Computerized classification of benign and malignant masses on digitized mammograms: A study of robustness

Academic Radiology

Volumn 7, Issue 12, 2000, Pages 1077-1084

  Huo, Zhimin ^a   Giger, Maryellen L ^a   Vyborny, Carl J ^a   Wolverton, Dulcy E ^a   Metz, Charles E ^a  

^a UNIVERSITY OF CHICAGO   (United States)

Author keywords

Breast cancer; Case subtlety; Computer aided diagnosis; Digitization; Mammography; Robustness

Indexed keywords

ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOMATION; BREAST CANCER; COMPUTER ASSISTED DIAGNOSIS; DISEASE CLASSIFICATION; MAMMOGRAPHY; PRIORITY JOURNAL; RECEIVER OPERATING CHARACTERISTIC;

EID: 0033663963     PISSN: 10766332     EISSN: None     Source Type: Journal    
DOI: 10.1016/S1076-6332(00)80060-4     Document Type: Article

References (16)

1. Computerized detection of clustered microcalcifications: Evaluation of performance on mammograms from multiple centers
2. Reproducibility of an automated scheme for the detection of clustered microcalcifications on digital mammograms
3. Automated computerized classification of malignant and benign masses on digitized mammograms
4. Pulmonary nodules: Computer-aided detection in digital chest images
5. Analysis of spiculation in the computerized classification of mammographic masses
6. Effect of dominant features on neural network performance in the classification of mammographic lesions
7. A receiver operating characteristics partial area index for highly sensitive diagnostic tests
8. Maximum-likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data
9. A new approach for testing the significance of differences between ROC curves measured from correlated data
10. Digitization requirements in mammography: Effect on computer-aided detection of microcalcifications
11. Effect of case selection on the performance of computer-aided detection schemes
12. Current issues in CAD for mammography
13. Computer-aided detection of clustered microcalcifications on digitized mammograms