Radiologists at Memorial Sloan-Kettering Cancer Center are hoping that computer-aided diagnosis (CAD) will increase the number of cancers detected at an early stage. Radiologists are using CAD to second-read mammograms at the center's Breast
Radiologists at Memorial Sloan-Kettering Cancer Center are hoping that computer-aided diagnosis (CAD) will increase the number of cancers detected at an early stage.
Radiologists are using CAD to second-read mammograms at the center's Breast Examination Center of Harlem (BECH), an outreach program that provides free cancer screening and educational programs on cancer prevention and detection.
CAD technology, which uses a computer to scan mammograms for abnormalities, may improve early detection of breast cancer by almost 20%, according to one study(Freer TW, Ulissey MJ. Screening mammography with computer-aided detection: prospective study of 12,860 patients in a community breast center. Radiology 2001;220(3):781-786).
Memorial Sloan-Kettering acquired the same R2 Technology ImageChecker CAD system used in the Freer study and began using it in August for mammograms performed at BECH.
"We are encouraged by the growing body of research showing the potential value of CAD as a companion technology to mammography and we look forward to gaining experience with the system," said Dr. Michael A. Cohen, director of the Memorial Sloan-Kettering Guttman Diagnostic Center, where the mammograms are interpreted.
The technology may improve the proportion of cancers detected at an early stage and that in turn may encourage more women in the local community to obtain regular mammograms, Cohen said.
Every mammogram at BECH is first read in the conventional way by a staff radiologist, after which CAD analysis is conducted and reviewed. While the radiologist remains the decision-maker, the CAD system is believed to improve the radiologist's ability to detect breast cancer by pointing out an area or areas that may have been overlooked initially.
Each mammogram in the Freer study was first interpreted without the assistance of CAD. After CAD was used, the areas it indicated were immediately reevaluated. Data were recorded to measure the effect of CAD on the recall rate, positive predictive value for biopsy, cancer detection rate, and stage of malignancy at detection.
In a comparison of radiologists' performance with and without CAD, the authors observed the following:
?an increase in the recall rate from 6.5% to 7.7%;
?no change in the 38% positive predictive value for biopsy;
?a 19.5% increase in the number of cancers detected; and
?an increase from 73% to 78% in the proportion of early-stage (0 and I) malignancies detected.
The authors concluded that the use of CAD in interpreting screening mammograms can increase detection of early-stage malignancies without undue effect on the recall rate or positive predictive value for biopsy.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.