medpundit |
||
|
Tuesday, November 18, 2003The computer-aided mammography device uses algorithms to highlight suspicious areas on digitized images that radiologists then examine more closely for possible disease. Clinical trials determined that 39% of missed breast cancers might have been detected almost 15 months earlier using its technology, Kodak says. For an example of how the computer interpretation differs from a radiologist's interpretaion, click here. The computer doesn't replace the radiologist, it just double-checks his work. Is it worth it? It certainly detects more cancers doing it that way: CAD marked 31 of 32 cancers (case-based sensitivity=96.8%). On a film and lesion basis, CAD identified 31 of 32 (96.8%) malignant calcifications and 29 of 42 (69.0%) malignant opacities, the only cancer not identified by CAD being depicted as an isolated opacity. But, it also has a much higher rate of false positives: CAD marked 348 areas (153 microcalcifications and 195 opacities) in 88 of 108 non cancer cases, with a case-based specificity of 18.5% (20/108). Considering all six readings, cancer was identified in 164 or 174 of 192 readings (85.4 vs 90.6%, c2 2.03, df=1, p=0.15) and recalls of non-cancer cases were 108 or 159 of 648 readings (16.6 vs 24.5%, c2 11.7, df=1, p<0.001) at conventional or CAD reading, respectively. Since breast cancer is one of those cancers that often turns deadly no matter how early it's caught (depending on the type), it might not be worth that extra hassle and extra money. It's a matter of personal choice. posted by Sydney on 11/18/2003 03:40:00 PM 0 comments 0 Comments: |
|