联邦学习使大数据赋能罕见癌症边界检测
机器学习
2022-12-07 v2 图像与视频处理
摘要
尽管机器学习(ML)已在众多领域展现出前景,但人们仍担忧其对样本外数据的泛化能力。目前这一问题通过集中共享来自多个站点的充足且关键的多样化数据来解决。然而,由于各种限制,这种集中化难以扩展(甚至不可行)。联邦机器学习(FL)提供了一种替代方案,通过仅共享数值模型更新来训练准确且可泛化的 ML 模型。在此,我们展示了迄今为止规模最大的 FL 研究结果,涉及六大洲 71 家医疗机构的数据,利用文献中曾使用过的最大规模此类患者数据集(来自 6,314 名患者的 25,256 张 MRI 扫描),为罕见疾病胶质母细胞瘤生成自动肿瘤边界检测器。我们展示,相较于公开训练的模型,在勾画可手术靶区肿瘤方面提升了 33%,在勾画肿瘤整体范围方面提升了 23%。我们预期本研究将:1) 使更多由大规模多样化数据支撑的医学研究成为可能,确保对罕见疾病和代表性不足人群产生有意义的结果;2) 通过对我们共识模型进行性能优化并最终公开发布,促进针对胶质母细胞瘤的进一步定量分析;3) 证明 FL 在此种规模和任务复杂度下的有效性,作为多站点协作的范式转变,免去数据共享之需。
引用
@article{arxiv.2204.10836,
title = {Federated Learning Enables Big Data for Rare Cancer Boundary Detection},
author = {Sarthak Pati and Ujjwal Baid and Brandon Edwards and Micah Sheller and Shih-Han Wang and G Anthony Reina and Patrick Foley and Alexey Gruzdev and Deepthi Karkada and Christos Davatzikos and Chiharu Sako and Satyam Ghodasara and Michel Bilello and Suyash Mohan and Philipp Vollmuth and Gianluca Brugnara and Chandrakanth J Preetha and Felix Sahm and Klaus Maier-Hein and Maximilian Zenk and Martin Bendszus and Wolfgang Wick and Evan Calabrese and Jeffrey Rudie and Javier Villanueva-Meyer and Soonmee Cha and Madhura Ingalhalikar and Manali Jadhav and Umang Pandey and Jitender Saini and John Garrett and Matthew Larson and Robert Jeraj and Stuart Currie and Russell Frood and Kavi Fatania and Raymond Y Huang and Ken Chang and Carmen Balana and Jaume Capellades and Josep Puig and Johannes Trenkler and Josef Pichler and Georg Necker and Andreas Haunschmidt and Stephan Meckel and Gaurav Shukla and Spencer Liem and Gregory S Alexander and Joseph Lombardo and Joshua D Palmer and Adam E Flanders and Adam P Dicker and Haris I Sair and Craig K Jones and Archana Venkataraman and Meirui Jiang and Tiffany Y So and Cheng Chen and Pheng Ann Heng and Qi Dou and Michal Kozubek and Filip Lux and Jan Michálek and Petr Matula and Miloš Keřkovský and Tereza Kopřivová and Marek Dostál and Václav Vybíhal and Michael A Vogelbaum and J Ross Mitchell and Joaquim Farinhas and Joseph A Maldjian and Chandan Ganesh Bangalore Yogananda and Marco C Pinho and Divya Reddy and James Holcomb and Benjamin C Wagner and Benjamin M Ellingson and Timothy F Cloughesy and Catalina Raymond and Talia Oughourlian and Akifumi Hagiwara and Chencai Wang and Minh-Son To and Sargam Bhardwaj and Chee Chong and Marc Agzarian and Alexandre Xavier Falcão and Samuel B Martins and Bernardo C A Teixeira and Flávia Sprenger and David Menotti and Diego R Lucio and Pamela LaMontagne and Daniel Marcus and Benedikt Wiestler and Florian Kofler and Ivan Ezhov and Marie Metz and Rajan Jain and Matthew Lee and Yvonne W Lui and Richard McKinley and Johannes Slotboom and Piotr Radojewski and Raphael Meier and Roland Wiest and Derrick Murcia and Eric Fu and Rourke Haas and John Thompson and David Ryan Ormond and Chaitra Badve and Andrew E Sloan and Vachan Vadmal and Kristin Waite and Rivka R Colen and Linmin Pei and Murat Ak and Ashok Srinivasan and J Rajiv Bapuraj and Arvind Rao and Nicholas Wang and Ota Yoshiaki and Toshio Moritani and Sevcan Turk and Joonsang Lee and Snehal