Evaluation of computer-assisted diagnosis system for carcinoma of the breast.

Citation
M. Funovics et al., Evaluation of computer-assisted diagnosis system for carcinoma of the breast., ROFO-F RONT, 173(3), 2001, pp. 218-223
Citations number
26
Language
TEDESCO
art.tipo
Article
Categorie Soggetti
Radiology ,Nuclear Medicine & Imaging
Journal title
ROFO-FORTSCHRITTE AUF DEM GEBIET DER RONTGENSTRAHLEN UND DER BILDGEBENDEN VERFAHREN
ISSN journal
1438-9029 → ACNP
Volume
173
Issue
3
Year of publication
2001
Pages
218 - 223
Database
ISI
SICI code
1438-9029(200103)173:3<218:EOCDSF>2.0.ZU;2-3
Abstract
Purpose: Evaluation of a computer-assisted diagnosis (CAD) system (R2 linag e Checker 1.2). Comparison of the results of three readers with and without knowledge of the computer results. Materials and methods: The mammograms o f 52 patients, bilaterally in two planes each, with histologically proven c arcinoma of the breast were included in the study. They were first scanned by the CAD machine and subsequently read by three readers with different de grees of experience in two sessions with and without knowledge of the compu ter results. Results: Of the 91 views of carcinomas, the readers detected 9 6 %, 89 %, and 85 %, respectively. With CAD, the values rose to 97 %, 93 %, and 96 %. The increase of the first observer was not significant. As for t he 49 areas of malignant microcalcifications, the first reader showed a sig nificant decrease of sensitivity, the other two readers showed no significa nt change. The sensitivity of CAD was 74 % for masses and 86 % for microcal cifications at a rate of 1.8 false positive markers per image. All but two tumors were correctly marked in at least one plane. Conclusions: Use of the CAD machine led to a significant increase of sensitivity in the detection of malignant masses by two of three observers. In the case of malignant mic rocalcifications, and for the most experienced observer, CAD did not improv e the results. The most important problem is the high rate of false positiv e markers.