Quantitative characterization of mass lesions on digitized mammograms for computer-assisted diagnosis

RATIONALE AND OBJECTIVES. To investigate features for discriminating benign from malignant mammographic findings by using computer-aided diagnosis (CA D) and to test the accuracy of CAD interpretations of mass lesions. METHODS. Fifty-five sequential, mammographically detected mass lesions, ref erred for biopsy, were digitized for computerized reevaluation with a CAD s ystem. Quantitative features that characterize spiculation were automatical ly extracted by the CAD system. Data generated by 271 known retrospective c ases were used to set reference values indicating the range for malignant a nd benign lesions. After conventional interpretation of the 55 prospective cases, they were evaluated a second time by the radiologist using the extra cted features and the reference ranges. In addition, a pattern-recognition scheme based on the extracted features was used to classify the prospective cases. Accuracy of interpretation with and without the CAD system was eval uated using receiver operating characteristic (ROC) curve analysis. RESULTS. Sensitivity of the CAD diagnosis for the prospective cases improve d from 92% to 100%. Specificity improved significantly from 26.7% to 66.7%. This was accompanied by a significant increase in the accuracy of diagnosi s from 56.4% to 81.8% and in the positive predictive value from 51.1% to 71 .4%, The A(z) for the CAD ROC curve significantly increased from 0.73 to 0. 90. The performance of the classification scheme was slightly lower than th at of the radiologists' interpretation with the CAD system. CONCLUSIONS. Us e of the CAD system significantly improved the accuracy of diagnosis. The f indings suggest that the classification scheme may improve the radiologist' s ability to differentiate benign from malignant mass Lesions in the interp retation of mammograms.