Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation

  title={Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation},
  author={Holger R. Roth and Ali Hatamizadeh and Ziyue Xu and Can Zhao and Wenqi Li and Andriy Myronenko and Daguang Xu},
. Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be beneficial as it allows insti-tutes with complementary features or images for a shared set of patients to jointly develop more robust and generalizable models. In this work, we propose “Split-U-Net” and successfully apply SL for collaborative biomedical image segmentation. Nonetheless, SL requires the exchanging of… 

Figures and Tables from this paper

Robust Split Federated Learning for U-shaped Medical Image Networks

To preserve data privacy, including the input, model parameters, label and output simultaneously, the proposed RoS-FL is proposed, which is a novel hybrid learning paradigm of FL and SL for U-shaped medical image networks.

Split Learning without Local Weight Sharing to Enhance Client-side Data Privacy

Caching in P-SL reduces the negative effect of forgetting, stabilizes the learning, and enables effective and low-complexity training in a dynamic environment with late-arriving clients and its cache-based version achieve comparable accuracy to SL under various data distributions with lower computation and communications costs.



Privacy-preserving Federated Brain Tumour Segmentation

The feasibility of applying differential-privacy techniques to protect the patient data in a federated learning setup for brain tumour segmentation on the BraTS dataset is investigated and there is a trade-off between model performance and privacy protection costs.

Split Learning for collaborative deep learning in healthcare

This work proves the significant benefit of distributed learning in healthcare, and paves the way for future real-world implementations of split learning based approach in the medical field.

Split learning for health: Distributed deep learning without sharing raw patient data

This paper compares performance and resource efficiency trade-offs of splitNN and other distributed deep learning methods like federated learning, large batch synchronous stochastic gradient descent and show highly encouraging results for splitNN.

Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images

The task of 3D brain tumor semantic segmentation is reformulated as a sequence to sequence prediction problem wherein multi-modal input data is projected into a 1D sequence of embedding and used as an input to a hierarchical Swin transformer as the encoder.

Feasibility study of multi-site split learning for privacy-preserving medical systems under data imbalance constraints in COVID-19, X-ray, and cholesterol dataset

A novel split learning algorithm is provided that enables a secure transfer of medical data between multiple hospitals without fear of exposing personal data contained in patient records, and a guideline for the most optimal configuration of split learning that ensures privacy of patient data whilst achieving performance is empirically given.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

End-to-end privacy preserving deep learning on multi-institutional medical imaging

PriMIA (Privacy-preserving Medical Image Analysis), a free, open-source software framework for differentially private, securely aggregated federated learning and encrypted inference on medical imaging data, is presented.

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

This work shows that these attacks presented in the literature are impractical in FL use-cases where the clients’ training involves updating the Batch Normalization statistics and provides a new baseline attack that works for such scenarios and presents new ways to measure and visualize potential data leakage in FL.

Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning

See through Gradients: Image Batch Recovery via GradInversion

It is shown that gradients encode a surprisingly large amount of information, such that all the individual images can be recovered with high fidelity via GradInversion, even for complex datasets, deep networks, and large batch sizes.