1
|
Benlala I, De Senneville BD, Dournes G, Menant M, Gramond C, Thaon I, Clin B, Brochard P, Gislard A, Andujar P, Chammings S, Gallet J, Lacourt A, Delva F, Paris C, Ferretti G, Pairon JC, Laurent F. Deep Learning for the Automatic Quantification of Pleural Plaques in Asbestos-Exposed Subjects. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19031417. [PMID: 35162440 PMCID: PMC8835296 DOI: 10.3390/ijerph19031417] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/16/2021] [Revised: 01/22/2022] [Accepted: 01/23/2022] [Indexed: 12/10/2022]
Abstract
Objective: This study aimed to develop and validate an automated artificial intelligence (AI)-driven quantification of pleural plaques in a population of retired workers previously occupationally exposed to asbestos. Methods: CT scans of former workers previously occupationally exposed to asbestos who participated in the multicenter APEXS (Asbestos PostExposure Survey) study were collected retrospectively between 2010 and 2017 during the second and the third rounds of the survey. A hundred and forty-one participants with pleural plaques identified by expert radiologists at the 2nd and the 3rd CT screenings were included. Maximum Intensity Projection (MIP) with 5 mm thickness was used to reduce the number of CT slices for manual delineation. A Deep Learning AI algorithm using 2D-convolutional neural networks was trained with 8280 images from 138 CT scans of 69 participants for the semantic labeling of Pleural Plaques (PP). In all, 2160 CT images from 36 CT scans of 18 participants were used for AI testing versus ground-truth labels (GT). The clinical validity of the method was evaluated longitudinally in 54 participants with pleural plaques. Results: The concordance correlation coefficient (CCC) between AI-driven and GT was almost perfect (>0.98) for the volume extent of both PP and calcified PP. The 2D pixel similarity overlap of AI versus GT was good (DICE = 0.63) for PP, whether they were calcified or not, and very good (DICE = 0.82) for calcified PP. A longitudinal comparison of the volumetric extent of PP showed a significant increase in PP volumes (p < 0.001) between the 2nd and the 3rd CT screenings with an average delay of 5 years. Conclusions: AI allows a fully automated volumetric quantification of pleural plaques showing volumetric progression of PP over a five-year period. The reproducible PP volume evaluation may enable further investigations for the comprehension of the unclear relationships between pleural plaques and both respiratory function and occurrence of thoracic malignancy.
Collapse
Affiliation(s)
- Ilyes Benlala
- Faculté de Médecine, Université de Bordeaux, 33000 Bordeaux, France; (G.D.); (P.B.); (F.L.)
- Service d’Imagerie Médicale Radiologie Diagnostique et Thérapeutique, CHU de Bordeaux, 33000 Bordeaux, France
- Centre de Recherche Cardio-Thoracique de Bordeaux, INSERM U1045, Université de Bordeaux, 33000 Bordeaux, France
- Correspondence:
| | - Baudouin Denis De Senneville
- Mathematical Institute of Bordeaux (IMB), CNRS, INRIA, Bordeaux INP, UMR 5251, Université de Bordeaux, 33400 Talence, France;
| | - Gael Dournes
- Faculté de Médecine, Université de Bordeaux, 33000 Bordeaux, France; (G.D.); (P.B.); (F.L.)
- Service d’Imagerie Médicale Radiologie Diagnostique et Thérapeutique, CHU de Bordeaux, 33000 Bordeaux, France
- Centre de Recherche Cardio-Thoracique de Bordeaux, INSERM U1045, Université de Bordeaux, 33000 Bordeaux, France
| | - Morgane Menant
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France; (M.M.); (C.G.); (J.G.); (A.L.); (F.D.)
| | - Celine Gramond
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France; (M.M.); (C.G.); (J.G.); (A.L.); (F.D.)
| | - Isabelle Thaon
- Centre de Consultation de Pathologies Professionnelles, CHRU de Nancy, Université de Lorraine, 54000 Nancy, France;
| | - Bénédicte Clin
- Service de Santé au Travail et Pathologie Professionnelle, CHU Caen, 14000 Caen, France;
- Faculté de Médecine, Université de Caen, 14000 Caen, France
| | - Patrick Brochard
- Faculté de Médecine, Université de Bordeaux, 33000 Bordeaux, France; (G.D.); (P.B.); (F.L.)
