Survey of Medical Applications of Federated Learning

다국어 초록 (Multilingual Abstract)

Objectives: Medical artificial intelligence (AI) has recently attracted considerable attention. However, training medical AI models is challenging due to privacy-protection regulations. Among the proposed solutions, federated learning (FL) stands out. FL involves transmitting only model parameters without sharing the original data, making it particularly suitable for the medical field, where data privacy is paramount. This study reviews the application of FL in the medical domain. Methods: We conducted a literature search using the keywords "federated learning" in combination with "medical," "healthcare," or "clinical" on Google Scholar and PubMed. After reviewing titles and abstracts, 58 papers were selected for analysis. These FL studies were categorized based on the types of data used, the target disease, the use of open datasets, the local model of FL, and the neural network model. We also examined issues related to heterogeneity and security. Results: In the investigated FL studies, the most commonly used data type was image data, and the most studied target diseases were cancer and COVID-19. The majority of studies utilized open datasets. Furthermore, 72% of the FL articles addressed heterogeneity issues, while 50% discussed security concerns. Conclusions: FL in the medical domain appears to be in its early stages, with most research using open data and focusing on specific data types and diseases for performance verification purposes. Nonetheless, medical FL research is anticipated to be increasingly applied and to become a vital component of multi-institutional research.

참고문헌 (Reference)

1 Stripelis D, "neuroscience research using federated learning" 1191-1195, 2021

2 WHO CVD Risk Chart Working Group, "World Health Organization cardiovascular disease risk charts : revised models to estimate risk in 21 global regions" 7 (7): e1332-e1345, 2019

3 Albawi S, "Understanding of a convolutional neural network" 1-6, 2017

4 Acheampong FA, "Transformer models for text-based emotion detection : a review of BERT-based approaches" 54 : 5789-5829, 2021

5 Liu P, "Threats, attacks and defenses to federated learning : issues, taxonomy and perspectives" 5 (5): 4-, 2022

6 Dwork C, "Theory and applications of models of computation" Springer 1-19, 2008

7 Gooch CL, "The burden of neurological disease in the United States : a summary report and call to action" 81 (81): 479-484, 2017

8 Chen RJ, "Synthetic data in machine learning for medicine and healthcare" 5 (5): 493-497, 2021

9 Elayan H, "Sustainability of healthcare data analysis IoT-based systems using deep federated learning" 9 (9): 7338-7346, 2021

10 Ke J, "Style normalization in histology with federated learning" 953-956, 2021

11 Feng CM, "Specificity-preserving federated learning for MR image reconstruction" 42 (42): 2010-2021, 2023

12 Hu H, "Source inference attacks in federated learning" 1102-1107, 2021

13 Andreux M, "Siloed federated learning for multi-centric histopathology datasets" arXiv.org

14 Karimireddy SP, "Scaffold: stochastic controlled averaging for federated learning" arXiv.org

15 Kanani P, "Private cross-silo federated learning for extracting vaccine adverse event mentions" arXiv.org

16 Park J, "Privacy-preserving federated learning using homomorphic encryption" 12 (12): 734-, 2022

17 Islam TU, "Privacy-preserving federated learning model for healthcare data" 281-287, 2022

18 Xu X, "Privacy-preserving federated depression detection from multisource mobile health data" 18 (18): 4788-4797, 2021

19 Can YS, "Privacy-preserving federated deep learning for wearable IoT-based biomedical monitoring" 21 (21): 21-, 2021

20 Li W, "Privacy-preserving federated brain tumour segmentation" arXiv.org

21 Sadilek A, "Privacy-first health research with federated learning" 4 (4): 132-, 2021

22 Fang H, "Privacy preserving machine learning with homomorphic encryption and federated learning" 13 (13): 94-, 2021

23 Choudhury O, "Predicting adverse drug reactions on distributed health data using federated learning" 2019 : 313-322, 2020

24 Zhang J, "Poisoning attack in federated learning using generative adversarial nets" 374-380, 2019

25 Yoo JH, "Personalized federated learning with clustering:non-IID heart rate variability data application" arXiv.org

26 Korea Law Translation Center, "Personal Information Protection Act (Act No. 16930, 2020)" Korea Law Translation Center

