March 2015


Friday, March 6 (ECR) – Computer-aided diagnosis (CAD) can only enhance performance if used correctly, and does not reduce the need for training, experts agree. Furthermore, CAD is moving away from pure detection to clinical decision support, but the adoption of new reading paradigms for the screening scenario and improvements in how the technology presents results are both vital if it is to become an essential imaging tool, experts will explain during a Refresher Course today.

CAD for colonography shows particular potential. Most radiologists will come across it in their workflow, so they need to understand sensitivity and specificity issues, as well as when CAD should be used in this area. The major benefits of the technique are in 6–9mm polyps, which are often difficult for the radiologist to spot, according to Dr. Stuart Taylor, professor of medical imaging and consultant gastrointestinal radiologist at University College London, who will speak during the course.

“CAD acts like a spell check for small polyps. There are also instances when tumours and large polyps are missed by the radiologist before CAD draws attention to them,” he said.

However, CAD is not 100% accurate and doesn’t reduce the need for training in CT colonography interpretation, according to Taylor. False negatives can present a challenge too. Typically the computer programme looks for the rounded bowler-hat contours of a polyp, but it may miss the flatter polyps and large mass-like lesions that don’t have characteristic rounded contours.

Most manufacturers are further developing CAD using validated CT colonography cases, improving the technology’s diagnostic capacity. CAD advances may also benefit patients regarding full bowel preparation prior to the procedure, meaning that patients will no longer have to take unpleasant bowel preparations before CT colonography, Taylor said.

An Italian multicentre screening study has pointed to greater time efficiency of using double-reading first-reader CAD (DR FR CAD). CAD initially reads the image, and this first interpretation is around 90% sensitive. Then the radiologist looks at the image with a primary 2D read. First results show that this double-reading paradigm leads to fast and accurate reporting.

“If CT colonography is implemented as a population screening test, there will be very large numbers of datasets to read by a relatively small number of trained radiologists. Implementing CAD in a DR FR CAD paradigm may allow the reading of large case numbers in a limited time,” he said.

Mass screening programmes of the 1980s are now moving towards an individualised screening approach. First, CAD tools need to factor in potential risks and point the radiologist to the best imaging studies, according to Prof. Dr. Ulrich Bick, professor of radiology and vice chair of the radiology department at the Charité University Hospital in Berlin. “Traditional CAD doesn’t take into account risk factors such as age or genetics. This, combined with its 98% sensitivity for finding microcalcifications, means that the radiologist must decide whether or not the often numerous findings are clinically relevant,” said Bick, who will provide an update on breast CAD during the course.

An Italian multicentre screening study has pointed to greater time efficiency of using double-reading first-reader CAD (DR FR CAD). CAD initially reads the image, and this first interpretation is around 90% sensitive. Then the radiologist looks at the image with a primary 2D read. First results show that this double-reading paradigm leads to fast and accurate reporting.

“If CT colonography is implemented as a population screening test, there will be very large numbers of datasets to read by a relatively small number of trained radiologists. Implementing CAD in a DR FR CAD paradigm may allow the reading of large case numbers in a limited time,” he said.

Mass screening programmes of the 1980s are now moving towards an individualised screening approach. First, CAD tools need to factor in potential risks and point the radiologist to the best imaging studies, according to Prof. Dr. Ulrich Bick, professor of radiology and vice chair of the radiology department at the Charité University Hospital in Berlin. “Traditional CAD doesn’t take into account risk factors such as age or genetics. This, combined with its 98% sensitivity for finding microcalcifications, means that the radiologist must decide whether or not the often numerous findings are clinically relevant,” said Bick, who will provide an update on breast CAD during the course.


myESR