Multiview-based computer-aided detection scheme for breast masses.
ABSTRACT In this study, we developed and tested a new multiview-based computer-aided detection (CAD) scheme that aims to maintain the same case-based sensitivity level as a single-image-based scheme while substantially increasing the number of masses being detected on both ipsilateral views. An image database of 450 four-view examinations (1800 images) was assembled. In this database, 250 cases depicted malignant masses, of which 236 masses were visible on both views and 14 masses were visible only on one view. First, we detected suspected mass regions depicted on each image in the database using a single-image-based CAD. For each identified region (with detection score > or = 0.55), we then identified a matching strip of interest on the ipsilateral view based on the projected distance to the nipple along the centerline. By lowering CAD operating threshold inside the matching strip, we searched for a region located inside the strip and paired it with the original region. A multifeature-based artificial neural network scored the likelihood of the paired "matched" regions representing true-positive masses. All single (unmatched) regions except for those either with very high detection scores (> or = 0.85) or those located near the chest wall that cannot be matched on the other view were discarded. The original single-image-based CAD scheme detected 186 masses (74.4% case-based sensitivity) and 593 false-positive regions. Of the 186 identified masses, 91 were detected on two views (48.9%) and 95 were detected only on one view (51.1%). Of the false-positive detections, 54 were paired on the ipsilateral view inside the corresponding matching strips and the remaining 485 were not, which represented 539 case-based false-positive detections (0.3 per image). Applying the multiview-based CAD scheme, the same case-based sensitivity was maintained while cueing 169 of 186 masses (90.9%) on both views and at the same time reducing the case-based false-positive detection rate by 23.7% (from 539 to 411). The study demonstrated that the new multiview-based CAD scheme could substantially increase the number of masses being cued on two ipsilateral views while reducing the case-based false-positive detection rate.
- [Show abstract] [Hide abstract]
ABSTRACT: To prospectively assess the effect of computer-aided detection (CAD) on the interpretation of screening mammograms in a community breast center. Over a 12-month period, 12,860 screening mammograms were interpreted with the assistance of a CAD system. Each mammogram was initially interpreted without the assistance of CAD, followed immediately by a reevaluation of areas marked by the CAD system. Data were recorded to measure the effect of CAD on the recall rate, positive predictive value for biopsy, cancer detection rate, and stage of malignancies at detection. When comparing the radiologist's performance without CAD with that when CAD was used, the authors observed the following: (a) an increase in recall rate from 6.5% to 7.7%, (b) no change in the positive predictive value for biopsy at 38%, (c) a 19.5% increase in the number of cancers detected, and (d) an increase in the proportion of early-stage (0 and I) malignancies detected from 73% to 78%. The use of CAD in the interpretation of screening mammograms can increase the detection of early-stage malignancies without undue effect on the recall rate or positive predictive value for biopsy.Radiology 10/2001; 220(3):781-6. · 6.21 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: To determine the false-negative rate in screening mammography, the capability of computer-aided detection (CAD) to identify these missed lesions, and whether or not CAD increases the radiologists' recall rate. All available screening mammograms that led to the detection of biopsy-proved cancer (n = 1,083) and the most recent corresponding prior mammograms (n = 427) were collected from 13 facilities. Panels of radiologists evaluated the retrospectively visible prior mammograms by means of blinded review. All mammograms were analyzed by a CAD system that marks features associated with cancer. The recall rates of 14 radiologists were prospectively measured before and after installation of the CAD system. At retrospective review, 67% (286 of 427) of screening mammography-detected breast cancers were visible on the prior mammograms. At independent, blinded review by panels of radiologists, 27% (115 of 427) were interpreted as warranting recall on the basis of a statistical evaluation index; and the CAD system correctly marked 77% (89 of 115) of these cases. The original attending radiologists' sensitivity was 79% (427 of [427 + 115]). There was no statistically significant increase in the radiologists' recall rate when comparing the values before (8.3%) with those after (7.6%) installation of the CAD system. The original attending radiologists had a false-negative rate of 21% (115 of [427 + 115]). CAD prompting could have potentially helped reduce this false-negative rate by 77% (89 of 115) without an increase in the recall rate.Radiology 06/2000; 215(2):554-62. · 6.21 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Our study evaluated radiologist detection of breast cancer using a computer-aided detection system. Three radiologists reviewed 377 screening mammograms interpreted as showing normal or benign findings 9-24 months before cancer diagnosis from 17 of the 18 participating centers. In 313 cases, study radiologists recommended additional mammographic evaluation. In 177 cases, the area warranting additional workup precisely correlated with the subsequently diagnosed cancer. These 177 missed cancers were evaluated with computer-aided detection. The proportion of radiologists identifying the missed cancers was used to determine radiologist sensitivity without computer-aided detection. The study radiologists determined that 123 of the 377 missed cancer cases warranted workup. Therefore, 123 additional cancers cases could have been found. The calculated radiologist sensitivity without computer-aided detection was therefore 75.4% (377 / [377 + 123]). Similarly, using the performance of the system on the missed cancers, we estimated that 80 (65.0%) of these 123 missed cancer cases would have been identified with the use of computer-aided detection. Consequently, the estimated sensitivity of radiologists using computer-aided detection was 91.4% ([377 + 80] / [377 + 123])-resulting in a 21.2% ([91.4% / 75.4%] - 1) increase in radiologist sensitivity with computer-aided detection. Use of the computer-aided detection system significantly improved the detection of breast cancer by increasing radiologist sensitivity by 21.2%. Therefore, for every 100,000 women with breast cancer identified without the use of computer-aided detection, an estimated additional 21,200 cancers would be found with the use of computer-aided detection.American Journal of Roentgenology 10/2003; 181(3):687-93. · 2.74 Impact Factor