t-test for paired data showed statistically significant diffe rence between the artificial neural network and the physicians' performance , independently and as a group. Discussion ann conclusion: our study showed that computer analysis achieves statistically significantly better perform ance than that of physicians in the classification of malignant and benign calcifications. This method, after further evaluation and improvement, may help radiologists and breast surgeons in better predictive estimation of su spicious clustered microcalcifications and reduce the number of biopsies fo r non-palpable benign lesions. (C) 2001 Elsevier Science Ireland Ltd. All r ights reserved.