Decentralized Distributed Multi-institutional PET Image Segmentation Using a Federated Deep Learning Framework.
Journal
Clinical nuclear medicine
ISSN: 1536-0229
Titre abrégé: Clin Nucl Med
Pays: United States
ID NLM: 7611109
Informations de publication
Date de publication:
01 Jul 2022
01 Jul 2022
Historique:
pubmed:
21
4
2022
medline:
11
6
2022
entrez:
20
4
2022
Statut:
ppublish
Résumé
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. 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. 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. 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.
Identifiants
pubmed: 35442222
doi: 10.1097/RLU.0000000000004194
pii: 00003072-202207000-00006
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
606-617Informations de copyright
Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: This work was supported by the Swiss National Science Foundation under grants SNSF 320030_176052 and SNSF 320030_173091/1.
Références
Unterrainer M, Eze C, Ilhan H, et al. Recent advances of PET imaging in clinical radiation oncology. Radiat Oncol . 2020;15:88.
Alterio D, Marvaso G, Ferrari A, et al. Modern radiotherapy for head and neck cancer. Semin Oncol . 2019;46:233–245.
Chen AM, Chin R, Beron P, et al. Inadequate target volume delineation and local-regional recurrence after intensity-modulated radiotherapy for human papillomavirus-positive oropharynx cancer. Radiother Oncol . 2017;123:412–418.
Zaidi H, Vees H, Wissmeyer M. Molecular PET/CT imaging–guided radiation therapy treatment planning. Acad Radiol . 2009;16:1108–1133.
Andrearczyk V, Oreiller V, Depeursinge A. Oropharynx detection in PET-CT for tumor segmentation. Irish Mach Vis Image Proc . 2020:109–112.
Gudi S, Ghosh-Laskar S, Agarwal JP, et al. Interobserver variability in the delineation of gross tumour volume and specified organs-at-risk during IMRT for head and neck cancers and the impact of FDG-PET/CT on such variability at the primary site. J Med Imaging Radiat Sci . 2017;48:184–192.
Moe YM, Groendahl AR, Tomic O, et al. Deep learning–based auto-delineation of gross tumour volumes and involved nodes in PET/CT images of head and neck cancer patients. Eur J Nucl Med Mol Imaging . 2021;48:2782–2792.
Li L, Lu W, Tan S, et al. Variational PET/CT tumor co-segmentation integrated with PET restoration. IEEE Trans Radiat Plasma Med Sci . 2020;4:37–49.
Iantsen A, Ferreira M, Lucia F, et al. 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.
Guezennec C, Bourhis D, Orlhac F, et al. Inter-observer and segmentation method variability of textural analysis in pre-therapeutic FDG PET/CT in head and neck cancer. PLoS One . 2019;14:e0214299.
Hatt M, Le Rest CC, Tixier F, et al. Radiomics: data are also images. J Nucl Med . 2019;60:38S–44S.
Zwanenburg A. Radiomics in nuclear medicine: robustness, reproducibility, standardization, and how to avoid data analysis traps and replication crisis. Eur J Nucl Med Mol Imaging . 2019;46:2638–2655.
Bradshaw TJ, Boellaard R, Dutta J, et al. Nuclear medicine and artificial intelligence: best practices for algorithm development. J Nucl Med . 2021.
Sanaat A, Shooli H, Ferdowsi S, et al. DeepTOFSino: a deep learning model for synthesizing full-dose time-of-flight bin sinograms from their corresponding low-dose sinograms. Neuroimage . 2021;245:118697.
Sanaat A, Shiri I, Arabi H, et al. Deep learning–assisted ultra-fast/low-dose whole-body PET/CT imaging. Eur J Nucl Med Mol Imaging . 2021;48:2405–2415.
Yousefirizi F, Jha AK, Brosch-Lenz J, et al. Toward high-throughput artificial intelligence–based segmentation in oncological PET imaging. PET Clin . 2021;16:577–596.
