Use of prior mammograms in the classification of benign and malignant masses

• Published in: European journal of radiology Vol. 56; no. 2; pp. 248 - 255
• Main Authors: Varela, Celia, Karssemeijer, Nico, Hendriks, Jan H.C.L., Holland, Roland
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier Ireland Ltd 01.11.2005
• Subjects: Aged; Area Under Curve; Biopsy; Breast Cyst - diagnostic imaging; Breast neoplasm; Breast Neoplasms - classification; Breast Neoplasms - diagnostic imaging; Cancer screening; Carcinoma in Situ - diagnostic imaging; Carcinoma, Ductal, Breast - diagnostic imaging; Data Display; Diagnosis; Diagnostic radiology; Female; Fibroadenoma - diagnostic imaging; Fibrocystic Breast Disease - diagnostic imaging; Follow-Up Studies; Humans; Hyperplasia; Image Processing, Computer-Assisted - methods; Mammography - statistics & numerical data; Mass Screening; Middle Aged; Observer performance; Observer Variation; Population Surveillance; ROC Curve; Diagnosis; Diagnostic radiology; Observer performance; Breast neoplasm; Cancer screening
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2005.04.007

The purpose of this study was to determine the importance of using prior mammograms for classification of benign and malignant masses. Five radiologists and one resident classified mass lesions in 198 mammograms obtained from a population-based screening program. Cases were interpreted twice, once without and once with comparison of previous mammograms, in a sequential reading order using soft copy image display. The radiologists’ performances in classifying benign and malignant masses without and with previous mammograms were evaluated with receiver operating characteristic (ROC) analysis. The statistical significance of the difference in performances was calculated using analysis of variance. The use of prior mammograms improved the classification performance of all participants in the study. The mean area under the ROC curve of the readers increased from 0.763 to 0.796. This difference in performance was statistically significant ( P = 0.008).