Louis Plesner talks AI x-ray exam reads vs. radiologists'

Will Morton
Sep 28, 2023

In an interview with AuntMinnie.com, Louis Plesner, MD, of Herlev and Gentofte Hospital in Copenhagen, Denmark, discussed a study he led that was published September 26 in Radiology that found radiologists outperformed four commercially available algorithms for identifying diseases on chest x-rays.


Latest in Digital X-Ray
Earth Thumbnail
Climate change boosts emergency department use of x-ray, CT
November 19, 2024
Ai Explainability2 673bc0b7a0c1f Thumbnail
Radiologists prefer local AI advice over global
November 19, 2024
Baby Infant Mom Closeup Social
Bone health normal in infants exposed to HIV medication
November 15, 2024
Dexa Hip
DEXA screening recommended in lung transplant patients
November 8, 2024
Related Stories
Plesner
Artificial Intelligence
Can AI help rule out ‘unremarkable’ chest x-rays?
Example of triage of no change in a pair of chest radiographs in the emergency department. (A) Baseline posteroanterior chest radiograph in a 63-year-old female patient shows a small amount of left (L) pleural effusion and partial atelectasis of the right middle lobe. (B) Follow-up posteroanterior chest radiograph obtained in the same patient 1 day later shows no significant change. (C) Gradient-weighted class activation map shows the algorithm determined no change in the image pair, without relevant highlighting, as the highlighted area is located over the gastroesophageal junction. Image courtesy of Radiology.
Digital X-Ray
AI model shows promise for interpreting follow-up chest x-rays
187x200 Am Logo
Companies
AuntMinnie.com
The AI model is an encoder-decoder model trained to generate a text report given a chest x-ray and most recent comparison (anterior-posterior or posterior-anterior view only). The vision encoder weights were initialized from Vision Transformer (ViT) base and the text decoder weights were initialized from Robustly Optimized BERT Pretraining Approach (RoBERTa) base before training for 30 epochs on a data set of 900,000 chest x-rays (CXRs). cp indicates chest pain; sob = shortness of breath. Image courtesy of JAMA Open Network.
Artificial Intelligence
AI model generates x-ray reports similar to radiologists
More in Digital X-Ray
Climate change boosts emergency department use of x-ray, CT
By Kate Madden Yee
Climate change's effects -- particularly higher outdoor heat and air pollution -- increase imaging use in the emergency department, especially x-ray and CT.
November 19, 2024
Earth Thumbnail
Radiologists prefer local AI advice over global
By Will Morton
Radiologists and other physicians tend to trust AI more when the algorithms provide local rather than global explanations of findings on chest x-rays.
November 19, 2024
Ai Explainability2 673bc0b7a0c1f Thumbnail
Bone health normal in infants exposed to HIV medication
By Will Morton
Bone health appears normal in infants born to women treated with tenofovir disoproxil fumarate to prevent HIV infection.
November 15, 2024
Baby Infant Mom Closeup Social
DEXA screening recommended in lung transplant patients
By Will Morton
Patients undergoing lung transplant should be screened annually with dual energy x-ray absorptiometry (DEXA).
November 8, 2024
Dexa Hip
Podcast: What's next for chest radiographs?
By Liz Carey
In this episode of Keeping up with the Radiologists, co-hosts Saurabh (Harry) Jha, MD, and Mitchell Schnall, MD, assess the future of the chest radiograph.
November 7, 2024
November 2024 Kuwtr Ep9
Dark-field x-ray detects bone changes related to osteoporosis
By Will Morton
Dark-field x-ray imaging can provide insights into bone microstructure and potentially could have a role in assessing osteoporosis.
November 5, 2024
Lateral conventional attenuation (a, b, e, f) and co-registered dark-field (c, d, g, h) images of two spine specimens. Vertical (a, c, e, g) and horizontal (b, d, f, h) scans of the spine specimen of a 77-year-old female with osteoporosis (bone mineral density = 65.75 mg/dL) (a–d) and a non-osteoporotic spine specimen (e–h) of a 61-year-old female (bone mineral density = 169.38 mg/dL).
Chest x-ray AI shines in ‘real-world’ setting
By Will Morton
A PACS-integrated AI tool correctly identified pneumothorax on inpatient chest x-rays, prioritized scans, and improved radiologist reporting times.
November 4, 2024
Critical Care Suite
How do open-source LLMs compare with GPT-4 on x-ray reports?
By Will Morton
Freely available large language models (LLMs) may overcome limitations associated with proprietary models like GPT-4 when extracting findings from chest x-ray reports.
October 29, 2024
Llm
AI lifts nonradiologists' x-ray interpretation skill levels
By Will Morton
An AI model is on par with radiologists for detecting abnormalities on chest x-rays and can boost nonradiologists' reading performance.
October 25, 2024
2024 10 25 Chest Cad Thumbnail
NLPs show age bias when annotating chest x-rays
By Will Morton
Four natural language processing (NLP) tools for chest x-ray report annotation show high overall accuracy but exhibit age-related bias.
October 22, 2024
Ll Ms Bias
AI performs well triaging lung x-rays in real-world settings
By Will Morton
AI-assisted triage of lung x-rays using commercially available software could help reduce turnaround times in real-world settings by 77%.
October 11, 2024
Lunit1
CDC considers chest x-ray AI for TB screening program
By Will Morton
The U.S. CDC is considering the use of AI to back up its tuberculosis screening program for immigrants and refugees.
October 3, 2024
XRAI (left) and GradCAM (right) heatmaps for true positive images. The original radiographs are on the left, the Grad-CAM activations and heatmaps are in the middle, and the XRAI activations and overlays are on the right. For the XRAI overlays, only regions reaching the 70th percentile of activation strength are shown. Images available under Creative Commons license (CC BY 4.0 DEED, Attribution 4.0 International) and courtesy of PLOS Digital Health.
Page 1 of 376
Next Page