Zhong Z, Kim Y, Zhou L, et al. 3D fully convolutional networks for co-segmentation of tumors on PET-CT images. Proc IEEE Int Symp Biomed Imaging . 2018;2018:228–231.
Czakon J, Drapejkowski F, Zurek G, et al. Machine learning methods for accurate delineation of tumors in PET images. arXiv:161009493. https://doi.org/10.48550/arXiv.1610.09493. 2016.
Hatt M, Laurent B, Ouahabi A, et al. The first MICCAI challenge on PET tumor segmentation. Med Image Anal . 2018;44:177–195.
Andrearczyk V, Oreiller V, Jreige M, et al. Overview of the HECKTOR challenge at MICCAI 2020: automatic head and neck tumor segmentation in PET/CT. In: 3D Head and Neck Tumor Segmentation in PET/CT Challenge . Lima, Peru: Springer; 2020:1–21.
Chen L, Shen C, Zhou Z, et al. Automatic PET cervical tumor segmentation by combining deep learning and anatomic prior. Phys Med Biol . 2019;64:085019.
Shiri I, Arabi H, Sanaat A, et al. Fully automated gross tumor volume delineation from PET in head and neck cancer using deep learning algorithms. Clin Nucl Med . 2021;46:872–883.
Rieke N, Hancox J, Li W, et al. The future of digital health with federated learning. NPJ Digit Med . 2020;3:119.
Kaissis GA, Makowski MR, Rückert D, et al. Secure, privacy-preserving and federated machine learning in medical imaging. Nat Mach Intell . 2020;2:305–311.
Kirienko M, Sollini M, Ninatti G, et al. Distributed learning: a reliable privacy-preserving strategy to change multicenter collaborations using AI. Eur J Nucl Med Mol Imaging . 2021;48:3791–3804.
Wei K, Li J, Ding M, et al. Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans Inf Forensics Secur . 2020;15:3454–3469.
Mothukuri V, Parizi RM, Pouriyeh S, et al. A survey on security and privacy of federated learning. Future Gener Comput Syst . 2021;115:619–640.
Lu Y, Huang X, Dai Y, et al. Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Trans Industr Inform . 2019;16:4177–4186.
Bonawitz K, Eichner H, Grieskamp W, et al. Towards federated learning at scale: system design. arXiv preprint arXiv:190201046. https://doi.org/10.48550/arXiv.1902.01046. 2019.
Li Q, Wen Z, Wu Z, et al. A survey on federated learning systems: vision, hype and reality for data privacy and protection. arXiv preprint arXiv:190709693. https://doi.org/10.1109/TKDE.2021.3124599. 2019.
Li T, Sahu AK, Talwalkar A, et al. Federated learning: challenges, methods, and future directions. IEEE Signal Proc Mag . 2020;37:50–60.
Amiri MM, Gündüz D. Federated learning over wireless fading channels. IEEE T Wirel Commun . 2020;19:3546–3557.
McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data. In: Aarti S, Jerry Z, eds. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics . Fort Lauderdale, FL: PMLR; 2017:1273–1282.
Roth HR, Chang K, Singh P, et al. Federated learning for breast density classification: a real-world implementation. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning . Lima, Peru: Springer; 2020:181–191.
Dayan I, Roth HR, Zhong A, et al. Federated learning for predicting clinical outcomes in patients with COVID-19. Nat Med . 2021;27:1735–1743.
Li W, Milletarì F, Xu D, et al. Privacy-preserving federated brain tumour segmentation. In: International Workshop on Machine Learning in Medical Imaging . Shenzhen, China: Springer; 2019:133–141.
Xia Y, Yang D, Li W, et al. Auto-FedAvg: learnable federated averaging for multi-institutional medical image segmentation. arXiv preprint arXiv:210410195. https://doi.org/10.48550/arXiv.2104.10195. 2021.
