Artificial Intelligence-Based Automated Detection of Chest X-ray Abnormalities as Support for Young Radiologists
4 affiliations
- 1Policlinico Umberto I Hospital, Department of Radiological and Oncological Sciences and Pathological Anatomy, Sapienza University, 00161 Rome, Italy
- 2Policlinico Umberto I Hospital, Department of Translational And Precision Medicine, Sapienza University, 00161 Rome, Italy
- 3Department of Experimental and Clinical Biomedical Sciences, Radiodiagnostic Unit n. 2, University of Florence-Azienda OspedalieroUniversitaria Careggi, Largo Brambilla 3, 50134, Florence, Italy
- 4Poliambulatorio Montezemolo, 00195 Rome, Italy
Abstract
Introduction: Chest X-ray (CXR) still represents the most performed radiological examination, but its interpretation may differ among readers. In the last years, several automatic detection tools have been developed to assist radiologists in CXR interpretation. We aimed to evaluate how artificial intelligence (AI)-based software may increase the performance of young radiologists in CXR interpretation compared to that of an experienced CXR radiologist.
Materials and Methods: 500 CXRs were selected to generate a well-balanced dataset. For each patient, the CXR reading was conducted by an AI-based software (Lunit INSIGHT CXR) and, independently, by two general radiologists with less than one year of experience. Furthermore, after three months, the radiologists reviewed all the examinations with the assistance of the software. The following CXR findings were searched: atelectasis, calcification, cardiomegaly, consolidation, fibrosis, nodules, mediastinal widening, pleural effusion, pneumoperitoneum, and pneumothorax. Sensitivity and specificity were computed compared to an expert reader allowed to use AI assistance. Chi-squared tests were used to compare the readings.
Results: A total of 600 findings were identified by the senior radiologist. The sensitivity of young radiologists without AI was significantly lower than that of AI (p < 0.001), while the specificity was significantly higher for both (p < 0.001). With the assistance of AI, overall sensitivity increased in both radiologists (p < 0.001), while specificity decreased (p ≤ 0.004).
Discussion: AI software achieves very high sensitivity, minimizing the number of false negatives as much as possible. As a counterpart, there could be a non-negligible risk of overdiagnosis.
Conclusion: AI-based software assistance can yield a potential enhancement in sensitivity for young radiologists in the interpretation of CXRs. However, there might be a reduction in specificity.
Related
- Development of an artificial intelligence algorithm for automated detection of cardiovascular intervention-related complications.
- Artificial Intelligence‐Assisted Automated Optical Coherence Tomography Analysis for Percutaneous Coronary Intervention Planning: From Plaque Analysis to Precision Lesion Preparation and Stent Optimization
- Harnessing Artificial Intelligence and ChatGPT in Early Detection of Neurodegenerative Disorders: A Transformative Opportunity for Neurology
- Reference Standards in Artificial Intelligence Detection of Apical Periodontitis: A Narrative Review of What Reported Accuracy Measures
- Reliable Detection, Unreliable Clinical Decision-making: Artificial Intelligence Models in Burn Assessment
BibTeX
@article{giuliani2026artificial,
title = {{Artificial Intelligence-Based Automated Detection of Chest X-ray Abnormalities as Support for Young Radiologists}},
author = {Luca Giuliani and Giorgio Maria Masci and Nicholas Landini and Leonardo Bosi and Cosimo Nardi and Flaminia De Cristofaro and Stefano Perotti and Valeria Panebianco and Paolo Giuliani and Carlo Catalano},
journal = {Current Medical Imaging},
year = {2026},
month = jul,
doi = {10.2174/0115734056407511250904090252},
url = {https://doi.org/10.2174/0115734056407511250904090252},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Artificial Intelligence-Based Automated Detection of Chest X-ray Abnormalities as Support for Young Radiologists
AU - Luca Giuliani
AU - Giorgio Maria Masci
AU - Nicholas Landini
AU - Leonardo Bosi
AU - Cosimo Nardi
AU - Flaminia De Cristofaro
AU - Stefano Perotti
AU - Valeria Panebianco
AU - Paolo Giuliani
AU - Carlo Catalano
PY - 2026
DA - 2026/07/30
JO - Current Medical Imaging
DO - 10.2174/0115734056407511250904090252
UR - https://doi.org/10.2174/0115734056407511250904090252
AB - Introduction: Chest X-ray (CXR) still represents the most performed radiological examination, but its interpretation may differ among readers. In the last years, several automatic detection tools have been developed to assist radiologists in CXR interpretation. We aimed to evaluate how artificial intelligence (AI)-based software may increase the performance of young radiologists in CXR interpretation compared to that of an experienced CXR radiologist. Materials and Methods: 500 CXRs were selected to generate a well-balanced dataset. For each patient, the CXR reading was conducted by an AI-based software (Lunit INSIGHT CXR) and, independently, by two general radiologists with less than one year of experience. Furthermore, after three months, the radiologists reviewed all the examinations with the assistance of the software. The following CXR findings were searched: atelectasis, calcification, cardiomegaly, consolidation, fibrosis, nodules, mediastinal widening, pleural effusion, pneumoperitoneum, and pneumothorax. Sensitivity and specificity were computed compared to an expert reader allowed to use AI assistance. Chi-squared tests were used to compare the readings. Results: A total of 600 findings were identified by the senior radiologist. The sensitivity of young radiologists without AI was significantly lower than that of AI (p < 0.001), while the specificity was significantly higher for both (p < 0.001). With the assistance of AI, overall sensitivity increased in both radiologists (p < 0.001), while specificity decreased (p ≤ 0.004). Discussion: AI software achieves very high sensitivity, minimizing the number of false negatives as much as possible. As a counterpart, there could be a non-negligible risk of overdiagnosis. Conclusion: AI-based software assistance can yield a potential enhancement in sensitivity for young radiologists in the interpretation of CXRs. However, there might be a reduction in specificity.
SN - 1573-4056
ER -