Medical Image Classification with Privacy: Centralized and Federated Learning Comparison
The use of different techniques in image-based medical diagnostic computing has positively impacted the healthcare industry. Diseases such as colon and lung cancer can be detected using image classification strategies. In this context, Federated Learning (FL) has emerged as an enabling approach to disease detection with security and privacy when handling sensitive patient data. This study aimed to compare the centralized and FL classifications of histopathological images of lung and colon cancer. We compared the performance of FL with that of centralized learning, and the results indicated that FL outperformed centralized approaches in scenarios with heterogeneous datasets. These findings highlight the potential of FL as an alternative to medical image classification, particularly in privacy-sensitive applications.
Authors
- Gleidson Barbosa
- Lara Cristina Evaristo Rodrigues (ORCID: https://orcid.org/0000-0003-4903-9574)
- André Ricardo Backes (ORCID: https://orcid.org/0000-0002-7486-4253)
- Rodrigo Moreira (ORCID: https://orcid.org/0000-0002-9328-8618)
- Larissa Ferreira Rodrigues Moreira (ORCID: https://orcid.org/0000-0001-8947-9182)
Institutions
- Universidade Federal de Viçosa (BR)
- Universidade Federal de São Carlos (BR)
- Universidade Federal de Uberlândia (BR)
Publication Details
- Journal
- Revista de Informática Teórica e Aplicada
- Published
- 2025-02-20
- DOI
- https://doi.org/10.22456/2175-2745.143478
- Citations
- 2
- Primary Topic
- Privacy-Preserving Technologies in Data
- Type
- article
- Field-Weighted Citation Impact
- 4.96
Funders
- Science Foundation Ireland
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais
- Ministério da Ciência, Tecnologia, Inovações e Comunicações