How do you think the new GigE standards will influence the machine vision industry?
Respond or ask your question now!
The author of the study (Comparison of Computer-Aided Detection to Double Reading of Screening Mammograms: Review of 231,221 Mammograms) is Dr. Matthew Gromet of the Breast Imaging Section of Charlotte Radiology, a Charlotte, N.C., imaging practice that does about 66,000 screening mammograms each year.
Dr. Gromet found that a single reader with CAD had a statistically significant increase in sensitivity (11 percent) and a smaller increase in recall rate (4 percent), when compared to a single reader without CAD assistance. He also found that single reading with CAD review, when compared with independent double reading, resulted in a not statistically significant increase in sensitivity but with a statistically significant lower recall rate. With manpower constraints limiting the use of double reading, Dr. Gromet concludes that "CAD appears to be an effective alternative that provides similar, and potentially greater, benefits."
The results were based on the performance of nine radiologists at Charlotte Radiology with a mean level of experience in mammography of 15 years. The mammograms in the study were screen-film studies obtained on the Hologic (Bedford, Mass.) R2 ImageChecker® CAD system. A total of 231,221 exams were included in the study; 49 percent of the exams were double-read without CAD and 51 percent were single-read with CAD. All mammograms in the study were obtained on Lorad M-IV equipment with Kodak Min-R and Kodak Min-R EV film.
The latest Hologic algorithm contains a range of software options, including breast geometry and lesion metrics. Breast geometry detects a breast outline for advanced sizing logic; lesion metrics creates advanced measures such as size, number of calcifications and distance to nipple. The system provides nine operating combinations, allowing the software to be adapted to the radiologists' reading preferences. Three separate operating points (sensitivity/false marker rate settings) can be selected for microcalcifications and masses.
For example, a site can choose to set the highest sensitivity for microcalcifications while selecting a balanced operating point for masses. This results in a lower overall false marker rate.