Radiology in public focus

Radiologists Outperformed AI in Identifying Lung Diseases on Chest X-Ray

In a study of more than 2,000 chest X-rays, radiologists outperformed AI in accurately identifying the presence and absence of three common lung disease, according to a study published in Radiology.

Researchers compared the performance of four commercially available AI tools with a pool of 72 thoracic radiologists in interpreting 2,040 consecutive adult chest X-rays taken over a two-year period at four Danish Hospitals in 2020.

“The AI tools showed moderate to a high sensitivity comparable to radiologists for detecting airspace disease, pneumothorax and pleural effusion on chest X-rays,” said lead researcher Louis L. Plesner, MD, Department of Radiology at Herlev and Gentofte Hospital in Copenhagen, Denmark. “However, they produced more false-positive results (predicting disease when none was present) than the radiologists, and their performance decreased when multiple findings were present and for smaller targets.”

Read the related RSNA News story, “Radiologists Outperformed AI in Identifying Lung Diseases on Chest X-Ray.”

Vision-based ChatGPT Shows Deficits Interpreting Radiologic Images

Researchers evaluating the performance of ChatGPT-4 Vision found that the model performed well on text-based radiology exam questions but struggled to answer image-related questions accurately. The study’s results were published in Radiology.

Chad Klochko, MD, Henry Ford Health in Detroit, and colleagues used retired questions from the American College of Radiology’s Diagnostic Radiology In-Training Examinations, a series of tests used to benchmark the progress of radiology residents. After excluding duplicates, the researchers used 377 questions across 13 domains, including 195 questions that were text-only and 182 that contained an image.

GPT-4 Vision achieved an overall score of 65.3%. The model correctly answered 81.5% (159) of the 195 text-only queries and 47.8% (87) of the 182 questions with images.

“Our study showed evidence of hallucinatory responses when interpreting image findings,” Dr. Klochko said. “We noted an alarming tendency for the model to provide correct diagnoses based on incorrect image interpretations, which could have significant clinical implications.”

Read the related RSNA News story, “Vision-based ChatGPT Shows Deficits Interpreting Radiologic Images.”

Expert Panel Endorses New US Terminology for Early Pregnancy

For the first time, a multi-medical society panel has developed and endorsed a uniform lexicon for describing the observations seen on US during the first trimester of pregnancy.

The lexicon, based on scientific evidence, societal guidelines and expert consensus, was published today in Radiology and simultaneously in the American Journal of Obstetrics & Gynecology.

“We recognize that specific language in the medical record could be used by third parties to negatively affect the physician-patient relationship,” said senior author Lori M. Strachowski, MD, University of California, San Francisco. “Our goal was to recommend clear, specific, scientifically based and medically appropriate terminology that communicates clearly across disciplines, minimizes bias and harm, and respects patient preferences.”

Read the related RSNA News story, “Expert Panel Endorses New US Terminology for Early Pregnancy.”