Federated Learning Enables Big Data for Rare Cancer Boundary Detection

Pati, Sarthak; Baid, Ujjwal; Edwards, Brandon L.; Sheller, Micah J.; Wang, Shih-Han; Reina, Giulio; Foley, Patrick; Gruzdev, A. D.; Karkada, Deepthi; Davatzikos, Christos; Sako, Chiharu; Ghodasara, Satyam; Bilello, Michel; Mohan, Suyash; Vollmuth, Philipp; Brugnara, Gianluca; Preetha, Chandrakanth Jayachandran; Sahm, Felix; Maier‐Hein, Klaus H.; Zenk, Maximilian; Bendszus, Martin; Wick, Wolfgang; Calabrese, Evan; Rudie, Jeffrey D.; Villanueva‐Meyer, Javier; Cha, Soonmee; Ingalhalikar, Madhura; Jadhav, Manali; Pandey, Umang; Saini, Jitender; Garrett, J. R.; Larson, Matthew; Jeraj, Robert; Currie, Stuart; Frood, Russell; Fatania, Kavi; Huang, Raymond Y.; Chang, Ken; Quintero, Carmen Balaña; Capellades, Jaume; Puig, Josep; Trenkler, Johannes; Pichler, Josef; Necker, Georg; Haunschmidt, Andreas; Meckel, Stephan; Shukla, Geeta; Liem, Spencer; Alexander, Gregory S.; Lombardo, Joseph S.; Palmer, Joshua D.; Flanders, Adam E.; Dicker, Adam P.; Sair, Haris I.; Jones, Craig K.; Venkataraman, Archana; Jiang, Meirui; So, Tiffany Y.; Chen, Cheng; Heng, Pheng‐Ann; Dou, Qi; Kozubek, Michal; Lux, Filip; Michálek, Jan; Matula, Petr; Keřkovský, Miloš; Kopřivová, Tereza; Dostál, Marek; Vybíhal, Václav; Vogelbaum, Michael A.; Mitchell, JJ; Farinhas, Joaquim M.; Maldjian, Joseph A.; Yogananda, Chandan Ganesh Bangalore; Pinho, Marco C.; Reddy, D V S; Holcomb, James F.; Wagner, Benjamin; Ellingson, Benjamin M.; Cloughesy, Timothy F.; Raymond, Catalina; Oughourlian, Talia; Hagiwara, Akifumi; Wang, Chencai; To, Minh‐Son; Bhardwaj, Sargam; Chong, Chee; Agzarian, Marc; Falcão, Alexandre X.; Martins, Samuel Botter; Teixeira, Bernardo Corrêa de Almeida; Sprenger, F; Menotti, David; Lucio, Diego Rafael; LaMontagne, Pamela; Marcus, Daniel S.; Wiestler, Benedikt; Wiestler, Benedikt; Ezhov, Ivan; Metz, Marie; Jain, Rajan; Lee, Matthew; Lui, Yvonne W.; McKinley, Richard L.; Slotboom, Johannes; Radojewski, Piotr; Meier, Raphaël; Wiest, Roland; Murcia, Derrick; Fu, Eric; Haas, Rourke; Thompson, John F.; Ormond, D. Ryan; Badve, Chaitra; Sloan, Andrew E.; Vadmal, Vachan; Waite, Kristin; Colen, Rivka R.; Pei, Linmin; Akçakaya, Murat; Srinivasan, Ashok; Bapuraj, J. R.; Rao, Arvind; Wang, Nicholas; Ota, Yutaka; Moritani, Toshio; Türk, Sevcan; Lee, Joon Sang; Prabhudesai, Snehal; Morón, Fanny; Mandel, Jacob; Kamnitsas, Konstantinos; Glocker, Ben; Dixon, Luke; Williams, M. P.; Zampakis, Peter; Panagiotopoulos, Vasileios; Tsiganos, Panagiotis; Alexiou, Sotiris; Haliassos, Ilias; Zacharaki, Evangelia