Radiologists puzzle over chest CAD choices

Article

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.

Recent Videos
Study: MRI-Based AI Enhances Detection of Seminal Vesicle Invasion in Prostate Cancer
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Related Content
© 2025 MJH Life Sciences

All rights reserved.