- Service de Médecine du Travail et de Pathologies Professionnelles, CHU de Bordeaux, 33000 Bordeaux, France
| | - Antoine Gislard
- Faculté de Médecine, Normandie Université, UNIROUEN, UNICAEN, ABTE, 76000 Rouen, France;
- Centre de Consultations de Pathologie Professionnelle, CHU de Rouen, CEDEX, 76031 Rouen, France
| | - Pascal Andujar
- Equipe GEIC20, INSERM U955, 94000 Créteil, France; (P.A.); (J.-C.P.)
- Faculté de Santé, Université Paris-Est Créteil, 94000 Créteil, France
- Service de Pathologies Professionnelles et de l’Environnement, Centre Hospitalier Intercommunal Créteil, Institut Santé-Travail Paris-Est, 94000 Créteil, France
- Institut Interuniversitaire de Médecine du Travail de Paris-Ile de France, 94000 Créteil, France;
| | - Soizick Chammings
- Institut Interuniversitaire de Médecine du Travail de Paris-Ile de France, 94000 Créteil, France;
| | - Justine Gallet
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France; (M.M.); (C.G.); (J.G.); (A.L.); (F.D.)
| | - Aude Lacourt
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France; (M.M.); (C.G.); (J.G.); (A.L.); (F.D.)
| | - Fleur Delva
- Epicene Team, Bordeaux Population Health Research Center, INSERM UMR 1219, Université de Bordeaux, 33000 Bordeaux, France; (M.M.); (C.G.); (J.G.); (A.L.); (F.D.)
| | - Christophe Paris
- 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
| | - Gilbert Ferretti
- INSERM U 1209 IAB, 38700 La Tronche, France;
- Domaine de la Merci, Faculté de Médecine, Université Grenoble Alpes, 38706 La Tronche, France
- Service de Radiologie Diagnostique et Interventionnelle Nord, CHU Grenoble Alpes, CS 10217, 38043 Grenoble, France
| | - Jean-Claude Pairon
- Equipe GEIC20, INSERM U955, 94000 Créteil, France; (P.A.); (J.-C.P.)
- Faculté de Santé, Université Paris-Est Créteil, 94000 Créteil, France
- Service de Pathologies Professionnelles et de l’Environnement, Centre Hospitalier Intercommunal Créteil, Institut Santé-Travail Paris-Est, 94000 Créteil, France
- Institut Interuniversitaire de Médecine du Travail de Paris-Ile de France, 94000 Créteil, France;
| | - François Laurent
- Faculté de Médecine, Université de Bordeaux, 33000 Bordeaux, France; (G.D.); (P.B.); (F.L.)