I.; Μουστάκας, Κωνσταντίνος; Kalogeropoulou, Christina; Kardamakis, Dimitrios; Choi, Yoon Seong; Lee, Seung Koo; Chang, Jong Hee; Ahn, Sung Soo; Luo, Bing; Poisson, Laila; Wen, Ning; Tiwari, Pallavi; Verma, Ruchika; Bareja, Rohan; Yadav, Ipsa; Chen, Jonathan; Kumar, Neeraj; Smits, Marion; Voort, Sebastian R. van der; Alafandi, Ahmed; Incekara, Fatih; Wijnenga, Maarten M.J.; Kapsas, Georgios; Gahrmann, Renske; Schouten, Joost W.; Dubbink, Hendrikus J.; Vincent, Arnaud J P E; Bent, Martin J. van den; French, Pim J.; Klein, Stefan; Yuan, Yading; Sharma, Sunil; Tseng, Tzu-Chi; Adabi, Saba; Niclou, Simone P.; Keunen, Olivier; Hau, Ann-Christin; Vallières, Martin; Fortin, David; Lepage, Martín; Landman, Bennett A.; Ramadass, Karthik; Xu, Kun; Chotai, Silky; Chambless, Lola B.; Mistry, Akshitkumar M.; Thompson, Reid C.; Gusev, Yuriy; Bhuvaneshwar, Krithika; Sayah, Anousheh; Bencheqroun, Camelia; Belouali, Anas; Madhavan, Subha; Booth, Thomas C.; Chelliah, Alysha; Modat, Marc; Shuaib, Haris; Dragos, Carmen; Abayazeed, Aly; Kolodziej, Kenneth; Hill, Michael D.; Abbassy, Ahmed; Gamal, Shady; Mekhaimar, Mahmoud; Qayati, Mohamed; Reyes, Mauricio; Park, Ji Eun; Yun, Jihye; Kim, Ho Sung; Mahajan, Abhishek; Muzi, Mark; Benson, S.; Beets‐Tan, Regina G. H.; Teuwen, Jonas; Herrera-Trujillo, Alejandro; Trujillo, María; Escobar, William; Abello, Ana Lorena; Bernal, José; Gómez, Jhon; Choi, Joseph; Baek, Stephen; Kim, Yusung; Ismael, Heba; Allen, Bryan G.; Buatti, John M.; Kotrotsou, Aikaterini; Li, Hongwei; Weiß, Tobias; Weller, Michael; Bink, Andrea; Pouymayou, Bertrand; Shaykh, Hassan F; Saltz, Joel; Prasanna, Prateek; Shrestha, Sampurna; Mani, Kartik; Payne, D. J.; Kurç, Tahsin; Peláez, Enrique; Franco-Maldonado, Heydy; Loayza, Francis R.; Quevedo, Sebastian; Guevara, Pamela; Torche, Esteban; Mendoza, Cristóbal; Vera, Franco; Ríos, Elvis; López, Eduardo; Velastín, Sergio A.; Ogbole, Godwin; Oyekunle, Dotun; Odafe-Oyibotha, Olubunmi; Osobu, Babatunde; Shu'aibu, Mustapha; Dorcas, Adeleye; Soneye, Mayowa; Dako, Farouk; Simpson, Amber L.; Hamghalam, Mohammad; Peoples, Jacob; Hu, Ricky; Tran, Anh; Cutler, Danielle; Moraes, Fábio Ynoe de; Boss, Michael A.; Gimpel, James G.; Veettil, Deepak Kattil; Schmidt, Kendall; Bialecki, Brian; Marella, Sailaja; Price, Cynthia; Cimino, Lisa; Apgar, Charles; Shah, Prashant; Menze, Bjoern; Barnholtz‐Sloan, Jill S.; Martín, José; Bakas, Spyridon

