Dynamic selectout and voting-based federated learning for enhanced medical image analysis
Federated learning (FL) is a promising technique for training machine learning models on distributed, privacy-aware datasets. Nevertheless, FL faces difficulties with agent/client participation, model performance, and the heterogeneous nature of networked data sources when it comes to distributed he...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada0a6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832593519539126272 |
|---|---|
| author | Saeed Iqbal Adnan N Qureshi Musaed Alhussein Khursheed Aurangzeb Atif Mahmood Saaidal Razalli Bin Azzuhri |
| author_facet | Saeed Iqbal Adnan N Qureshi Musaed Alhussein Khursheed Aurangzeb Atif Mahmood Saaidal Razalli Bin Azzuhri |
| author_sort | Saeed Iqbal |
| collection | DOAJ |
| description | Federated learning (FL) is a promising technique for training machine learning models on distributed, privacy-aware datasets. Nevertheless, FL faces difficulties with agent/client participation, model performance, and the heterogeneous nature of networked data sources when it comes to distributed healthcare systems. When these agents work together in the system, it is imperative to tackle the complexities of distributed deep learning. We suggest a novel approach that uses a voting mechanism and dynamic SelectOut inside the FL framework to address these problems. Local medical imaging datasets frequently show diversity in distribution and data imbalances. In certain situations, traditional FL techniques like FedProx and federated averaging, which depend on data size to weight contributions, might not be the optimal choice. In order to improve parameter aggregation and client selection unpredictability and increase the model’s adaptability to imbalanced and heterogeneous datasets, our proposed FedVoteNet model introduces SelectOut techniques based on voting methodology. Based on how much their local performance has improved from the last communication cycle, we arbitrarily remove clients. Additionally eliminated are clients whose model weights when combined with the global model adversely affect its performance. Our method is further enhanced by the inclusion of a voting mechanism. At the conclusion of each communication cycle, clients that improve both their local performance and their contribution to the global model are awarded higher voting values. This encourages more significant and effective contributions from clients by providing incentives for them to actively increase the diversity of their training data. We assess our approach on a dataset of medical images, including magnetic resonance imaging scans, and find that the FL model performs noticeably better (F1 Score = 0.968, Sensitivity = 0.977, Specificity = 0.945, and AUC = 0.950). The voting system and the dynamic SelectOut algorithms improve the convergence of the FL model and successfully handle the difficulties presented by uneven and heterogeneous datasets. To sum up, our proposed approach uses voting and dynamic SelectOut techniques to improve FL performance on a variety of uneven, distributed, and varied datasets. This strategy has a lot of potential to improve FL across a range of applications, especially those that prioritize data privacy, diversity, and performance. |
| format | Article |
| id | doaj-art-0a40824bca67404fb056eabd0e11ab5b |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-0a40824bca67404fb056eabd0e11ab5b2025-01-20T11:30:05ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101501010.1088/2632-2153/ada0a6Dynamic selectout and voting-based federated learning for enhanced medical image analysisSaeed Iqbal0https://orcid.org/0000-0002-3176-4658Adnan N Qureshi1Musaed Alhussein2Khursheed Aurangzeb3Atif Mahmood4https://orcid.org/0009-0004-1108-2053Saaidal Razalli Bin Azzuhri5College of Mechatronics and Control Engineering, Shenzhen University , Shenzhen 518060, People’s Republic of China; Department of Computer Science, Faculty of Information Technology & Computer Science, University of Central Punjab , Lahore 54000, PakistanFaculty of Arts, Society and Professional Studies, Newman University , Birmingham, United KingdomDepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University , PO Box 51178, Riyadh 11543, Saudi ArabiaDepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University , PO Box 51178, Riyadh 11543, Saudi ArabiaDepartment of Software Engineering, School of Systems and Technology, University of Management and Technology , Lahore 54000, PakistanDepartment of Computer System & Technology, Faculty of Computer Science and Information Technology, University of Malaya , 50603 Kuala Lumpur, MalaysiaFederated learning (FL) is a promising technique for training machine learning models on distributed, privacy-aware datasets. Nevertheless, FL faces difficulties with agent/client participation, model performance, and the heterogeneous nature of networked data sources when it comes to distributed healthcare systems. When these agents work together in the system, it is imperative to tackle the complexities of distributed deep learning. We suggest a novel approach that uses a voting mechanism and dynamic SelectOut inside the FL framework to address these problems. Local medical imaging datasets frequently show diversity in distribution and data imbalances. In certain situations, traditional FL techniques like FedProx and federated averaging, which depend on data size to weight contributions, might not be the optimal choice. In order to improve parameter aggregation and client selection unpredictability and increase the model’s adaptability to imbalanced and heterogeneous datasets, our proposed FedVoteNet model introduces SelectOut techniques based on voting methodology. Based on how much their local performance has improved from the last communication cycle, we arbitrarily remove clients. Additionally eliminated are clients whose model weights when combined with the global model adversely affect its performance. Our method is further enhanced by the inclusion of a voting mechanism. At the conclusion of each communication cycle, clients that improve both their local performance and their contribution to the global model are awarded higher voting values. This encourages more significant and effective contributions from clients by providing incentives for them to actively increase the diversity of their training data. We assess our approach on a dataset of medical images, including magnetic resonance imaging scans, and find that the FL model performs noticeably better (F1 Score = 0.968, Sensitivity = 0.977, Specificity = 0.945, and AUC = 0.950). The voting system and the dynamic SelectOut algorithms improve the convergence of the FL model and successfully handle the difficulties presented by uneven and heterogeneous datasets. To sum up, our proposed approach uses voting and dynamic SelectOut techniques to improve FL performance on a variety of uneven, distributed, and varied datasets. This strategy has a lot of potential to improve FL across a range of applications, especially those that prioritize data privacy, diversity, and performance.https://doi.org/10.1088/2632-2153/ada0a6federated learningdynamic SelectOut mechanismsvoting systemheterogeneous datasetsmodel performancedata privacy |
| spellingShingle | Saeed Iqbal Adnan N Qureshi Musaed Alhussein Khursheed Aurangzeb Atif Mahmood Saaidal Razalli Bin Azzuhri Dynamic selectout and voting-based federated learning for enhanced medical image analysis Machine Learning: Science and Technology federated learning dynamic SelectOut mechanisms voting system heterogeneous datasets model performance data privacy |
| title | Dynamic selectout and voting-based federated learning for enhanced medical image analysis |
| title_full | Dynamic selectout and voting-based federated learning for enhanced medical image analysis |
| title_fullStr | Dynamic selectout and voting-based federated learning for enhanced medical image analysis |
| title_full_unstemmed | Dynamic selectout and voting-based federated learning for enhanced medical image analysis |
| title_short | Dynamic selectout and voting-based federated learning for enhanced medical image analysis |
| title_sort | dynamic selectout and voting based federated learning for enhanced medical image analysis |
| topic | federated learning dynamic SelectOut mechanisms voting system heterogeneous datasets model performance data privacy |
| url | https://doi.org/10.1088/2632-2153/ada0a6 |
| work_keys_str_mv | AT saeediqbal dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis AT adnannqureshi dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis AT musaedalhussein dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis AT khursheedaurangzeb dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis AT atifmahmood dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis AT saaidalrazallibinazzuhri dynamicselectoutandvotingbasedfederatedlearningforenhancedmedicalimageanalysis |