As the long winter continues to linger, it was good to get away to sunny Florida for the Healthcare Information and Management Systems Society (HIMSS) annual conference. If you were in attendance, I hope you were able to take home some valuable lessons about health IT. If you couldn’t go, check out our coverage in Health Imaging and Clinical Innovation + Technology.
Now that I’m back and looking over some of the top stories of the past month aside from the headlines at HIMSS, a pair of studies related to computer-aided detection (CAD) systems stood out.
The first involved the use of CAD to improve characterization of prostate lesions at multiparametric MRI. Emilie Niaf, PhD, of the Université de Lyon in France, and colleagues designed a CAD system to assess the likelihood of visible lesion malignancy using a protocol that combines T2-weighted, diffusion-weighted and dynamic contrast-enhanced imaging.
The results, published online in Radiology, demonstrated only a moderate improvement in reader performance with CAD assistance. Niaf and colleagues remained positive about CAD’s prospects in daily routine use, writing that the “results suggest that the main benefit of our CAD system was in improving the correct classification of benign lesions. This is an interesting perspective because up to 75 percent of focal lesions seen at multiparametric MR imaging are benign and the false-positive rate at multiparametric MR imaging can be as high as 40 percent, even for experienced readers. Recognizing a portion of these false-positives as formally benign could avoid unnecessary biopsy when multiparametric MR imaging is used as a triage test or improve patient selection for focal therapy.”
The second study, also published in Radiology, involved the use of CT colonography to depict carpet lesions, a subset of nonpolypoid colorectal lesions. In the process of the study, researchers from the University of Wisconsin, Madison, sought to describe the clinical, imaging and pathologic features of carpet lesions at CT colonography.
One of the common features of these lesions is that they draw multiple CAD hits. Of the 18 carpet lesions detected in the study population of more than 9,000 patients, CAD was able to detect 17 (94.4 percent).
As we continue to learn about the strengths and weaknesses of CAD systems and how best to utilize them in practice, studies like these will provide valuable insights.
Editor – Health Imaging