doi:10.48550/arxiv.2204.10836

Cited by 3 publications

(3 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, various studies have been conducted to address the problem of domain shift in medical images. Domain adaptation (DA), fine-tuning, and federated learning [44][45][46] are effective solutions to the domain shift in our study.…”

Section: Discussionmentioning

confidence: 99%

Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

et al. 2022

View full text Add to dashboard Cite

Background Although cervical lymph node metastasis is an important prognostic factor for oral cancer, occult metastases remain undetected even by diagnostic imaging. We developed a learning model to predict lymph node metastasis in resected specimens of tongue cancer by classifying the level of immunohistochemical (IHC) staining for angiogenesis‐ and lymphangiogenesis‐related proteins using a multilayer perceptron neural network (MNN). Methods We obtained a dataset of 76 patients with squamous cell carcinoma of the tongue who had undergone primary tumor resection. All 76 specimens were IHC stained for the six types shown above (VEGF‐C, VEGF‐D, NRP1, NRP2, CCR7, and SEMA3E) and 456 slides were prepared. We scored the staining levels visually on all slides. We created virtual slides (4560 images) and the accuracy of the MNN model was verified by comparing it with a hue–saturation (HS) histogram, which quantifies the manually determined visual information. Results The accuracy of the training model with the MNN was 98.6%, and when the training image was converted to grayscale, the accuracy decreased to 52.9%. This indicates that our MNN adequately evaluates the level of staining rather than the morphological features of the IHC images. Multivariate analysis revealed that CCR7 staining level and T classification were independent factors associated with the presence of cervical lymph node metastasis in both HS histograms and MNN. Conclusion These results suggest that IHC assessment using MNN may be useful for identifying lymph node metastasis in patients with tongue cancer.

show abstract

Section: Discussionmentioning

confidence: 99%

Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We deployed Intel Federated Learning (OpenFL) [18] framework for training brain tumor segmentation model -an encoder-decoder 3D U-shape type of convolutional neural network provided by FeTS2022 challenge -using the data-private collaborative learning paradigm of FL [16]. OpenFL considers two main components: 1) the collaborator which uses a local dataset to train the global model and 2) the aggregator which receives model updates from each collaborator and fuses them to form the global model.…”

Section: Fets 2022 Challengementioning

confidence: 99%

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

Khan¹,

Azeem²,

Alhoniemi³

et al. 2023

Preprint

View full text Add to dashboard Cite

In federated learning (FL), the global model at the server requires an efficient mechanism for weight aggregation and a systematic strategy for collaboration selection to manage and optimize communication payload. We introduce a practical and cost-efficient method for regularized weight aggregation and propose a laborsaving technique to select collaborators per round. We illustrate the performance of our method, regularized similarity weight aggregation (RegSimAgg), on the Federated Tumor Segmentation (FeTS) 2022 challenge's federated training (weight aggregation) problem. Our scalable approach is principled, frugal, and suitable for heterogeneous non-IID collaborators. Using FeTS2021 evaluation criterion, our proposed algorithm RegSimAgg stands at 3rd position in the final rankings of FeTS2022 challenge in the weight aggregation task. Our solution is open sourced at: https://github.com/ dskhanirfan/FeTS2022

show abstract

“…The Federated Tumor Segmentation (FeTS) initiative, led by the University of Pennsylvania, describes an ongoing development of the largest international federation of healthcare institutions aiming at gaining knowledge for tumor boundary detection from ample and diverse patient populations without sharing any patient data (Baid et al 2021, Pati et al 2022a. To facilitate this initiative, a dedicated open-source platform with a user-friendly graphical user interface was developed (Pati et al 2022b).…”

Section: The Real-world Federated Tumor Segmentation Initiativementioning

confidence: 99%

OpenFL: the open federated learning library

Foley¹,

Sheller²,

Pati³

et al. 2022

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective: Federated learning (FL) is a computational paradigm that enables organizations to collaborate on machine learning (ML) and deep learning (DL) projects without sharing sensitive data, such as patient records, financial data, or classified secrets. Approach: Open Federated Learning (OpenFL) framework is an open-source python-based tool for training ML/DL algorithms using the data-private collaborative learning paradigm of FL, irrespective to the use case. OpenFL works with training pipelines built with both TensorFlow and PyTorch, and can be easily extended to other ML and DL frameworks. Main Results: In this manuscript, we present OpenFL and summarize its motivation and development characteristics, with the intention of facilitating its application to existing ML/DL model training in a production environment. We further provide recommendations to secure a federation using trusted execution environments to ensure explicit model security and integrity, as well as maintain data confidentiality. Finally, we describe the first real-world healthcare federations that use the OpenFL library, and highlight how it can be applied to other non-healthcare use cases. Significance: The OpenFL library is designed for real world scalability, trusted execution, and also prioritizes easy migration of centralized ML models into a federated training pipeline. Although OpenFL's initial use case was in healthcare, it is applicable beyond this domain and is now reaching wider adoption both in research and production settings. The tool is open sourced at github.com/intel/openfl.

show abstract

Federated Learning Enables Big Data for Rare Cancer Boundary Detection

Cited by 3 publications

References 50 publications

Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

Prediction of cervical lymph node metastasis from immunostained specimens of tongue cancer using a multilayer perceptron neural network

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

OpenFL: the open federated learning library

Contact Info

Product

Resources

About