27 Huang L, "Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records" 99 : 103291-, 2019

28 Liu D, "Multiple sclerosis lesion segmentation : revisiting weighting mechanisms for federated learning" 17 : 1167612-, 2023

29 Agbley BL, "Multimodal melanoma detection with federated learning" 238-244, 2021

30 Shen C, "Multi-task federated learning for heterogeneous pancreas segmentation" arXiv.org

31 Li X, "Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation : ABIDE results" 65 : 101765-, 2020

32 Guo P, "Multi-institutional collaborations for improving deep learningbased magnetic resonance image reconstruction using federated learning" 2021 : 2423-2432, 2021

33 Fung C, "Mitigating sybils in federated learning poisoning" arXiv.org

34 Jimenez-Sanchez A, "Memory-aware curriculum federated learning for breast cancer classification" 229 : 107318-, 2023

35 Fang M, "Local model poisoning attacks to Byzantine-Robust federated learning" 1605-1622, 2020

36 Kalra S, "Learning permutation invariant representations using memory networks" arXiv.org

37 Yang Z, "Hypernetwork-based physics-driven personalized federated learning for CT imaging" 2023

38 US Centers for Disease Control and Prevention, "Health Insurance Portability and Accountability Act of 1996(HIPAA)" Centers for Disease Control and Prevention

39 Goncalves A, "Generation and evaluation of synthetic patient data" 20 (20): 108-, 2020

40 European Union, "General Data Protection Regulation" European Union

41 Frid-Adar M, "GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification" 321 : 321-331, 2018

42 Zhang J, "GAN enhanced membership inference: a passive local attack in federated learning" 1-6, 2020

43 Ge S, "Fedner:privacy-preserving medical named entity recognition with federated learning" arXiv. org

44 Wu Q, "Fedhome : cloudedge based personalized federated learning for inhome health monitoring" 21 (21): 2818-2832, 2020

45 Chen Y, "Fedhealth : a federated transfer learning framework for wearable healthcare" 35 (35): 83-93, 2020

46 Li T, "Federated optimization in heterogeneous networks" arXiv.org

47 Yoo JH, "Federated learning:issues in medical application" arXiv.org

48 Li Q, "Federated learning on non-IID data silos: an experimental study" arXiv.org

49 Vaid A, "Federated learning of electronic health records to improve mortality prediction in hospitalized patients with COVID-19 : machine learning approach" 9 (9): e24207-, 2021

50 Sheller MJ, "Federated learning in medicine : facilitating multi-institutional collaborations without sharing patient data" 10 (10): 12598-, 2020

51 Pfitzner B, "Federated learning in a medical context : a systematic literature review" 21 (21): 50-, 2021

52 Sarma KV, "Federated learning improves site performance in multicenter deep learning without data sharing" 28 (28): 1259-1264, 2021

53 Borger T, "Federated learning for violence incident prediction in a simulated cross-institutional psychiatric setting" 199 : 116720-, 2022

54 Lee H, "Federated learning for thyroid ultrasound image analysis to protect personal information : validation study in a real health care environment" 9 (9): e25869-, 2021

55 Baid U, "Federated learning for the classification of tumor infiltrating lymphocytes" arXiv.org

56 Nguyen DC, "Federated learning for smart healthcare : a survey" 55 (55): 60-, 2022

57 Dayan I, "Federated learning for predicting clinical outcomes in patients with COVID-19" 27 (27): 1735-1743, 2021

58 Linardos A, "Federated learning for multi-center imaging diagnostics : a simulation study in cardiovascular disease" 12 (12): 3551-, 2022

59 Misonne T, "Federated learning for heart segmentation" 1-5, 2022

60 Antunes RS, "Federated learning for healthcare : systematic review and architecture proposal" 13 (13): 54-, 2022

61 Dang TK, "Federated learning for electronic health records" 13 (13): 72-, 2022

62 Lu MY, "Federated learning for computational pathology on gigapixel whole slide images" 76 : 102298-, 2022

63 Roth HR, "Federated learning for breast density classification:a real-world implementation" arXiv.org

64 Zhang M, "Federated learning for arrhythmia detection of non-IID ECG" 1176-1180, 2020

65 Feki I, "Federated learning for COVID-19 screening from chest X-ray images" 106 : 107330-, 2021

66 Pati S, "Federated learning enables big data for rare cancer boundary detection" 13 (13): 7346-, 2022

67 Adnan M, "Federated learning and differential privacy for medical image analysis" 12 (12): 1953-, 2022

68 Dou Q, "Federated deep learning for detecting COVID-19lung abnormalities in CT : a privacy-preserving multinational validation study" 4 (4): 60-, 2021

