Radiology in public focus

Access to Patient Questionnaire Improves Spine MRI Diagnosis

Knowing a patient’s symptoms helps radiologists in lumbar spine MRI interpretation and diagnosis, according to a study published in Radiology.

William E. Palmer, MD, division chief of Musculoskeletal Radiology at Massachusetts General Hospital, in Boston, and colleagues found the questionnaire helped to avoid diagnostic discrepancies between radiologists and spine specialists.

“By distinguishing actionable pain generators from incidental findings, radiologists can best help primary care physicians who depend on MRI reports to guide their treatments and referrals,” Dr. Palmer said.

Read the related RSNA News story, including a video from Dr. Palmer sharing details about his research.

Incorrect AI Advice Influences Diagnostic Decisions

When making diagnostic decisions, radiologists and other physicians may rely too much on AI when it points out a specific area of interest in an X-ray, according to a study published in Radiology.

Paul H. Yi, MD, director of intelligent imaging informatics and associate member in the Department of Radiology at St. Jude Children’s Research Hospital in Memphis, TN, and colleague conducted a multi-site, prospective study in which 220 radiologists and internal medicine/emergency medicine physicians read chest X-rays alongside AI advice.

When the AI advice was correct, the average diagnostic accuracy among reviewers was 92.8% with local explanations and 85.3% with global explanations. When AI advice was incorrect, physician accuracy was 23.6% with local and 26.1% with global explanations.

“When we rely too much on whatever the computer tells us, that’s a problem, because AI is not always right,” Dr. Yi said. “I think as radiologists using AI, we need to be aware of these pitfalls and stay mindful of our diagnostic patterns and training.”

Read the related RSNA News story.

Ten-Year STudy Shows Tomosynthesis Improves Breast Cancer Detection

According to a new 10-year study, screening for breast cancer with digital breast tomosynthesis (DBT) increases cancer detection rates and significantly reduces the rate of advanced cancers compared to conventional 2D digital mammography. The findings were published in Radiology.

In the retrospective study, first co-author Liane Elizabeth Philpotts, MD, professor of radiology and biomedical imaging at Yale School of Medicine in New Haven, CT, and a team of researchers analyzed consecutive cancer cases detected by screening mammography over 13 years at Yale University/Yale-New Haven Health.

They found that digital mammography and DBT screening mammography found the same types of cancers but at different stages, with DBT finding more aggressive cancers at an earlier stage.

“DBT’s lower recall rate, higher cancer detection rate and lower rate of advanced cancers is a win, win, win,” Dr. Philpotts said. “I think this data will contribute to the debate of overdiagnosis by demonstrating that DBT is not over-diagnosing cancers. It’s finding the bad actors earlier.”

Read the related RSNA News story.