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
Shoulder
Deep-learning model measures shoulder kinematics on DDR
December 1, 2023
X Ray Radiography Tech Patient
Vieworks introduces new technologies at RSNA 2023
November 30, 2023
From a Single Detector to a Family of Solutions.
Sponsored
From a Single Detector to a Family of Solutions.
August 31, 2023
Artificial Intelligence Ai Global Communication Network
AI cuts time for radiologists reporting fractures on x-rays
November 28, 2023
Related Stories
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
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
Representative radiographs (top), acquired in anteroposterior projection in the supine position, and corresponding attention maps (bottom). (A) Images show main diagnostic findings of the internal data set in a 49-year-old male patient with congestion, pneumonic infiltrates, and effusion (left); a 64-year-old male patient with congestion, pneumonic infiltrates, and effusion (middle); and a 69-year-old female patient with effusion (right). Image courtesy of Radiology.
Artificial Intelligence
Can transformer models improve AI image interpretations?
From a Single Detector to a Family of Solutions.
Sponsor Content
From a Single Detector to a Family of Solutions.
More in Digital X-Ray
Deep-learning model measures shoulder kinematics on DDR
An AI algorithm may make dynamic digital radiography (DDR) more efficient by automatically measuring kinematics involved in certain shoulder injuries.
December 1, 2023
Shoulder
Vieworks introduces new technologies at RSNA 2023
Vieworks introduced three new radiation dose and image processing software technologies at RSNA 2023.
November 30, 2023
X Ray Radiography Tech Patient
AI assist for x-ray reads serves nonradiologists well in the ED
German researchers are testing ways to support nonradiologists in interpreting chest x-rays in emergency department (ED) settings using an AI assistant.
November 29, 2023
Chest Lung Xray 400
AI cuts time for radiologists reporting fractures on x-rays
A commercially available AI algorithm that can prioritize x-ray exams when it detects fractures yields “tremendous reductions” in report turnaround times.
November 28, 2023
Artificial Intelligence Ai Global Communication Network
3 AI-based technology trends on display at the 2023 RSNA conference
Vincent Chan of Carestream predicts technology trends for AI in digital radiography at RSNA 2023.
November 22, 2023
Vincent Chan.
Hip x-rays help screen for osteoporosis in THA patients
Plain hip x-rays may help screen patients for osteoporosis before they undergo total hip arthroplasty (THA).
November 21, 2023
An example of measurement on plain anterior-posterior x-rays used in the study: canal-bone-ratio CBR-7 cm (Cm/Cc) and CBR-10 cm (Dm/Dc), canal-calcar ratio CCR (Dm/Bm); canal flare index CFI (A/Dm). Image courtesy of Scientific Reports.
AI detects incidental lung nodules on chest x-rays
AI based lesion-detection software used in daily practice can help identify clinically significant incidental lung nodules on chest x-rays
November 16, 2023
A true positive case in a 72-year-old male with a granuloma on chest x-ray after visiting the neurology outpatient clinic for memory disturbance. A small lung nodule was detected in the left-middle to lower lung field by AI software, with an abnormality score of 26%. Co-existing fibrosis was suspected in the apex of bilateral upper lungs, with an abnormality score of 76%. Image courtesy of Scientific Reports.
Julianna Czum talks AI chest radiograph study with AuntMinnie.com
Julianna Czum, MD, spoke with AuntMinnie.com on a study that tested a deep-learning algorithm on triaging chest radiographs.
November 6, 2023
Julianna Czum Interview
AI model predicts scoliosis spinal curve progression
A deep-learning AI model shows promise for predicting spinal curves in individuals with adolescent idiopathic scoliosis.
November 3, 2023
Three regions of interest (ROI) were selected and processed for training from each original radiograph. The leftmost image is the original coronal view radiograph. The original radiograph was passed through the CLAHE algorithm to enhance image brightness and contrast. The three crop boxes outlined by red dotted lines illustrate the three crops generated for model training. Crop 1 selects the ROI for the whole-spine region according to coordinates exported by AlignProCARE. Crops 2 and 3 select the ROIs for the upper and lower end vertebra of the major curvature. All ROIs were subsequently resized into 256 × 256 for Crop 1 and 50 × 50 for Crop 2 and 3. Crop 1 ROI was additionally multiplied by a Gaussian mask to amplify the signal of the vertebrae. Image courtesy of the Global Spine Journal.
Bone health assessed among transgender adults
Puberty suppression treatment in transgender adolescents followed by long-term gender-affirming hormones appears safe for bone health.
November 1, 2023
Transgender
AI boosts radiologist perception training
A team in Europe has launched a novel web application to help radiology trainees gain skills in detecting lung nodules on chest x-rays.
October 31, 2023
Screenshots of the imaging viewer interface before (a-b) and after (c-d) having clicked “Review placed markers.” The “Case assessment widget” has been magnified in (b,d). One marker was incorrectly placed (c), which is signified with a red cross. One nodule was not identified (c) and was highlighted by a yellow circle through the mouse over function in the “List of synthetic lesions.” Image courtesy of the British Journal of Radiology.
AI model shows promise for interpreting follow-up chest x-rays
A group in Seoul, South Korea, has developed an AI model that could help reduce radiology workflows by identifying “no changes” in follow-up chest x‑rays.
October 24, 2023
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.
Page 1 of 371
Next Page