Vallières M, Kay-Rivest E, Perrin LJ, et al. Radiomics strategies for risk assessment of tumour failure in head-and-neck cancer. Sci Rep . 2017;7:10117.
Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging . 2013;26:1045–1057.
Fedorov A, Clunie D, Ulrich E, et al. DICOM for quantitative imaging biomarker development: a standards based approach to sharing clinical data and structured PET/CT analysis results in head and neck cancer research. PeerJ . 2016;4:e2057.
Grossberg AJ, Mohamed ASR, Elhalawani H, et al. Imaging and clinical data archive for head and neck squamous cell carcinoma patients treated with radiotherapy. Sci Data . 2018;5:180173.
MICCAI/M.D. Anderson Cancer Center Head and Neck Quantitative Imaging Working Group. Matched computed tomography segmentation and demographic data for oropharyngeal cancer radiomics challenges. Sci Data . 2017;4:170077.
Zuley ML, Jarosz R, Kirk S, et al. Radiology data from the Cancer Genome Atlas Head-Neck Squamous Cell Carcinoma [TCGA-HNSC] collection. Cancer Imaging Arch . 2016;10:K9.
Konečný J, McMahan HB, Yu FX, et al. Federated learning: strategies for improving communication efficiency. arXiv preprint arXiv:161005492. 2016.
Singh A, Vepakomma P, Gupta O, et al. Detailed comparison of communication efficiency of split learning and federated learning. arXiv preprint arXiv:190909145. https://doi.org/10.48550/arXiv.1909.09145. 2019.
Luping W, Wei W, Bo L. CMFL: mitigating communication overhead for federated learning. In: 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS) , Dallas, TX: IEEE; 2019:954–964.
Zhang M, Qu L, Singh P, et al. SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging. arXiv preprint arXiv:210702375. https://doi.org/10.48550/arXiv.2107.02375. 2021.
Stripelis D, Saleem H, Ghai T, et al. Secure neuroimaging analysis using federated learning with homomorphic encryption. In: 17th International Symposium on Medical Information Processing and Analysis, Campinas, Brazil: SPIE; 2021:351–359.
Qu L, Zhou Y, Liang PP, et al. Rethinking architecture design for tackling data heterogeneity in federated learning. arXiv preprint arXiv:210606047. https://doi.org/10.48550/arXiv.2106.06047. 2021.
Liu Q, Yang H, Dou Q, et al. Federated semi-supervised medical image classification via inter-client relation matching. arXiv preprint arXiv:210608600. https://doi.org/10.48550/arXiv.2106.08600 . 2021.
Chakravarty A, Kar A, Sethuraman R, et al. Federated learning for site aware chest radiograph screening. In: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), Nice, France: IEEE; 2021:1077–1081.
Linardos A, Kushibar K, Walsh S, et al. Federated learning for multi-center imaging diagnostics: a study in cardiovascular disease. arXiv preprint arXiv:210703901. 2021.
Feki I, Ammar S, Kessentini Y, et al. Federated learning for COVID-19 screening from chest x-ray images. Appl Soft Comput . 2021;106:107330.
Alom MZ, Yakopcic C, Hasan M, et al. Recurrent residual U-Net for medical image segmentation. J Med Imaging (Bellingham) . 2019;6:014006.
Ashrafinia S. Quantitative Nuclear Medicine Imaging Using Advanced Image Reconstruction and Radiomics . Baltimore, MD: The Johns Hopkins University; 2019.
Zwanenburg A, Vallières M, Abdalah MA, et al. The Image Biomarker Standardization Initiative: standardized quantitative Radiomics for high-throughput image-based phenotyping. Radiology . 2020;295:328–338.
Foster B, Bagci U, Mansoor A, et al. A review on segmentation of positron emission tomography images. Comput Biol Med . 2014;50:76–96.
Hatt M, Lee JA, Schmidtlein CR, et al. Classification and evaluation strategies of auto-segmentation approaches for PET: report of AAPM task group no. 211. Med Phys . 2017;44:e1–e42.
