Soft-copy mammographic readings with different computer-assisted detection cuing environments: preliminary findings.

PURPOSE: To assess the performance of radiologists in the detection of masses and microcalcification clusters on digitized mammograms by using different computer-assisted detection (CAD) cuing environments. MATERIALS AND METHODS: Two hundred nine digitized mammograms depicting 57 verified masses and 38 microcalcification clusters in 85 positive and 35 negative cases were interpreted independently by seven radiologists using five display modes. Except for the first mode, for which no CAD results were provided, suspicious regions identified with a CAD scheme were cued in all the other modes by using a combination of two cuing sensitivities (90% and 50%) and two false-positive rates (0.5 and 2.0 per image). A receiver operating characteristic study was performed by using soft-copy images. RESULTS: CAD cuing at 90% sensitivity and a rate of 0.5 false-positive region per image improved observer performance levels significantly (P < .01). As accuracy of CAD cuing decreased so did observer performances (P < .01). Cuing specificity affected mass detection more significantly, while cuing sensitivity affected detection of microcalcification clusters more significantly (P < .01). Reduction of cuing sensitivity and specificity significantly increased false-negative rates in noncued areas (P < .05). Trends were consistent for all observers. CONCLUSION: CAD systems have the potential to significantly improve diagnostic performance in mammography. However, poorly performing schemes could adversely affect observer performance in both cued and noncued areas.

Knowledge-based computer-aided detection of masses on digitized mammograms: a preliminary assessment.

The purpose of this work was to develop and evaluate a computer-aided detection (CAD) scheme for the improvement of mass identification on digitized mammograms using a knowledge-based approach. Three hundred pathologically verified masses and 300 negative, but suspicious, regions, as initially identified by a rule-based CAD scheme, were randomly selected from a large clinical database for development purposes. In addition, 500 different positive and 500 negative regions were used to test the scheme. This suspicious region pruning scheme includes a learning process to establish a knowledge base that is then used to determine whether a previously identified suspicious region is likely to depict a true mass. This is accomplished by quantitatively characterizing the set of known masses, measuring "similarity" between a suspicious region and a "known" mass, then deriving a composite "likelihood" measure based on all "known" masses to determine the state of the suspicious region. To assess the performance of this method, receiver-operating characteristic (ROC) analyses were employed. Using a leave-one-out validation method with the development set of 600 regions, the knowledge-based CAD scheme achieved an area under the ROC curve of 0.83. Fifty-one percent of the previously identified false-positive regions were eliminated, while maintaining 90% sensitivity. During testing of the 1,000 independent regions, an area under the ROC curve as high as 0.80 was achieved. Knowledge-based approaches can yield a significant reduction in false-positive detections while maintaining reasonable sensitivity. This approach has the potential of improving the performance of other rule-based CAD schemes.

Preliminary clinical evaluation of a high-resolution telemammography system.

RATIONALE AND OBJECTIVES: The authors designed, assembled, tested, and clinically evaluated a high-quality, fast, and relatively inexpensive telemammography system. METHODS: The authors designed a telemammography system that uses a high-resolution film digitizer and high data compression (> or = 40:1) to send images over regular telephone lines to a high-resolution laser printer that produces images with the look and feel of the original image and can operate in a hub and spokes mode. The authors then evaluated the system's performance. In a preliminary clinical study, interpretations of the laser-printed system's output of 119 cases were compared with the original interpretations, followed by a review of any clinically significant differences. RESULTS: With the exception of the laser printer, which is a modified off-the-shelf product, all hardware components of the system are commercially available products. The system digitizes (50 microns pixel size), compresses, transmits, receives, decompresses, and prints a 30 MB mammography file in less than 4 minutes. In the clinical study, there were 13 differences (in 13 cases) in the level of concern or recommendations. Seven were found to be clinically insignificant by a third-party review. The remaining six were reviewed by the original interpreter, and three were determined to be significant enough for further action. All were found to result from intra-reader variability rather than differences in visualization of possible abnormalities. CONCLUSIONS: Almost real-time, high-quality telemammography without geographic boundaries is possible with the use of high-level data compression. Telemammography with laser-printed film as the display may make it possible to offer mammographic services in remote locations while using commercially available technology.