Federated learning for brain tumor segmentation and classification : A statistical approach
Journal of Statistics and Management Systems · 2025 · 28 (1) · 67-77
DOI: 10.47974/jsms-1315 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Statistics and Management Systems, 2025. Verfasst von Sivakumar Nadarajan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Enhancing the chances of survival for cancer patients requires early brain tumour identification. This study suggests a federated learning-based method to deal with classification problems caused by overfitting. With the use of the BRATS 2019 and 2020 datasets, the method successfully divides and categorises brain tumours. Data preprocessing involves min-max normalization, followed by CNN segmentation from MRI images. Extracted features undergo shape, texture, and Resnet-50-based feature extraction. These features are then inputted into an LSTM classifier, utilizing Federated Learning for improved classification. Findings indicate that the suggested FL utilizing the CNN-LSTM model outperforms other techniques like U-net and ensemble models, achieving high accuracy: 99.59% on BRATS 2019 and 99.61% on BRATS 2020 datasets.
Zitieren
APA
Nadarajan, S., Unhelkar, B., Shankar, S. S., Chakrabarti, T., Chakrabarti, P., Sivaneasan, B., & Margala, M. (2025). Federated learning for brain tumor segmentation and classification : A statistical approach. Journal of Statistics and Management Systems, 28(1), 67-77. https://doi.org/10.47974/jsms-1315
Vancouver
Nadarajan S, Unhelkar B, Shankar SS, Chakrabarti T, Chakrabarti P, Sivaneasan B, et al. Federated learning for brain tumor segmentation and classification : A statistical approach. Journal of Statistics and Management Systems. 2025;28(1):67-77. doi:10.47974/jsms-1315
BibTeX
@article{Nadarajan2025,
author = {Nadarajan, Sivakumar and Unhelkar, Bhuvan and Shankar, S. Siva and Chakrabarti, Tulika and Chakrabarti, Prasun and Sivaneasan, B. and Margala, Martin},
title = {Federated learning for brain tumor segmentation and classification : A statistical approach},
journal = {Journal of Statistics and Management Systems},
year = {2025},
volume = {28},
number = {1},
pages = {67--77},
doi = {10.47974/jsms-1315}
}
EUVIMED