Prabhudesai and Fanny Morón and Jacob Mandel and Konstantinos Kamnitsas and Ben Glocker and Luke V M Dixon and Matthew Williams and Peter Zampakis and Vasileios Panagiotopoulos and Panagiotis Tsiganos and Sotiris Alexiou and Ilias Haliassos and Evangelia I Zacharaki and Konstantinos Moustakas and Christina Kalogeropoulou and Dimitrios M Kardamakis and Yoon Seong Choi and Seung-Koo Lee and Jong Hee Chang and Sung Soo Ahn and Bing Luo and Laila Poisson and Ning Wen and Pallavi Tiwari and Ruchika Verma and Rohan Bareja and Ipsa Yadav and Jonathan Chen and Neeraj Kumar and Marion Smits and Sebastian R van der Voort and Ahmed Alafandi and Fatih Incekara and Maarten MJ Wijnenga and Georgios Kapsas and Renske Gahrmann and Joost W Schouten and Hendrikus J Dubbink and Arnaud JPE Vincent and Martin J van den Bent and Pim J French and Stefan Klein and Yading Yuan and Sonam Sharma and Tzu-Chi Tseng and Saba Adabi and Simone P Niclou and Olivier Keunen and Ann-Christin Hau and Martin Vallières and David Fortin and Martin Lepage and Bennett Landman and Karthik Ramadass and Kaiwen Xu and Silky Chotai and Lola B Chambless and Akshitkumar Mistry and Reid C Thompson and Yuriy Gusev and Krithika Bhuvaneshwar and Anousheh Sayah and Camelia Bencheqroun and Anas Belouali and Subha Madhavan and Thomas C Booth and Alysha Chelliah and Marc Modat and Haris Shuaib and Carmen Dragos and Aly Abayazeed and Kenneth Kolodziej and Michael Hill and Ahmed Abbassy and Shady Gamal and Mahmoud Mekhaimar and Mohamed Qayati and Mauricio Reyes and Ji Eun Park and Jihye Yun and Ho Sung Kim and Abhishek Mahajan and Mark Muzi and Sean Benson and Regina G H Beets-Tan and Jonas Teuwen and Alejandro Herrera-Trujillo and Maria Trujillo and William Escobar and Ana Abello and Jose Bernal and Jhon Gómez and Joseph Choi and Stephen Baek and Yusung Kim and Heba Ismael and Bryan Allen and John M Buatti and Aikaterini Kotrotsou and Hongwei Li and Tobias Weiss and Michael Weller and Andrea Bink and Bertrand Pouymayou and Hassan F Shaykh and Joel Saltz and Prateek Prasanna and Sampurna Shrestha and Kartik M Mani and David Payne and Tahsin Kurc and Enrique Pelaez and Heydy Franco-Maldonado and Francis Loayza and Sebastian Quevedo and Pamela Guevara and Esteban Torche and Cristobal Mendoza and Franco Vera and Elvis Ríos and Eduardo López and Sergio A Velastin and Godwin Ogbole and Dotun Oyekunle and Olubunmi Odafe-Oyibotha and Babatunde Osobu and Mustapha Shu'aibu and Adeleye Dorcas and Mayowa Soneye and Farouk Dako and Amber L Simpson and Mohammad Hamghalam and Jacob J Peoples and Ricky Hu and Anh Tran and Danielle Cutler and Fabio Y Moraes and Michael A Boss and James Gimpel and Deepak Kattil Veettil and Kendall Schmidt and Brian Bialecki and Sailaja Marella and Cynthia Price and Lisa Cimino and Charles Apgar and Prashant Shah and Bjoern Menze and Jill S Barnholtz-Sloan and Jason Martin and Spyridon Bakas},
journal= {arXiv preprint arXiv:2204.10836},
year = {2022}
}
备注
federated learning, deep learning, convolutional neural network, segmentation, brain tumor, glioma, glioblastoma, FeTS, BraTS