1
|
Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework. Clin Nucl Med 2022; 47:606-617. [PMID: 35442222 DOI: 10.1097/rlu.0000000000004194] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
PURPOSE The generalizability and trustworthiness of deep learning (DL)-based algorithms depend on the size and heterogeneity of training datasets. However, because of patient privacy concerns and ethical and legal issues, sharing medical images between different centers is restricted. Our objective is to build a federated DL-based framework for PET image segmentation utilizing a multicentric dataset and to compare its performance with the centralized DL approach. METHODS PET images from 405 head and neck cancer patients from 9 different centers formed the basis of this study. All tumors were segmented manually. PET images converted to SUV maps were resampled to isotropic voxels (3 × 3 × 3 mm3) and then normalized. PET image subvolumes (12 × 12 × 12 cm3) consisting of whole tumors and background were analyzed. Data from each center were divided into train/validation (80% of patients) and test sets (20% of patients). The modified R2U-Net was used as core DL model. A parallel federated DL model was developed and compared with the centralized approach where the data sets are pooled to one server. Segmentation metrics, including Dice similarity and Jaccard coefficients, percent relative errors (RE%) of SUVpeak, SUVmean, SUVmedian, SUVmax, metabolic tumor volume, and total lesion glycolysis were computed and compared with manual delineations. RESULTS The performance of the centralized versus federated DL methods was nearly identical for segmentation metrics: Dice (0.84 ± 0.06 vs 0.84 ± 0.05) and Jaccard (0.73 ± 0.08 vs 0.73 ± 0.07). For quantitative PET parameters, we obtained comparable RE% for SUVmean (6.43% ± 4.72% vs 6.61% ± 5.42%), metabolic tumor volume (12.2% ± 16.2% vs 12.1% ± 15.89%), and total lesion glycolysis (6.93% ± 9.6% vs 7.07% ± 9.85%) and negligible RE% for SUVmax and SUVpeak. No significant differences in performance (P > 0.05) between the 2 frameworks (centralized vs federated) were observed. CONCLUSION The developed federated DL model achieved comparable quantitative performance with respect to the centralized DL model. Federated DL models could provide robust and generalizable segmentation, while addressing patient privacy and legal and ethical issues in clinical data sharing.
Collapse
|
2
|
Pretherapy 18F-fluorodeoxyglucose positron emission tomography/computed tomography robust radiomic features predict overall survival in non-small cell lung cancer. Nucl Med Commun 2022; 43:540-548. [PMID: 35190518 DOI: 10.1097/mnm.0000000000001541] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
Abstract
OBJECTIVE To extract robust radiomic features from staging positron emission tomography/computed tomography (18F- fluroodeoxyglucose PET/CT) in patients with non-small cell lung cancer from different segmentation methods and to assess their association with 2-year overall survival. METHODS Eighty-one patients with stage I-IV non-small cell lung cancer were included. All patients underwent a pretherapy 18F-FDG PET/CT. Primary tumors were delineated using four different segmentation methods: method 1, manual; method 2: manual with peripheral 1 mm erosion; method 3: absolute threshold at standardized uptake value (SUV) 2.5; and method 4: relative threshold at 40% SUVmax. Radiomic features from each method were extracted using Image Biomarker Standardization Initiative-compliant process. The study cohort was divided into two groups (exploratory and testing) in a ratio of 1:2 (n = 25 and n = 56, respectively). Exploratory cohort was used to identify robust radiomic features, defined as having a minimum concordance correlation coefficient ≥0.75 among all the 4-segmentation methods. The resulting texture features were evaluated for association with 2-year overall survival in the testing cohort (n = 56). All patients in the testing cohort had a follow-up for 2 years from the date of staging 18F-FDG PET/CT scan or till death. Cox proportional hazard models were used to evaluate the independent prognostic factors. RESULTS Exploratory and validation cohorts were equivalent regarding their basic characteristics (age, sex, and tumor stage). Ten radiomic features were deemed robust to the described four segmentation methods: SUV SD, SUVmax, SUVQ3, SUVpeak in 0.5 ml, total lesion glycolysis, histogram entropy log 2, histogram entropy log 10, histogram energy uniformity, gray level run length matrix-gray level non-uniformity, and gray level zone length matrix-gray level non-uniformity. At the end of 2-year follow-up, 41 patients were dead and 15 were still alive (overall survival = 26.8%; median survival = 14.7 months, 95% confidence interval: 10.2-19.2 months). Three texture features, regardless the segmentation method, were associated with 2-year overall survival: total lesion glycolysis, gray level run length matrix_gray level non-uniformity, and gray level zone length matrix_run-length non-uniformity. In the final Cox-regression model: total lesion glycolysis, and gray level zone length matrix_gray level non-uniformity were independent prognostic factors. The quartiles from the two features were combined with clinical staging in a prognostic model that allowed better risk stratification of patients for overall survival. CONCLUSION Ten radiomic features were robust to segmentation methods and two of them (total lesion glycolysis and gray level zone length matrix_gray level non-uniformity) were independently associated with 2-year overall survival. Together with the clinical staging, these features could be utilized towards improved risk stratification of lung cancer patients.
