article thumbnail

ChatGPT outperforms clinicians in post-negative test disease probability

AuntMinnie

ChatGPT-4 outperformed human clinicians in determining pretest and post-test disease probability after a negative test result involving chest radiographs and mammograms, according to a research letter published December 11 in JAMA Network Open.

Disease 317
article thumbnail

What's best practice for using AI for thoracic imaging?

AuntMinnie

AI for thoracic imaging includes using it for reading chest radiographs and low-dose chest CT scans for lung cancer screening and for triaging pulmonary embolism on chest CT scans, the group noted.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Moore’s Law for radiologists

AuntMinnie

Some of my radiological heroes would report a staggering 30,000 to 40,000 radiographs a year. Some even [startled gasp] gave up reporting plain radiographs. We understand so much more about the human body, disease, and how to detect it accurately via cross-sectional means. I still don’t know how they did it.

article thumbnail

Understanding CT flow artifacts is key to better disease diagnosis

AuntMinnie

Understanding the mechanics of flow artifacts on CT or CT angiography (CTA) and how these artifacts are created is key to better disease diagnosis, according to a review published April 25 in RadioGraphics. In the review, a team led by Caroline Robb, MD, of Mallinckrodt Institute of Radiology, Washington University in St.

Disease 299
article thumbnail

PSMA-PET provides long-term benefits

AuntMinnie

Although studies have shown that PSMA-PET is highly effective for detecting prostate cancer, the long-term consequences of widely implementing the technique in patients with recurrent disease are unknown, the authors explained. population and was informed by data from real-world settings.

article thumbnail

Can AI help rule out ‘unremarkable’ chest x-rays?

AuntMinnie

These included chest radiographs that displayed abnormalities of no clinical significance, which are typically treated as normal. of unremarkable chest radiographs, while only missing 0.1%, 1%, and 2% of remarkable chest radiographs. Reports by radiologists for the images were classified similarly.

X-ray 279
article thumbnail

Road to RSNA 2023: AI Preview

AuntMinnie

AI methods improve detection of Parkinson’s disease Sunday, November 26 | 1:50 p.m.-2:00 S4-SSNR02-6 | Room E352 A systematic review has found that machine-learning and deep-learning techniques are highly sensitive and specific for detecting Parkinson’s disease on dopamine transporter (DaT) SPECT exams. 2:00 p.m. | 1:50 p.m. |