69 Kassem H, "Federated cycling(FedCy) : semi-supervised federated learning of surgical phases" 42 (42): 1920-1931, 2023

70 Bercea CI, "Feddis:disentangled federated learning for unsupervised brain pathology segmentation" arXiv.org

71 Sui D, "FedED : federated learning via ensemble distillation for medical relation extraction" 2118-2128, 2020

72 Luo X, "Feature inference attack on model predictions in vertical federated learning" 181-192, 2021

73 Yang Q, "FLOP:federated learning on medical datasets using partial networks" 3845-3853, 2021

74 Mondrejevski L, "FLICU: a federated learning workflow for intensive care unit mortality prediction" 32-37, 2022

75 Arikumar KS, "FL-PMI : federated learningbased person movement identification through wearable devices in smart healthcare systems" 22 (22): 1377-, 2022

76 Liu B, "Experiments of federated learning for COVID-19 chest X-ray images" arXiv.org

77 Timmis A, "European Society of Cardiology : cardiovascular disease statistics 2021" 43 (43): 716-799, 2022

78 Dumurgier J, "Epidemiology of neurological diseases in older adults" 176 (176): 642-648, 2020

79 Zhang W, "Dynamic-fusion-based federated learning for COVID-19 detection" 8 (8): 15884-15891, 2021

80 Malekzadeh M, "Dopamine: differentially private federated learning on medical data" arXiv.org

81 Jaladanki SK, "Development of a federated learning approach to predict acute kidney injury in adult hospitalized patients with COVID-19 in New York City" medRxiv.org

82 Abadi M, "Deep learning with differential privacy" 308-318, 2016

83 Shen D, "Deep learning in medical image analysis" 19 : 221-248, 2017

84 Elayan H, "Deep federated learning for IoT-based decentralized healthcare systems" 105-109, 2021

85 Wang R, "Deep & cross network for Ad click predictions" arXiv. org

86 Tolpegin V, "Data Poisoning Attacks Against Federated Learning Systems" arXiv.org

87 McMahan HB, "Communication-efficient learning of deep networks from decentralized data" arXiv.org

88 Qayyum A, "Collaborative federated learning for healthcare : multi-modal COVID-19 diagnosis at the edge" 3 : 172-184, 2022

89 Rajendran S, "Cloud-based federated learning implementation across medical centers" 5 : 1-11, 2021

90 Naehrig M, "Can homomorphic encryption be practical?" 113-124, 2011

91 Wang Z, "Beyond inferring class representatives: user-level privacy leakage from federated learning" 2512-2520, 2019

92 Basu P, "Benchmarking differential privacy and federated learning for BERT models" arXiv.org

93 Thwal CM, "Attention on personalized clinical decision support system : federated learning approach" 141-147, 2021

94 Bhagoji AN, "Analyzing federated learning through an adversarial lens" arXiv.org

95 Ruder S, "An overview of gradient descent optimization algorithms" arXiv.org

96 Kairouz P, "Advances and open problems in federated learning" arXiv.org

97 Kingma DP, "Adam: a method for stochastic optimization" arXiv.org

98 Crowson MG, "A systematic review of federated learning applications for biomedical data" 1 (1): e0000033-, 2022

99 Acar A, "A survey on homomorphic encryption schemes : Theory and implementation" 51 (51): 79-, 2018

100 Litjens G, "A survey on deep learning in medical image analysis" 42 : 60-88, 2017

101 Fontaine C, "A survey of homomorphic encryption for nonspecialists" 2007 : 13801-, 2007

102 Yu Y, "A review of recurrent neural networks : LSTM cells and network architectures" 31 (31): 1235-1270, 2019

103 Cetinkaya AE, "A communication efficient federated learning approach to multi chest diseases classification" 429-434, 2021

104 Xu Y, "A collaborative online AI engine for CT-based COVID-19diagnosis" arXiv.org