Collapse
|
3
|
Vaz SC, Adam JA, Bolton RCD, Vera P, van Elmpt W, Herrmann K, Hicks RJ, Lievens Y, Santos A, Schöder H, Dubray B, Visvikis D, Troost EGC, de Geus-Oei LF. Joint EANM/SNMMI/ESTRO practice recommendations for the use of 2-[ 18F]FDG PET/CT external beam radiation treatment planning in lung cancer V1.0. Eur J Nucl Med Mol Imaging 2022; 49:1386-1406. [PMID: 35022844 PMCID: PMC8921015 DOI: 10.1007/s00259-021-05624-5] [Citation(s) in RCA: 18] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/05/2021] [Accepted: 11/15/2021] [Indexed: 12/16/2022]
Abstract
Purpose 2-[18F]FDG
PET/CT is of utmost importance for radiation treatment (RT) planning and response monitoring in lung cancer patients, in both non-small and small cell lung cancer (NSCLC and SCLC). This topic has been addressed in guidelines composed by experts within the field of radiation oncology. However, up to present, there is no procedural guideline on this subject, with involvement of the nuclear medicine societies. Methods A literature review was performed, followed by a discussion between a multidisciplinary team of experts in the different fields involved in the RT planning of lung cancer, in order to guide clinical management. The project was led by experts of the two nuclear medicine societies (EANM and SNMMI) and radiation oncology (ESTRO). Results and conclusion This guideline results from a joint and dynamic collaboration between the relevant disciplines for this topic. It provides a worldwide, state of the art, and multidisciplinary guide to 2-[18F]FDG PET/CT RT planning in NSCLC and SCLC. These practical recommendations describe applicable updates for existing clinical practices, highlight potential flaws, and provide solutions to overcome these as well. Finally, the recent developments considered for future application are also reviewed.
Collapse
Affiliation(s)
- Sofia C Vaz
- Nuclear Medicine Radiopharmacology, Champalimaud Centre for the Unkown, Champalimaud Foundation, Lisbon, Portugal.,Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| | - Judit A Adam
- Department of Radiology and Nuclear Medicine, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | - Roberto C Delgado Bolton
- Department of Diagnostic Imaging (Radiology) and Nuclear Medicine, University Hospital San Pedro and Centre for Biomedical Research of La Rioja (CIBIR), Logroño (La Rioja), Spain
| | - Pierre Vera
- Henri Becquerel Cancer Center, QuantIF-LITIS EA 4108, Université de Rouen, Rouen, France
| | - Wouter van Elmpt
- Department of Radiation Oncology (MAASTRO), GROW - School for Oncology, Maastricht University Medical Centre, Maastricht, The Netherlands
| | - Ken Herrmann
- Department of Nuclear Medicine, University of Duisburg-Essen and German Cancer Consortium (DKTK)-University Hospital Essen, Essen, Germany.