Drever L, Roa W, McEwan A, et al. Iterative threshold segmentation for PET target volume delineation. Med Phys . 2007;34:1253–1265.
Hatt M, Cheze le Rest C, Turzo A, et al. A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET. IEEE Trans Med Imaging . 2009;28:881–893.
Brambilla M, Matheoud R, Secco C, et al. Threshold segmentation for PET target volume delineation in radiation treatment planning: the role of target-to-background ratio and target size. Med Phys . 2008;35:1207–1213.
Zaidi H, Abdoli M, Fuentes CL, et al. Comparative methods for PET image segmentation in pharyngolaryngeal squamous cell carcinoma. Eur J Nucl Med Mol Imaging . 2012;39:881–891.
Huang B, Chen Z, Wu PM, et al. Fully automated delineation of gross tumor volume for head and neck Cancer on PET-CT using deep Learning: a dual-center study. Contrast Media Mol Imaging . 2018;2018:8923028.
Andrearczyk V, Oreiller V, Vallières M, et al. Automatic segmentation of head and neck tumors and nodal metastases in PET-CT scans. In: Proceedings of Machine Learning Research . Montreal, QC, Canada: PMLR; 2020:33–43.
Leung KH, Marashdeh W, Wray R, et al. A physics-guided modular deep-learning based automated framework for tumor segmentation in PET. Phys Med Biol . 2020;65:245032.
Gawali M, Arvind C, Suryavanshi S, et al. Comparison of privacy-preserving distributed deep learning methods in healthcare. In: Annual Conference on Medical Image Understanding and Analysis . Oxford, United Kingdom: Springer; 2021:457–471.
Lee H, Chai YJ, Joo H, et al. Federated Learning for thyroid ultrasound image analysis to protect personal information: validation study in a real health care environment. JMIR Med Inform . 2021;9:e25869.
Li X, Gu Y, Dvornek N, et al. Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE results. Med Image Anal . 2020;65:101765.
Melis L, Song C, De Cristofaro E, et al. Exploiting unintended feature leakage in collaborative learning. In: 2019 IEEE Symposium on Security and Privacy (SP) . San Francisco, CA: IEEE; 2019:691–706.
Carlini N, Liu C, Erlingsson Ú, et al. The secret sharer: evaluating and testing unintended memorization in neural networks. In: 28th Security Symposium (Security 19) . Santa Clara, CA; USENIX; 2019:267–284.
Duchi JC, Jordan MI, Wainwright MJ. Privacy aware learning. Journal of the ACM (JACM) . 2014;61:1–57.
Shokri R, Stronati M, Song C, et al. Membership inference attacks against machine learning models. In: 2017 IEEE Symposium on Security and Privacy (SP) . San Jose, CA: IEEE; 2017:3–18.
Fredrikson M, Jha S, Ristenpart T. Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC conference on computer and communications security . 2015:1322–1333.
Malekzadeh M, Hasircioglu B, Mital N, et al. Dopamine: differentially private federated learning on medical data. The Second AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI-21) . arXiv e-prints, pp. arXiv–2101, 2021.
Pfohl SR, Dai AM, Heller K. Federated and differentially private learning for electronic health records. arXiv preprint arXiv:191105861. https://doi.org/10.48550/arXiv.1911.05861 . 2019.
Chen X, Liu C, Li B, et al. Targeted backdoor attacks on deep learning systems using data poisoning. arXiv preprint arXiv:171205526. https://doi.org/10.48550/arXiv.1712.05526. 2017.
Li B, Wang Y, Singh A, et al. Data poisoning attacks on factorization-based collaborative filtering. Adv Neural Inform Proc Syst . 2016;29:1885–1893.
Xie C, Huang K, Chen PY, et al. DBA: distributed backdoor attacks against federated learning. In: International Conference on Learning Representations. Addis Ababa, Ethiopia: ICLR; 2019.