AI-Driven Automated Detection of Pleural Plaques on Chest CT Scans in Retired Asbestos-Exposed Workers
Abstract
This study aimed to develop and validate an automated framework for detecting pleural plaques (PPs) at the patient level using a single chest CT scan. Methods: A database of chest CT scans with corresponding individual binary annotations for PP presence was first established through expert visual assessment, based on consensus among a board of specialized radiologists. This dataset served to train and validate a patient-level classification framework for automated PP presence detection. This framework leverages a pre-trained PP segmentation network, thus obviating the need for retraining large-scale deep learning models. This segmentation backbone is supplemented by a lightweight classification module that integrates the network’s outputs to infer the presence or absence of PPs at patient level. Furthermore, a patch-wise processing strategy was employed to optimize computational efficiency and training time while retaining critical local contextual information. Results: The framework was evaluated on a cohort of 1241 retired workers with documented occupational asbestos exposure, using 10-fold cross-validation (30% training, 10% validation, 60% testing). It achieved a balanced accuracy of 97.0%, sensitivity of 96.6%, and specificity of 97.4%, demonstrating performance slightly superior to that of two expert radiologists (balanced accuracy: 90.9%/91.4%, sensitivity: 88.0%/88.8%, specificity: 93.9%/94.1% for Expert1/Expert2) and substantially superior to that of a radiologist without specialized expertise in asbestos-related manifestations (balanced accuracy: 80.0%, sensitivity: 75.1%, specificity: 84.8%). Conclusion: The proposed framework demonstrates strong potential for automated patient-level identification of pleural plaques from a single CT scan. Our approach could be particularly useful in screening settings that involve compensation claims related to occupational diseases.
Related
- Evidence for a cohesion-related function of alpaca hums: Linking automated call detection with GPS data
- Efficient primer design for broad-range virus detection: A semi-automated workflow using sequence clustering and varVAMP
- Reproducible detection of antigen-specific T cells and Tregs via standardized and automated activation-induced marker assay workflows
- OsteoNet-X: A deep residual learning framework for automated osteoporosis detection from knee X-ray images
- YOLO-WSR: A wavelet feature and structure guided diffusion model for detection and automated restoration of cultural heritage artifact images
BibTeX
@article{petitpas2026aidriven,
title = {{AI-Driven Automated Detection of Pleural Plaques on Chest CT Scans in Retired Asbestos-Exposed Workers}},
author = {Yannis Petitpas and Ilyes Benlala and Fabien Baldacci and Gaël Dournes and Kellian Jaunas and Bénédicte Clin and Patrick Brochard and M. Antoine Gislard and Fleur Delva and Aude Lacourt and Christophe Paris and François Laurent and Jean-Claude Pairon and Baudouin Denis de Senneville},
journal = {Diagnostics},
year = {2026},
month = oct,
doi = {10.3390/diagnostics16162519},
url = {https://hal.science/hal-05748869v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-Driven Automated Detection of Pleural Plaques on Chest CT Scans in Retired Asbestos-Exposed Workers
AU - Yannis Petitpas
AU - Ilyes Benlala
AU - Fabien Baldacci
AU - Gaël Dournes
AU - Kellian Jaunas
AU - Bénédicte Clin
AU - Patrick Brochard
AU - M. Antoine Gislard
AU - Fleur Delva
AU - Aude Lacourt
AU - Christophe Paris
AU - François Laurent
AU - Jean-Claude Pairon
AU - Baudouin Denis de Senneville
PY - 2026
DA - 2026/10/19
JO - Diagnostics
DO - 10.3390/diagnostics16162519
UR - https://hal.science/hal-05748869v1
AB - This study aimed to develop and validate an automated framework for detecting pleural plaques (PPs) at the patient level using a single chest CT scan. Methods: A database of chest CT scans with corresponding individual binary annotations for PP presence was first established through expert visual assessment, based on consensus among a board of specialized radiologists. This dataset served to train and validate a patient-level classification framework for automated PP presence detection. This framework leverages a pre-trained PP segmentation network, thus obviating the need for retraining large-scale deep learning models. This segmentation backbone is supplemented by a lightweight classification module that integrates the network’s outputs to infer the presence or absence of PPs at patient level. Furthermore, a patch-wise processing strategy was employed to optimize computational efficiency and training time while retaining critical local contextual information. Results: The framework was evaluated on a cohort of 1241 retired workers with documented occupational asbestos exposure, using 10-fold cross-validation (30% training, 10% validation, 60% testing). It achieved a balanced accuracy of 97.0%, sensitivity of 96.6%, and specificity of 97.4%, demonstrating performance slightly superior to that of two expert radiologists (balanced accuracy: 90.9%/91.4%, sensitivity: 88.0%/88.8%, specificity: 93.9%/94.1% for Expert1/Expert2) and substantially superior to that of a radiologist without specialized expertise in asbestos-related manifestations (balanced accuracy: 80.0%, sensitivity: 75.1%, specificity: 84.8%). Conclusion: The proposed framework demonstrates strong potential for automated patient-level identification of pleural plaques from a single CT scan. Our approach could be particularly useful in screening settings that involve compensation claims related to occupational diseases.
SN - 2075-4418
ER -