Breast screening: visual search as an aid for digital mammographic interpretation training

Using eye gaze in intelligent interactive imaging training

“…just behind the nipple) and (2) areas which, per image, suggest potential abnormal appearance based wholly on the individual appearance of that image. This is supported by a recent study [7] of 15 experienced screeners examining 40 cases which demonstrated that whilst each individual exhibited different scanning patterns yet they examined broadly similar image areas in detail. …”

Performance differences across the Atlantic when UK and USA radiologists read the same set of test screening cases

“…To counter this to some extent, the cases which were used were carefully selected so as not to have significant micro-calcifications. We have previously shown that acceptable performance can be obtained when the same group of screeners examined a case set using either their clinical mammographic workstations or a single office monitor as long as suitable interaction software is utilised 9 . The reporting software was new to the American group, however it is a transparent reporting system which has been well researched to be very user friendly.…”

“…Additionally, high resolution mammography workstations are a clinical requirement for soft copy reporting of FFDM images. Notwithstanding this, our previous work 9 has demonstrated that good performance in identifying abnormalities on screening mammograms can be achieved using a single office monitor with suitable image manipulation software as compared to a clinical mammography workstation when the same UK screeners read the same cases on different occasions. In the present study the effects of differences in experience, case volume per annum and monitor resolution were investigated.…”

Is image manipulation necessary to interpret digital mammographic images efficiently?

“…The participants' behaviour whilst examining each image was recorded for subsequent detailed analyses. The procedure has been reported elsewhere in details [3].…”

“…As reported previously [3] a long and detailed study was performed examining screening performance on a workstation, standard computer monitor and an iPhone where participants either were able to manipulate the displayed images using typical DICOM viewing software or else were not permitted to manipulate the images in such a manner. Here, more detailed data regarding the comparison of performance and the related underlying factors on the workstation and monitor are presented.…”