Training trumps experience when it comes to interpreting CT colonography, said Dr. Abe Dachman, director of the Fellowship Programs at the University of Chicago Medical Center.
Training trumps experience when it comes to interpreting CT colonography, said Dr. Abe Dachman, director of the Fellowship Programs at the University of Chicago Medical Center.
In a Wednesday presentation at the International Symposium on Multidetector Row CT, Dachman drew evidence from his own and others’ research to show that proper training is critical to achieving high sensitivity and specificity in the detection of polyps on CTC exams. One of the challenges is in the characterization of lesions.
“It’s not just finding the polyp,” he said. “About half the errors are errors of detection. The rest are errors of characterization. The good news is that this means, with more training, you will be able to do a good job.”
The two critical components of such training, he said, are lectures and hands-on training. The lectures should explain how to integrate CTC into clinical practice and teach the results of clinical trials examining the value of this procedure. Patient preparation strategies, exam performance and aspects of making interpretations such as the principles and pitfalls of software must be included, as well as an understanding of extracolonic findings and ongoing developments in the field.
The hands-on work should include training in the software and a full reading of about 60 cases with feedback on cases in which errors were made. Dachman called this an “unblinding to the truth.”
“They have to be able to learn from their mistakes,” he said.
Some pick up the nuances of interpretation quickly. Some take more time. And some, Dachman said, never get it. Success often comes down to context – whether the prospective practitioner has good reading skills and can conceptualize in three dimensions.
And just getting the interpretations right is not enough. Interpretations must be done quickly. Here formal training again plays a role. Dachman cited research indicating that interpreters who consistently demonstrate high sensitivity and specificity, but take longer than average to complete their readings, can get faster after receiving additional training.
But even fast, accurate reading of CTCs does not ensure success in this field. Users of CTC must win the acceptance of the technique by those around them.
“You’ll need to do some PR,” he said. “You’ll have to handle questions from referring physicians, patients and staff about where it fits in clinical practice.”
Photon-Counting Computed Tomography: Eleven Takeaways from a New Literature Review
May 27th 2025In a review of 155 studies, researchers examined the capabilities of photon-counting computed tomography (PCCT) for enhanced accuracy, tissue characterization, artifact reduction and reduced radiation dosing across thoracic, abdominal, and cardiothoracic imaging applications.
Can AI Predict Future Lung Cancer Risk from a Single CT Scan?
May 19th 2025In never-smokers, deep learning assessment of single baseline low-dose computed tomography (CT) scans demonstrated a 79 percent AUC for predicting lung cancer up to six years later, according to new research presented today at the American Thoracic Society (ATS) 2025 International Conference.
Can Emerging AI Software Offer Detection of CAD on CCTA on Par with Radiologists?
May 14th 2025In a study involving over 1,000 patients who had coronary computed tomography angiography (CCTA) exams, AI software demonstrated a 90 percent AUC for assessments of cases > CAD-RADS 3 and 4A and had a 98 percent NPV for obstructive coronary artery disease.