A deep learning model to generate synthetic CT for prostate MR-only radiotherapy dose planning: a multicenter study.
| Autor: | Tahri S; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Texier B; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Nunes JC; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Hemon C; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Lekieffre P; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Collot E; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Chourak H; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France.; The Australian eHealth Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Health and Biosecurity, Brisbane, QLD, Australia., Le Guevelou J; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Greer P; School of Mathematical and Physical Sciences, University of Newcastle, Newcastle, NSW, Australia.; Radiation Oncology, Calvary Mater Newcastle Hospital, Newcastle, NSW, Australia., Dowling J; The Australian eHealth Research Centre, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Health and Biosecurity, Brisbane, QLD, Australia., Acosta O; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Bessieres I; Centre Georges François Leclerc, Dijon, France., Marage L; Centre Georges François Leclerc, Dijon, France., Boue-Rafle A; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., De Crevoisier R; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Lafond C; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France., Barateau A; University of Rennes, Centre de Lutte contre le Cancer (CLCC) Eugène Marquis, INSERM Laboratoire Traitement du Signal et de l'Image (LTSI) - Unité Mixte de Recherche (UMR) 1099, Rennes, France. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Frontiers in oncology [Front Oncol] 2023 Nov 28; Vol. 13, pp. 1279750. Date of Electronic Publication: 2023 Nov 28 (Print Publication: 2023). |
| DOI: | 10.3389/fonc.2023.1279750 |
| Abstrakt: | Introduction: For radiotherapy based solely on magnetic resonance imaging (MRI), generating synthetic computed tomography scans (sCT) from MRI is essential for dose calculation. The use of deep learning (DL) methods to generate sCT from MRI has shown encouraging results if the MRI images used for training the deep learning network and the MRI images for sCT generation come from the same MRI device. The objective of this study was to create and evaluate a generic DL model capable of generating sCTs from various MRI devices for prostate radiotherapy. Materials and Methods: In total, 90 patients from three centers (30 CT-MR prostate pairs/center) underwent treatment using volumetric modulated arc therapy for prostate cancer (PCa) (60 Gy in 20 fractions). T2 MRI images were acquired in addition to computed tomography (CT) images for treatment planning. The DL model was a 2D supervised conditional generative adversarial network (Pix2Pix). Patient images underwent preprocessing steps, including nonrigid registration. Seven different supervised models were trained, incorporating patients from one, two, or three centers. Each model was trained on 24 CT-MR prostate pairs. A generic model was trained using patients from all three centers. To compare sCT and CT, the mean absolute error in Hounsfield units was calculated for the entire pelvis, prostate, bladder, rectum, and bones. For dose analysis, mean dose differences of D Results: Considering the image results for the entire pelvis, when the data used for the test comes from the same center as the data used for training, the results were not significantly different from the generic model. Absolute dose differences were less than 1 Gy for the CTV D Conclusion: The accuracy of sCT, in terms of image and dose, is equivalent to whether MRI images are generated using the generic model or the monocentric model. The generic model, using only eight MRI-CT pairs per center, offers robust sCT generation, facilitating PCa MRI-only radiotherapy for routine clinical use. Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. (Copyright © 2023 Tahri, Texier, Nunes, Hemon, Lekieffre, Collot, Chourak, Le Guevelou, Greer, Dowling, Acosta, Bessieres, Marage, Boue-Rafle, De Crevoisier, Lafond and Barateau.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|