| | - Rodney J Hicks
- The Sir Peter MacCallum Department of Oncology, University of Melbourne, Melbourne, Australia
| | - Yolande Lievens
- Radiation Oncology Department, Ghent University Hospital and Ghent University, Ghent, Belgium
| | - Andrea Santos
- Nuclear Medicine Department, CUF Descobertas Hospital, Lisbon, Portugal
| | - Heiko Schöder
- Molecular Imaging and Therapy Service, Memorial Sloan Kettering Cancer Center, New York, USA
| | - Bernard Dubray
- Department of Radiotherapy and Medical Physics, Centre Henri Becquerel, Rouen, France.,QuantIF-LITIS EA4108, University of Rouen, Rouen, France
| | | | - Esther G C Troost
- Department of Radiotherapy and Radiation Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany.,OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden-Rossendorf, Dresden, Germany.,Helmholtz-Zentrum Dresden - Rossendorf, Institute of Radiooncology - OncoRay, Dresden, Germany.,National Center for Tumor Diseases (NCT), Partner Site Dresden, Germany: German Cancer Research Center (DKFZ), Heidelberg, Germany; Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany; Helmholtz Association / Helmholtz-Zentrum Dresden - Rossendorf (HZDR), Dresden, Germany.,German Cancer Consortium (DKTK), Partner Site Dresden, and German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Lioe-Fee de Geus-Oei
- Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
4
|
Iantsen A, Ferreira M, Lucia F, Jaouen V, Reinhold C, Bonaffini P, Alfieri J, Rovira R, Masson I, Robin P, Mervoyer A, Rousseau C, Kridelka F, Decuypere M, Lovinfosse P, Pradier O, Hustinx R, Schick U, Visvikis D, Hatt M. Convolutional neural networks for PET functional volume fully automatic segmentation: development and validation in a multi-center setting. Eur J Nucl Med Mol Imaging 2021; 48:3444-3456. [PMID: 33772335 PMCID: PMC8440243 DOI: 10.1007/s00259-021-05244-z] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2020] [Accepted: 02/07/2021] [Indexed: 11/12/2022]
Abstract
Purpose In this work, we addressed fully automatic determination of tumor functional uptake from positron emission tomography (PET) images without relying on other image modalities or additional prior constraints, in the context of multicenter images with heterogeneous characteristics. Methods In cervical cancer, an additional challenge is the location of the tumor uptake near or even stuck to the bladder. PET datasets of 232 patients from five institutions were exploited. To avoid unreliable manual delineations, the ground truth was generated with a semi-automated approach: a volume containing the tumor and excluding the bladder was first manually determined, then a well-validated, semi-automated approach relying on the Fuzzy locally Adaptive Bayesian (FLAB) algorithm was applied to generate the ground truth. Our model built on the U-Net architecture incorporates residual blocks with concurrent spatial squeeze and excitation modules, as well as learnable non-linear downsampling and upsampling blocks. Experiments relied on cross-validation (four institutions for training and validation, and the fifth for testing). Results The model achieved good Dice similarity coefficient (DSC) with little variability across institutions (0.80 ± 0.03), with higher recall (0.90 ± 0.05) than precision (0.75 ± 0.05) and improved results over the standard U-Net (DSC 0.77 ± 0.05, recall 0.87 ± 0.02, precision 0.74 ± 0.08). Both vastly outperformed a fixed threshold at 40% of SUVmax (DSC 0.33 ± 0.15, recall 0.52 ± 0.17, precision 0.30 ± 0.16). In all cases, the model could determine the tumor uptake without including the bladder. Neither shape priors nor anatomical information was required to achieve efficient training. Conclusion The proposed method could facilitate the deployment of a fully automated radiomics pipeline in such a challenging multicenter context. Supplementary Information The online version contains supplementary material available at 10.1007/s00259-021-05244-z.
