Objective: This study aimed to investigate the feasibility of using artificial intelligence (AI) to identify normal chest radiography (CXR) from the worklist of radiologists in a health-screening environment.
Materials And Methods: This retrospective simulation study was conducted using the CXRs of 5887 adults (mean age ± standard deviation, 55.4 ± 11.8 years; male, 4329) from three health screening centers in South Korea using a commercial AI (Lunit INSIGHT CXR3, version 3.5.8.8). Three board-certified thoracic radiologists reviewed CXR images for referable thoracic abnormalities and grouped the images into those with visible referable abnormalities (identified as abnormal by at least one reader) and those with clearly visible referable abnormalities (identified as abnormal by at least two readers). With AI-based simulated exclusion of normal CXR images, the percentages of normal images sorted and abnormal images erroneously removed were analyzed. Additionally, in a random subsample of 480 patients, the ability to identify visible referable abnormalities was compared among AI-unassisted reading (i.e., all images read by human readers without AI), AI-assisted reading (i.e., all images read by human readers with AI assistance as concurrent readers), and reading with AI triage (i.e., human reading of only those rendered abnormal by AI).
Results: Of 5887 CXR images, 405 (6.9%) and 227 (3.9%) contained visible and clearly visible abnormalities, respectively. With AI-based triage, 42.9% (2354/5482) of normal CXR images were removed at the cost of erroneous removal of 3.5% (14/405) and 1.8% (4/227) of CXR images with visible and clearly visible abnormalities, respectively. In the diagnostic performance study, AI triage removed 41.6% (188/452) of normal images from the worklist without missing visible abnormalities and increased the specificity for some readers without decreasing sensitivity.
Conclusion: This study suggests the feasibility of sorting and removing normal CXRs using AI with a tailored cut-off to increase efficiency and reduce the workload of radiologists.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9523233 | PMC |
| http://dx.doi.org/10.3348/kjr.2022.0189 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Diagnostic accuracy of ultra-low-dose chest CT vs chest X-ray for acute non-traumatic pulmonary diseases.
Eur Radiol
January 2025
Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
Objectives: To compare the diagnostic accuracy of ULDCT to CXR for detecting non-traumatic pulmonary diseases at the emergency department (ED) and to study diagnostic confidence levels.
Methods: Secondary analysis of the prospective OPTIMACT trial (2418 ED participants randomly allocated to ULDCT or CXR). Diagnoses at imaging at the ED were compared to the reference diagnosis on day 28.
Assessing the Image Quality of Digitally Reconstructed Radiographs from Chest CT.
J Imaging Inform Med
January 2025
Leiden University Medical Center (LUMC), Leiden, the Netherlands.
Rising computed tomography (CT) workloads require more efficient image interpretation methods. Digitally reconstructed radiographs (DRRs), generated from CT data, may enhance workflow efficiency by enabling faster radiological assessments. Various techniques exist for generating DRRs.
View Article and Find Full Text PDFAssessment of scattered and leakage radiation from ultra-portable X-ray systems in chest imaging: An independent study.
PLOS Glob Public Health
January 2025
Médecins Sans Frontières, International, Geneva, Switzerland.
Ultraportable (UP) X-ray devices are ideal to use in community-based settings, particularly for chest X-ray (CXR) screening of tuberculosis (TB). Unfortunately, there is insufficient guidance on the radiation safety of these devices. This study aims to determine the radiation dose by UP X-ray devices to both the public and radiographers compared to international dose limits.
View Article and Find Full Text PDFZooCNN: A Zero-Order Optimized Convolutional Neural Network for Pneumonia Classification Using Chest Radiographs.
J Imaging
January 2025
Department of Food Science, Fu Jen Catholic University, New Taipei City 242062, Taiwan.
Pneumonia, a leading cause of mortality in children under five, is usually diagnosed through chest X-ray (CXR) images due to its efficiency and cost-effectiveness. However, the shortage of radiologists in the Least Developed Countries (LDCs) emphasizes the need for automated pneumonia diagnostic systems. This article presents a Deep Learning model, Zero-Order Optimized Convolutional Neural Network (ZooCNN), a Zero-Order Optimization (Zoo)-based CNN model for classifying CXR images into three classes, Normal Lungs (NL), Bacterial Pneumonia (BP), and Viral Pneumonia (VP); this model utilizes the Adaptive Synthetic Sampling (ADASYN) approach to ensure class balance in the Kaggle CXR Images (Pneumonia) dataset.
View Article and Find Full Text PDFFeasibility of ultraportable US in detecting clinically concerning recurrent pneumothorax in patients with chest trauma.
Trauma Surg Acute Care Open
December 2024
Department of Surgery, Division of Trauma & Acute Care Surgery, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
Background: Bedside thoracic ultrasound (US) offers numerous advantages over chest X-ray (CXR) for identification of recurrent pneumothoraces (PTX) after tube thoracostomy (TT) removal. Technologic advancements have led to the development of hand-held devices capable of producing high-quality images termed ultra-portable US (UPUS). We hypothesized that UPUS would be as successful as CXR in detecting post-TT removal PTX and would be preferred by patients.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!