- Service d’Imagerie Médicale Radiologie Diagnostique et Thérapeutique, CHU de Bordeaux, 33000 Bordeaux, France
- Centre de Recherche Cardio-Thoracique de Bordeaux, INSERM U1045, Université de Bordeaux, 33000 Bordeaux, France
| |
Collapse
|
3
|
Diagnostic Performance of Ultra-Low-Dose Computed Tomography for Detecting Asbestos-Related Pleuropulmonary Diseases: Prospective Study in a Screening Setting. PLoS One 2016; 11:e0168979. [PMID: 28033378 PMCID: PMC5199059 DOI: 10.1371/journal.pone.0168979] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2016] [Accepted: 12/11/2016] [Indexed: 12/21/2022] Open
Abstract
Objective To evaluate the diagnostic performance of Ultra-Low-Dose Chest CT (ULD CT) for the detection of any asbestos-related lesions (primary endpoint) and specific asbestos-related abnormalities, i.e. non-calcified and calcified pleural plaques, diffuse pleural thickening, asbestosis and significant lung nodules (secondary endpoints). Material and Methods 55 male patients (55.7±8.1 years old) with occupational asbestos exposure for at least 15 years and where CT screening was indicated were prospectively included. They all underwent a standard unenhanced chest CT (120kV, automated tube current modulation), considered as the reference, and an ULD CT (135kV, 10mA), both with iterative reconstruction. Two chest radiologists independently and blindly read the examinations, following a detailed protocol. Sensitivity, specificity, positive predictive value, negative predictive value, accuracy and error rate of ULD CT were calculated using the exact method of Pearson with a confidence interval of 95%. Results Radiation dose was 17.9±1.2mGy.cm (0.25mSv) for the ULD-CT versus 288.8 ±151mGy.cm (4mSv); p <2.2e-16. Prevalence of abnormalities was 20%. The ULD CT’s diagnostic performance in joint reading was high for the primary endpoint (sensitivity = 90.9%, specificity = 100%, positive predictive value = 100%, negative predictive value = 97.8%), high for lung nodules, diffuse pleural thickening and calcified pleural plaques (sensitivity, specificity, PPV and NPV = 100%) and fair for asbestosis (sensitivity = 75%, specificity = 100%, PPV = 00%, NPV = 98.1%). Intra-reader accuracy between the ULD CT and the reference CT for the primary endpoint was 98% for the senior and 100% for the junior radiologist. Inter-reader agreement for the primary endpoint was almost perfect (Cohen’s Kappa of 0.81). Conclusion ULD CT in the screening of asbestos exposure related diseases has 90.9% sensitivity and 100% specificity, and could therefore be proposed as a first line examination.
Collapse
|
7
|
Claude-Desroches M, Bierry G, Touitou-Gottenberg D, Golmard JL, Grenier PA, Beigelman-Aubry C. Focal dependent pleural thickening at MDCT: pleural lesion or functional abnormality? Diagn Interv Imaging 2012; 93:360-4. [PMID: 22542210 DOI: 10.1016/j.diii.2012.01.011] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/19/2022]
Abstract
PURPOSE To describe the characteristics of reversible focal pleural thickenings (PTs) mimicking real plaques, that firstly suggest asbestos exposure or pleural metastasis; to propose an imaging strategy and propose an explanation for their mechanism of formation. PATIENTS AND METHODS Retrospective review of data from 19 patients with PTs fitting the description of pleural plaques at chest computed tomography (CT) and presenting modifications (clearance or appearance) of at least one PT at an additional chest examination in prone position. RESULTS A total of 152 PTs were recorded on the first chest CT examinations with a range of two to 19 pleural opacities per patient. All PTs had a posterior distribution in the lower lobes. On the additional acquisitions, 144 PTs disappeared. Seventeen patients presented complete regression of PTs and two patients presented persistence of eight PTs. CONCLUSION Additional low dose acquisition in prone position should be performed in all patients presenting with focal PT in a dependent and basal location. This may allow to exclude a pleural plaque in case of asbestos exposure but also a pleural metastasis in oncologic patients. These reversible dependent PTs could be related to physiological focal accumulation of lymphatic fluid in subpleural area.