Collapse
Affiliation(s)
- Andrei Iantsen
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France.
| | - Marta Ferreira
- GIGA-CRC in vivo Imaging, University of Liège, Liège, Belgium
| | - Francois Lucia
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Vincent Jaouen
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | - Caroline Reinhold
- Department of Radiology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Pietro Bonaffini
- Department of Radiology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Joanne Alfieri
- Department of Radiation Oncology, McGill University Health Centre (MUHC), Montreal, Canada
| | - Ramon Rovira
- Gynecology Oncology and Laparoscopy Department, Hospital de la Santa Creu i Sant Pau, Barcelona, Spain
| | - Ingrid Masson
- Department of Radiation Oncology, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Philippe Robin
- Nuclear Medicine Department, University Hospital, Brest, France
| | - Augustin Mervoyer
- Department of Radiation Oncology, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Caroline Rousseau
- Nuclear Medicine Department, Institut de Cancérologie de l'Ouest (ICO), Nantes, France
| | - Frédéric Kridelka
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Marjolein Decuypere
- Division of Oncological Gynecology, University Hospital of Liège, Liège, Belgium
| | - Pierre Lovinfosse
- Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège, Liège, Belgium
| | | | - Roland Hustinx
- GIGA-CRC in vivo Imaging, University of Liège, Liège, Belgium
| | - Ulrike Schick
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| | | | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, University Brest, Brest, France
| |
Collapse
|
5
|
Tixier F, Cheze-le-Rest C, Schick U, Simon B, Dufour X, Key S, Pradier O, Aubry M, Hatt M, Corcos L, Visvikis D. Transcriptomics in cancer revealed by Positron Emission Tomography radiomics. Sci Rep 2020; 10:5660. [PMID: 32221360 PMCID: PMC7101432 DOI: 10.1038/s41598-020-62414-z] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2019] [Accepted: 03/13/2020] [Indexed: 11/09/2022] Open
Abstract
Metabolic images from Positron Emission Tomography (PET) are used routinely for diagnosis, follow-up or treatment planning purposes of cancer patients. In this study we aimed at determining if radiomic features extracted from 18F-Fluoro Deoxy Glucose (FDG) PET images could mirror tumor transcriptomics. In this study we analyzed 45 patients with locally advanced head and neck cancer (H&N) that underwent FDG-PET scans at the time of diagnosis and transcriptome analysis using RNAs from both cancer and healthy tissues on microarrays. Association between PET radiomics and transcriptomics was carried out with the Genomica software and a functional annotation was used to associate PET radiomics, gene expression and altered biological pathways. We identified relationships between PET radiomics and genes involved in cell-cycle, disease, DNA repair, extracellular matrix organization, immune system, metabolism or signal transduction pathways, according to the Reactome classification. Our results suggest that these FDG PET radiomic features could be used to infer tissue gene expression and cellular pathway activity in H&N cancers. These observations strengthen the value of radiomics as a promising approach to personalize treatments through targeting tumor-specific molecular processes.
Collapse
Affiliation(s)
- Florent Tixier
- Department of Nuclear Medicine, Poitiers University Hospital, Poitiers, France.
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France.
| | - Catherine Cheze-le-Rest
- Department of Nuclear Medicine, Poitiers University Hospital, Poitiers, France
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Ulrike Schick
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
- Radiation Oncology Department, University Hospital, Brest, France
| | - Brigitte Simon
- INSERM, UMR 1078, Université de Brest, Génétique Génomique Fonctionnelle et Biotechnologies, Etablissement Français du Sang, Brest, France
| | - Xavier Dufour
- Head and Neck Department, Poitiers University Hospital, Poitiers, France
| | - Stéphane Key
- Radiation Oncology Department, University Hospital, Brest, France
| | - Olivier Pradier
- Radiation Oncology Department, University Hospital, Brest, France
| | - Marc Aubry
- CNRS, UMR 6290, IGDR, Université de Rennes 1, Rennes, France
| | - Mathieu Hatt
- LaTIM, INSERM, UMR 1101, Univ Brest, Brest, France
| | - Laurent Corcos
- INSERM, UMR 1078, Université de Brest, Génétique Génomique Fonctionnelle et Biotechnologies, Etablissement Français du Sang, Brest, France
| | | |
Collapse
|