Brain Tumor Detection in MRI Based on Federated Learning with YOLOv11

TL;DR

The paper addresses the challenge of brain tumor detection in MRI under data privacy and latency constraints. It introduces a federated learning framework that deploys YOLOv11 across multiple medical facilities, using FedAvg to aggregate locally trained detectors without sharing patient data. The approach demonstrates improved generalization and accuracy over centralized baselines, with comprehensive experiments on a synthetic MRI dataset and a detailed complexity analysis. The work highlights the practical potential of privacy-preserving, multi-institution collaboration for rapid, accurate brain tumor detection in clinical settings, while also acknowledging heterogeneity and communication challenges. Overall, the combination of YOLOv11 with federated learning provides a scalable, privacy-conscious pathway for deploying real-time brain tumor detectors in diverse healthcare environments.

Abstract

One of the primary challenges in medical diagnostics is the accurate and efficient use of magnetic resonance imaging (MRI) for the detection of brain tumors. But the current machine learning (ML) approaches have two major limitations, data privacy and high latency. To solve the problem, in this work we propose a federated learning architecture for a better accurate brain tumor detection incorporating the YOLOv11 algorithm. In contrast to earlier methods of centralized learning, our federated learning approach protects the underlying medical data while supporting cooperative deep learning model training across multiple institutions. To allow the YOLOv11 model to locate and identify tumor areas, we adjust it to handle MRI data. To ensure robustness and generalizability, the model is trained and tested on a wide range of MRI data collected from several anonymous medical facilities. The results indicate that our method significantly maintains higher accuracy than conventional approaches.

Figures (5)

• Figure 1: An overview of the Federated Learning System for Brain Tumor Detection. This image depicts the architecture of our federated learning framework, including the interaction between the central utility server and $N$ client devices, each representing a medical facility. It describes the flow of local model training, data aggregation, and global model updates over numerous global rounds, emphasizing data privacy and the collaborative training process.
• Figure 2: Score matrices of four types: F1-curve (a), P-curve (b), PR-curve (c), and R-curve (d).
• Figure 3: Simulation results on the model's predictions across various images.
• Figure 4: Comparison between ML (a) and FL (b) results between 2 confusion matrix where the more precise diagonal indicates better model prediction.
• Figure 5: Comparison between ML and FL results in terms of accuracy (a) and loss (b) value.