Exploiting Test-Time Augmentation in Federated Learning for Brain Tumor MRI Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914263288774656 |
|---|---|
| author | Melo, Thamara Leandra de Deus Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo |
| author_facet | Melo, Thamara Leandra de Deus Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo |
| contents | Efficient brain tumor diagnosis is crucial for early treatment; however, it is challenging because of lesion variability and image complexity. We evaluated convolutional neural networks (CNNs) in a federated learning (FL) setting, comparing models trained on original versus preprocessed MRI images (resizing, grayscale conversion, normalization, filtering, and histogram equalization). Preprocessing alone yielded negligible gains; combined with test-time augmentation (TTA), it delivered consistent, statistically significant improvements in federated MRI classification (p<0.001). In practice, TTA should be the default inference strategy in FL-based medical imaging; when the computational budget permits, pairing TTA with light preprocessing provides additional reliable gains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_12671 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploiting Test-Time Augmentation in Federated Learning for Brain Tumor MRI Classification Melo, Thamara Leandra de Deus Moreira, Rodrigo Moreira, Larissa Ferreira Rodrigues Backes, André Ricardo Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Efficient brain tumor diagnosis is crucial for early treatment; however, it is challenging because of lesion variability and image complexity. We evaluated convolutional neural networks (CNNs) in a federated learning (FL) setting, comparing models trained on original versus preprocessed MRI images (resizing, grayscale conversion, normalization, filtering, and histogram equalization). Preprocessing alone yielded negligible gains; combined with test-time augmentation (TTA), it delivered consistent, statistically significant improvements in federated MRI classification (p<0.001). In practice, TTA should be the default inference strategy in FL-based medical imaging; when the computational budget permits, pairing TTA with light preprocessing provides additional reliable gains. |
| title | Exploiting Test-Time Augmentation in Federated Learning for Brain Tumor MRI Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.12671 |