Thoracic imaging is attracting considerable interest and investment as a prime application for computer-aided detection. But implementing lung CAD into the clinical radiology workflow requires careful thought to realize the software’s true potential, according to speakers at a Computer Assisted Radiology and Surgery 2005 session.
Thoracic imaging is attracting considerable interest and investment as a prime application for computer-aided detection. But implementing lung CAD into the clinical radiology workflow requires careful thought to realize the software's true potential, according to speakers at a Computer Assisted Radiology and Surgery 2005 session.
Many radiologists distrust the ability of chest CAD to either improve their performance or speed reporting throughput, said Dr. Dag Wormanns, a radiologist at the University of Münster in Germany. Common complaints include the tendency of the software to highlight clinically irrelevant findings and the extra time required to load CAD applications or move to another workstation to run the package.
"If you talk with general radiologists, they are quite skeptical. They do not use chest CAD for the most part," Wormanns said.
He would like to see CAD applied to every chest CT scan as standard. This strategy would be more acceptable if CAD software was readily available on radiologists' desktops together with the CT data, he said.
More information is needed as well on the best way to use the software, he said. Use of chest CAD as a prereading filter saves time but leaves radiologists reliant on the software's sensitivity. Looking at CAD marks after having viewed a series of images should improve radiologists' sensitivity, but it would inevitably increase reporting time. Alternatively, the radiologist could use CAD while actively reporting, though the clinical and workflow impacts of this strategy require further clarification.
"CAD can either save time as a filter or increase sensitivity as a second reader. I am not too optimistic that there is a trade-off," Wormanns said. "The role of concurrent reading is still to be defined."
Addressing skeptics' concerns over chest CAD is only the first step. Departments may face a more complex choice than they expect when purchasing a system, said Dr. Matthew Freedman, a radiologist with the Lombardi Cancer Center and ISIS Imaging Science Center at Georgetown University in Washington, DC.
Freedman presented data showing the wide variation in sensitivity and specificity when two chest CAD systems were applied to a selection of differently biased data sets. He highlighted variance between 15 radiologists viewing the same data set with chest CAD and the range in sensitivity when one radiologist used CAD to view four different data sets.
"If you are trying to compare two CAD systems, you really have a difficult problem, because the best system for one radiologist is not necessarily the best for another, and the best CAD system for one practice or caseload may not be the best for another," he said.
MRI Study at ARRS Raises Questions About Disparities in Detection of MASLD
May 3rd 2025New research revealed that Hispanic Americans with evidence of hepatic steatosis on MRI but no formal diagnosis of MASLD had over a fourfold higher risk of developing hepatocellular carcinoma in comparison to those who had a formal diagnosis of MASLD.
The Reading Room Podcast: Current Perspectives on the Updated Appropriate Use Criteria for Brain PET
March 18th 2025In a new podcast, Satoshi Minoshima, M.D., Ph.D., and James Williams, Ph.D., share their insights on the recently updated appropriate use criteria for amyloid PET and tau PET in patients with mild cognitive impairment.
Contrast-Enhanced Mammography Study Reveals 24 Percent Lower Sensitivity with Moderate/Marked BPE
April 30th 2025In comparison to minimal or mild background parenchymal enhancement on contrast-enhanced mammography (CEM), researchers found that moderate or marked BPE was associated with a 12 percent lower AUC for breast cancer detection.