The subgroup imperative: Chest radiograph classifier generalization gaps in patient, setting, and pathology subgroups

M Ahluwalia, M Abdalla, J Sanayei… - Radiology: Artificial …, 2023 - pubs.rsna.org
… implications for algorithm deployment because radiologists … alarm when users consider
deploying these algorithms as a … error; however, it was validated in this study and its error lies …

Classification of chest radiographs using general purpose cloud-based automated machine learning: pilot study

T Ghosh, S Tanwar, S Chumber, K Vani - Egyptian Journal of Radiology …, 2021 - Springer
… the quest for greater accuracy by deploying multiple synergistically working trained machine
… Data augmentation procedures should also be validated for use with medical imaging, …

Analysis of potential for user errors in mobile deployment of radiology deep learning for cardiac rhythm device detection

C Sabottke, M Breaux, R Lee, A Foreman… - Journal of Digital …, 2021 - Springer
… devices on AP chest radiographs during our … validation images. For this simplified scenario,
the model had only one prediction error for the validation set on a lateral chest radiograph. …

Evaluation of the Performance of an Artificial Intelligence (AI) Algorithm in Detecting Thoracic Pathologies on Chest Radiographs

H Bettinger, G Lenczner, J Guigui, L Rotenberg… - Diagnostics, 2024 - mdpi.com
… on chest radiographs of patients to validate its performance in the real-world clinical setting.
Deployment and validation of an AI system for detecting abnormal chest radiographs in …

External validation based on transfer learning for diagnosing atelectasis using portable chest X-rays

X Huang, B Li, T Huang, S Yuan, W Wu, H Yin… - Frontiers in …, 2022 - frontiersin.org
… the data into the training (80%) and validation (20%) sets, and the same pretreatment
operation was adopted. Since the chest radiography images were asymmetric (16), we adopted …

Development and validation of an abnormality-derived deep-learning diagnostic system for major respiratory diseases

C Wang, J Ma, S Zhang, J Shao, Y Wang… - NPJ Digital …, 2022 - nature.com
… actual deployment in the scenario where CT devices are less available. Further we deployed
… of major thoracic diseases based on chest radiographs. The multi-label abnormality results …

Risk of bias in chest radiography deep learning foundation models

B Glocker, C Jones, M Roschewitz… - Radiology: Artificial …, 2023 - pubs.rsna.org
… of data from a total of 42,884 patients with 127,118 chest radiographs divided into three
sets for training (76,205 radiographs), validation (12,673 radiographs) and testing (38,240 …

Automated chest radiography and mass systematic screening for tuberculosis

F Madhani, RA Maniar, A Burfat… - … of Tuberculosis and …, 2020 - ingentaconnect.com
… -aided detection of pulmonary tuberculosis in chest radiographs: a validation study from sub-…
on chest radiography among private sector patients in Pakistan. Sci Rep 2018; 8(1): 12339. …

Deep-learning: A potential method for tuberculosis detection using chest radiography

R Hooda, S Sofat, S Kaur, A Mittal… - … conference on signal …, 2017 - ieeexplore.ieee.org
chest radiographs (CXRs) are prominently used because they have low radiation dose, low
cost, wider acceptability and extensive deployment. … Validation accuracy is obtained by the …

Performance of a deep learning algorithm compared with radiologic interpretation for lung cancer detection on chest radiographs in a health screening population

JH Lee, HY Sun, S Park, H Kim, EJ Hwang, JM Goo… - Radiology, 2020 - pubs.rsna.org
chest radiograph, the chest radiograph was excluded because we could not guarantee whether
there was lung cancer on the chest radiograph… All chest radiographs in the validation test …