Collapse
Affiliation(s)
- M Claude-Desroches
- Department of Radiology, hôpital Pitié-Salpêtrière, Assistance publique-Hôpitaux de Paris, 47/83, boulevard de l'Hôpital, 75651 Paris, France
| | | | | | | | | | | |
Collapse
|
8
|
Letourneux M, Clin B, Clin-Godard B, Marquignon MF, Gauberti P. [What tools should be used for follow-up post occupational exposure? What should be the frequency?]. Rev Mal Respir 2012; 29:205-12. [PMID: 22405114 DOI: 10.1016/j.rmr.2011.07.008] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2011] [Accepted: 07/18/2011] [Indexed: 11/28/2022]
Abstract
As long as the value of screening for cancers related to asbestos is not proven in the population at risk, the medical benefits of follow-up post-professional exposure remain uncertain and the only justification is to answer the questions of anxious retired workers concerning the consequences of their past-exposure and to provide compensation for any abnormalities that are demonstrated. In this country, to answer the questions posed in the title of this contribution in the case of pathologies related to asbestos, it is necessary, after verifying the fact and the level of exposure, to identify the pleural or pulmonary fibrosis and, above all, the pleural plaques, which constitute the essential lesions currently screened for. Thoracic CT scanning without contrast is the examination of choice to achieve this objective. There are, however, two significant problems. On one hand there is a high incidence of pulmonary micronodules, the necessary surveillance of which requires subsequent scans, leading to increased irradiation and anxiety. On the other hand the diagnostic uncertainty concerning discrete lesions is a source of confusion for the persons followed-up. There are, at present, neither scientific criteria to determine the optimum frequency of examination nor any arguments for replacing the pragmatic proposals of the consensus conference of 1999. It is important, therefore, to provide a medical assessment appropriate to the symptoms and anxiety expressed by a person previously exposed to asbestos. Overall it is necessary to question the benefit to the exposed person, in terms of quality of life, of a regular search for lesions that would usually be asymptomatic if not identified. Would it not be more judicious and more equitable to compensate persons whose past-exposure is sufficient to increase significantly their risk of cancer independently of the presence of benign abnormalities.
Collapse
Affiliation(s)
- M Letourneux
- ERI3 "cancers et populations", UFR de médecine de Caen, service de santé au travail et pathologie professionnelle, CHU de Caen, avenue de la Côte-de-Nacre, France.
| | | | | | | | | |
Collapse
|
9
|
Ameille J, Rosenberg N, Matrat M, Descatha A, Mompoint D, Hamzi L, Atassi C, Vasile M, Garnier R, Pairon JC. Asbestos-related diseases in automobile mechanics. THE ANNALS OF OCCUPATIONAL HYGIENE 2012; 56:55-60. [PMID: 21965465 PMCID: PMC3678990 DOI: 10.1093/annhyg/mer066] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Abstract
PURPOSE Automobile mechanics have been exposed to asbestos in the past, mainly due to the presence of chrysotile asbestos in brakes and clutches. Despite the large number of automobile mechanics, little is known about the non-malignant respiratory diseases observed in this population. The aim of this retrospective multicenter study was to analyse the frequency of pleural and parenchymal abnormalities on high-resolution computed tomography (HRCT) in a population of automobile mechanics. METHODS The study population consisted of 103 automobile mechanics with no other source of occupational exposure to asbestos, referred to three occupational health departments in the Paris area for systematic screening of asbestos-related diseases. All subjects were examined by HRCT and all images were reviewed separately by two independent readers; who in the case of disagreement discussed until they reached agreement. Multiple logistic regression models were constructed to investigate factors associated with pleural plaques. RESULTS Pleural plaques were observed in five cases (4.9%) and interstitial abnormalities consistent with asbestosis were observed in one case. After adjustment for age, smoking status, and a history of non-asbestos-related respiratory diseases, multiple logistic regression models showed a significant association between the duration of exposure to asbestos and pleural plaques. CONCLUSIONS The asbestos exposure experienced by automobile mechanics may lead to pleural plaques. The low prevalence of non-malignant asbestos-related diseases, using a very sensitive diagnostic tool, is in favor of a low cumulative exposure to asbestos in this population of workers.
