AI-Driven Automated Detection of Pleural Plaques on Chest CT Scans in Retired Asbestos-Exposed Workers.
Authors
Affiliations (17)
Affiliations (17)
- Mathematical Institute of Bordeaux (IMB), CNRS, INRIA, Bordeaux INP, UMR 5251, Université de Bordeaux, 33400 Talence, France.
- Centre de Recherche Cardio-Thoracique de Bordeaux, INSERM U1045, Université de Bordeaux, 33000 Bordeaux, France.
- Service d'Imagerie Médicale Radiologie Diagnostique et Thérapeutique, CHU de Bordeaux, 33000 Bordeaux, France.
- CNRS, Bordeaux INP, LaBRI, UMR 5800, Université de Bordeaux, 33400 Talence, France.
- Service de Médecine du Travail et de Pathologies Professionnelles, CHU de Bordeaux, 33000 Bordeaux, France.
- Service de Santé au Travail et Pathologie Professionnelle, CHU Caen, 14000 Caen, France.
- Faculté de Médecine, Université de Caen, 14000 Caen, France.
- INSERM U1086 «ANTICIPE», 14000 Caen, France.
- Centre de Consultations de Pathologie Professionnelle, CHU de Rouen, CEDEX, 76031 Rouen, France.
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France.
- Service Santé Travail Environnement, CHU de Bordeaux, 33000 Bordeaux, France.
- Service de Santé au Travail et Pathologie Professionnelle, CHU Rennes, 35000 Rennes, France.
- Institut de Recherche en Santé, Environnement et Travail, INSERM U1085, 35000 Rennes, France.
- Equipe GEIC20, INSERM U955, 94000 Créteil, France.
- Faculté de Santé, Université Paris-Est Créteil, 94000 Créteil, France.
- Service de Pathologies Professionnelles et de l'Environnement, Centre Hospitalier Intercommunal, Institut Santé-Travail Paris-Est, 94000 Créteil, France.
- Institut Interuniversitaire de Médecine du Travail de Paris-Ile de France, 94000 Créteil, France.
Abstract
<b>Background/Objective:</b> 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. <b>Methods:</b> 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. <b>Results:</b> 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%). <b>Conclusion:</b> 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.