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

• Published in: European journal of radiology 2001-07, Vol.39 (1), p.60-65
• Main Authors: Markopoulos, Christos, Kouskos, Efstratios, Koufopoulos, Konstantinos, Kyriakou, Vasiliki, Gogas, John
• Format: Article
• Language: English
• Subjects: Adult; Aged; Artificial neural network; Biological and medical sciences; Breast cancer; Breast Diseases - diagnosis; Breast Diseases - diagnostic imaging; Breast Neoplasms - diagnosis; Calcification (biochemistry); Calcinosis - diagnosis; Calcinosis - diagnostic imaging; Computer aided diagnosis; Diagnosis, Differential; Female; Genital system. Mammary gland; Humans; Image analysis; Investigative techniques, diagnostic techniques (general aspects); Mammography; Medical sciences; Microcalcifications; Middle Aged; Neural networks; Neural Networks (Computer); Nonpalpable breast lesions; Radiodiagnosis. Nmr imagery. Nmr spectrometry; ROC Curve
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/S0720-048X(00)00281-3

Introduction/objective: the purpose of this study was to evaluate a computer based method for differentiating malignant from benign clustered microcalcifications, comparing it with the performance of three physicians. Methods and material: materials for the study are 240 suspicious microcalcifications on mammograms from 220 female patients who underwent breast biopsy, following hook wire localization under mammographic guidance. The histologic findings were malignant in 108 cases (45%) and benign in 132 cases (55%). Those clusters were analyzed by a computer program and eight features of the calcifications (density, number, area, brightness, diameter average, distance average, proximity average, perimeter compacity average) were quantitatively estimated by a specific artificial neural network. Human input was limited to initial identification of the calcifications. Three physicians–observers were also evaluated for the malignant or benign nature of the clustered microcalcifications. Results: the performance of the artificial network was 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 physicians were compared and the results are:area under the curve (AUC) value for computer is 0.937, for physician-1 is 0.746, for physician-2 is 0.785, for physician-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 difference between the artificial neural network and the physicians’ performance, independently and as a group. Discussion and conclusion: our study showed that computer analysis achieves statistically significantly better performance 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 suspicious clustered microcalcifications and reduce the number of biopsies for non-palpable benign lesions.