Collapse
Affiliation(s)
- Jacques Ameille
- AP-HP, Unité de pathologie professionnelle, Hôpital Raymond Poincaré, 92380 Garches, France.
| | | | | | | | | | | | | | | | | | | |
Collapse
|
10
|
Ferretti G. [What are the tools for post-occupational follow-up, how should they be performed and what are their performance, limits and benefit/risk ratio? Chest X-Ray and CT scan]. Rev Mal Respir 2011; 28:761-72. [PMID: 21742237 DOI: 10.1016/j.rmr.2011.02.012] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2011] [Accepted: 02/17/2011] [Indexed: 10/18/2022]
Abstract
Chest radiography and computed tomography (CT) are the two radiological techniques used for the follow-up of people exposed to asbestos. Since the last conference of consensus (1999), the scientific literature has primarily covered high-resolution CT and high-resolution volume CT (HR-VCT). We consider in turn the contribution of digital thoracic radiography, recommendations for the performance of HR-VCT to ensure the quality of examination while controlling the delivered radiation dose, and the need to refer to the "CT atlas of benign diseases related to asbestos exposure", published by a group of French experts in 2007, for interpretation. The results of the published studies concerning radiography or CT are then reviewed. We note the great interobserver variability in the recognition of pleural plaques and asbestosis, indicating the need for adequate training of radiologists, and the importance of defining standardized, quantified criteria for CT abnormalities. The very low agreement between thoracic and general radiologists must be taken into account. The reading of CT scans in cases of occupational exposure to asbestos should be entrusted to thoracic radiologists or to general radiologists having validated specific training. A double interpretation of CT could be considered in medicosocial requests. CT is more sensitive than chest radiography in the detection of bronchial carcinoma but generates a great number of false positive results (96 to 99%). No scientific data are available to assess the role of imaging by either CT or chest radiography in the early detection of mesothelioma.
Collapse
Affiliation(s)
- G Ferretti
- Université J-Fourrier, BP 53, 38041 Grenoble cedex 9, France.
| |
Collapse
|
15
|
Carette MF, Chabchoub H, Tassart M, Korzec J, Marsault C, Khalil A. [Virtual pleuroscopy of diaphragmatic pleura: myth or reality?]. REVUE DE PNEUMOLOGIE CLINIQUE 2008; 64:15-19. [PMID: 18603174 DOI: 10.1016/j.pneumo.2008.06.006] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/26/2023]
Abstract
PURPOSE Evaluate the feasibility of the virtual pleuroscopy (VP) in the detection of the pleural plaques. METHOD AND MATERIALS Twenty consecutive patients, having asbestos exposure, explored by unenhanced multidetector CT-scan (Siemens, Sensation 16). The imaging parameters were as follows: beam width, 12 mm; beam pitch, 1; and reconstruction thickness, 1mm every 0.8mm at 120 kV and 180 mA. The image display used a surface-rendering algorithm and produced perspective red-scale images with a matrix of 512 x 512. Each VP image simulated a coned-down view, with a variable cone angle to explore the diaphragmatic pleura. The camera was placed 1 to 2 cm above the diaphragmatic dome. Four views are studied by diaphragm: crâniocaudal, lateral tangential, anterior and posterior. The observed virtual pleura aspect was classified in 5 groups (gr): gr 1: Rib band, gr 2: lobulated pleural thickening, gr 3: spicular, gr 4: plaques and gr 5: nodules. The results were compared to the other MDCT images using multiplanar reformatting. RESULTS The visualization of each diaphragm was optimal (35/40; 87.5%), limited (3/40; round atelectasis and asbestosis) or impossible (2/40; asbestosis). The classifications of the studied 38 diaphragmatic pleura were: gr 1 (n=15), gr 2 (n=5), gr 3 (n=11), gr 4 (n=7), gr 5 (n=0). The MDCT analysis showed normal pleura for both gr 1 and gr 2, a confirmed or beginning of fibrosis for gr 3 and confirmed the presence of pleural plaques on the diaphragmatic pleura in all cases of gr 4. CONCLUSION The virtual pleuroscopy is a reality. It is a feasible technique. Other studies are necessary to confirm these preliminary results.
Collapse
Affiliation(s)
- M-F Carette
- Service de radiologie, Hôpital Tenon (AP-HP), 4 rue de la Chine, Paris cedex 20, France.
| | | | | | | | | | | |
Collapse
|