학술논문
U-net convolutional neural network applied to progressive fibrotic interstitial lung disease: Is progression at CT scan associated with a clinical outcome?
Document Type
Academic Journal
Author
Guerra X; Department of Radiology, Avicenne Hospital, Assistance Publique - Hôpitaux de Paris, Bobigny, France. Electronic address: Guerra.xavier2407@gmail.com.; Rennotte S; Samovar Laboratory, Télécom SudParis, Institut Polytechnique de Paris, Evry, France.; Fetita C; Samovar Laboratory, Télécom SudParis, Institut Polytechnique de Paris, Evry, France.; Boubaya M; Clinical Research Unit, Avicenne Hospital, Assistance Publique - Hôpitaux de Paris, Sorbonne Paris-Nord, Bobigny, France.; Debray MP; Department of Radiology, Bichat-Claude Bernard Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France.; Israël-Biet D; Department of Pulmonology, Georges Pompidou European Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France; Université Paris - Cité, Paris, France.; Bernaudin JF; INSERM UMR 1272 Hypoxie & Poumon SMBH, Université Sorbonne Paris - Nord, Bobigny, France; Medicine Sorbonne Université, Paris, France.; Valeyre D; INSERM UMR 1272 Hypoxie & Poumon SMBH, Université Sorbonne Paris - Nord, Bobigny, France; Department of Pulmonology, Avicenne Hospital, Assistance Publique - Hôpitaux de Paris, Bobigny, France.; Cadranel J; Medicine Sorbonne Université, Paris, France; Department of Pulmonology, Tenon Hospital, Assistance Publique - Hôpitaux de Paris, Paris, France.; Naccache JM; Department of Pulmonology, Groupe Hospitalier Paris Saint Joseph, Paris, France.; Nunes H; INSERM UMR 1272 Hypoxie & Poumon SMBH, Université Sorbonne Paris - Nord, Bobigny, France; Department of Pulmonology, Avicenne Hospital, Assistance Publique - Hôpitaux de Paris, Bobigny, France.; Brillet PY; Department of Radiology, Avicenne Hospital, Assistance Publique - Hôpitaux de Paris, Bobigny, France; INSERM UMR 1272 Hypoxie & Poumon SMBH, Université Sorbonne Paris - Nord, Bobigny, France.
Source
Publisher: Elsevier Masson SAS Country of Publication: France NLM ID: 101746324 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2590-0412 (Electronic) Linking ISSN: 25900412 NLM ISO Abbreviation: Respir Med Res Subsets: MEDLINE
Subject
Language
English
Abstract
Background: Computational advances in artificial intelligence have led to the recent emergence of U-Net convolutional neural networks (CNNs) applied to medical imaging. Our objectives were to assess the progression of fibrotic interstitial lung disease (ILD) using routine CT scans processed by a U-Net CNN developed by our research team, and to identify a progression threshold indicative of poor prognosis.
Methods: CT scans and clinical history of 32 patients with idiopathic fibrotic ILDs were retrospectively reviewed. Successive CT scans were processed by the U-Net CNN and ILD quantification was obtained. Correlation between ILD and FVC changes was assessed. ROC curve was used to define a threshold of ILD progression rate (PR) to predict poor prognostic (mortality or lung transplantation). The PR threshold was used to compare the cohort survival with Kaplan Mayer curves and log-rank test.
Results: The follow-up was 3.8 ± 1.5 years encompassing 105 CT scans, with 3.3 ± 1.1 CT scans per patient. A significant correlation between ILD and FVC changes was obtained (p = 0.004, ρ = -0.30 [95% CI: -0.16 to -0.45]). Sixteen patients (50%) experienced unfavorable outcome including 13 deaths and 3 lung transplantations. ROC curve analysis showed an aera under curve of 0.83 (p < 0.001), with an optimal cut-off PR value of 4%/year. Patients exhibiting a PR ≥ 4%/year during the first two years had a poorer prognosis (p = 0.001).
Conclusions: Applying a U-Net CNN to routine CT scan allowed identifying patients with a rapid progression and unfavorable outcome.
Competing Interests: Declaration of Competing Interest XG, SR, CF, MB, DIBI, JFB, DV, JCj, JMN, PYB have no conflicts of interest. MPD received fees (presentations or participation in expert groups) from Boehringer-Ingelheim. HN received fees from Roche/Genentech, Boehringer-Ingelheim, Galapagos.
(Copyright © 2023 SPLF and Elsevier Masson SAS. All rights reserved.)
Methods: CT scans and clinical history of 32 patients with idiopathic fibrotic ILDs were retrospectively reviewed. Successive CT scans were processed by the U-Net CNN and ILD quantification was obtained. Correlation between ILD and FVC changes was assessed. ROC curve was used to define a threshold of ILD progression rate (PR) to predict poor prognostic (mortality or lung transplantation). The PR threshold was used to compare the cohort survival with Kaplan Mayer curves and log-rank test.
Results: The follow-up was 3.8 ± 1.5 years encompassing 105 CT scans, with 3.3 ± 1.1 CT scans per patient. A significant correlation between ILD and FVC changes was obtained (p = 0.004, ρ = -0.30 [95% CI: -0.16 to -0.45]). Sixteen patients (50%) experienced unfavorable outcome including 13 deaths and 3 lung transplantations. ROC curve analysis showed an aera under curve of 0.83 (p < 0.001), with an optimal cut-off PR value of 4%/year. Patients exhibiting a PR ≥ 4%/year during the first two years had a poorer prognosis (p = 0.001).
Conclusions: Applying a U-Net CNN to routine CT scan allowed identifying patients with a rapid progression and unfavorable outcome.
Competing Interests: Declaration of Competing Interest XG, SR, CF, MB, DIBI, JFB, DV, JCj, JMN, PYB have no conflicts of interest. MPD received fees (presentations or participation in expert groups) from Boehringer-Ingelheim. HN received fees from Roche/Genentech, Boehringer-Ingelheim, Galapagos.
(Copyright © 2023 SPLF and Elsevier Masson SAS. All rights reserved.)