FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation

Federated learning with integrated attention multiscale model for brain tumor segmentation

Brain tumors are an extremely deadly condition and the growth of abnormal cells that have formed inside the brain causes the illness. According to studies, Magnetic Resonance Imaging (MRI) is a fundamental imaging method that is frequently used in medical diagnostics to identify, treat, and routinely check for brain cancers. These images include extremely private and delicate details regarding the brain health of the individuals and it must be treated with much care to ensure anonymity of patients. However, traditional brain tumor segmentation techniques usually rely on centralized data storage and analysis, which might result in privacy issues and violations. Federated learning offers a solution by enabling the cooperative development of brain tumor segmentation models without necessitating the transfer of raw patient data to a centralized location. All the data are held securely within their institution. A Reinforcement Learning-based Federated Averaging (RL-FedAvg) model is proposed that fuses the Federated Averaging (FedAvg) model with Reinforcement Learning (RL). To optimize the global model for image segmentation jobs as well as to govern the consumption of client resources, the model dynamically updates client hyperparameters upon real-time performance feedback. A Double Attention-based Multiscale Dense-U-Net model, known as mixed-fed-UNet, is proposed in the work that uses the RL-FedAvg algorithm. The proposed technique achieves 98.24% accuracy and 93.28% dice coefficient on BraTs 2020 dataset. While comparing the developed model with the other existing methods, the proposed methodology shows better performance.

FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-Supervised Medical Image Segmentation

Federated learning (FL) effectively mitigates the data silo challenge brought about by policies and privacy concerns, implicitly harnessing more data for deep model training. However, traditional centralized FL models grapple with diverse multi-center data, especially in the face of significant data heterogeneity, notably in medical contexts. In the realm of medical image segmentation, the growing imperative to curtail annotation costs has amplified the importance of weakly-supervised techniques which utilize sparse annotations such as points, scribbles, etc. A pragmatic FL paradigm shall accommodate diverse annotation formats across different sites, which research topic remains under-investigated. In such context, we propose a novel personalized FL framework with learnable prompt and aggregation (FedLPPA) to uniformly leverage heterogeneous weak supervision for medical image segmentation. In FedLPPA, a learnable universal knowledge prompt is maintained, complemented by multiple learnable personalized data distribution prompts and prompts representing the supervision sparsity. Integrated with sample features through a dual-attention mechanism, those prompts empower each local task decoder to adeptly adjust to both the local distribution and the supervision form. Concurrently, a dual-decoder strategy, predicated on prompt similarity, is introduced for enhancing the generation of pseudo-labels in weakly-supervised learning, alleviating overfitting and noise accumulation inherent to local data, while an adaptable aggregation method is employed to customize the task decoder on a parameter-wise basis. Extensive experiments on four distinct medical image segmentation tasks involving different modalities underscore the superiority of FedLPPA, with its efficacy closely parallels that of fully supervised centralized training. Our code and data will be available at https://github.com/llmir/FedLPPA.

Federated learning for medical image analysis: A survey

Machine learning in medical imaging often faces a fundamental dilemma, namely, the small sample size problem. Many recent studies suggest using multi-domain data pooled from different acquisition sites/centers to improve statistical power. However, medical images from different sites cannot be easily shared to build large datasets for model training due to privacy protection reasons. As a promising solution, federated learning, which enables collaborative training of machine learning models based on data from different sites without cross-site data sharing, has attracted considerable attention recently. In this paper, we conduct a comprehensive survey of the recent development of federated learning methods in medical image analysis. We have systematically gathered research papers on federated learning and its applications in medical image analysis published between 2017 and 2023. Our search and compilation were conducted using databases from IEEE Xplore, ACM Digital Library, Science Direct, Springer Link, Web of Science, Google Scholar, and PubMed. In this survey, we first introduce the background of federated learning for dealing with privacy protection and collaborative learning issues. We then present a comprehensive review of recent advances in federated learning methods for medical image analysis. Specifically, existing methods are categorized based on three critical aspects of a federated learning system, including client end, server end, and communication techniques. In each category, we summarize the existing federated learning methods according to specific research problems in medical image analysis and also provide insights into the motivations of different approaches. In addition, we provide a review of existing benchmark medical imaging datasets and software platforms for current federated learning research. We also conduct an experimental study to empirically evaluate typical federated learning methods for medical image analysis. This survey can help to better understand the current research status, challenges, and potential research opportunities in this promising research field.