News | Artificial Intelligence | October 23, 2019

NVIDIA and King's College London Debut First Privacy-preserving Federated Learning System

Federated learning is a type of deep learning or artificial intelligence that distributes training data across multiple locations

NVIDIA and King's College London Debut First Privacy-preserving Federated Learning System

Image courtesy of NVIDIA

October 23, 2019 — To help advance medical research while preserving data privacy and improving patient outcomes for brain tumor identification, NVIDIA researchers in collaboration with King’s College London researchers recently announced the introduction of the first privacy-preserving federated learning system for medical image analysis. NVIDIA is working with King’s College London and French startup Owkin to enable federated learning for the newly established London Medical Imaging and AI Centre for Value Based Healthcare.

This new paper was presented at the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), one of the world’s top conferences on medical imaging, Oct. 13-17 in Shenzhen, China. In the work, NVIDIA and King’s College London researchers describe in detail how they developed their technique.

Federated learning is a learning paradigm that allows developers and organizations to train a centralized deep neural network (DNN) with training data distributed across multiple locations. This makes it possible for organizations to collaborate on a shared model, without needing to directly share any clinical data. 

“Federated learning allows collaborative and decentralized training of neural networks without sharing the patient data,” the researchers stated in their paper. “Each node trains its own local model and, periodically, submits it to a parameter server. The server accumulates and aggregates the individual contributions to yield a global model, which is then shared with all nodes.”

Although federated learning can provide high security in terms of privacy, there are still ways to reconstruct data by model inversion, the researchers explained. To help make federated learning even safer, the researchers investigate the feasibility of using the ε-differential privacy framework, a way to formally define privacy loss, to protect patient and institutional data with a strong privacy guarantee. To ensure patient privacy is priority, differential privacy and other state-of-the-art privacy protection techniques are being built into the Owkin architecture.

The experiments for this breakthrough were performed on brain tumor segmentation data from the BraTS 2018 dataset. The BraTS 2018 dataset contains magnetic resonance imaging (MRI) scans of 285 patients with brain tumors.

The dataset is used here for evaluating federated learning algorithms on the multi-modal and multi-class segmentation task. On the client side, the team adapted a state-of-the-art training pipeline originally designed for data-centralized training and implemented it as part of the NVIDIA Clara Train SDK.

For training and inference, the team used NVIDIA V100 Tensor Core GPUs.

When comparing federated learning to a data-centralized system, the proposed approach can achieve a comparable segmentation performance without sharing institutional data. 

Moreover, the experimental results show a natural tradeoff between privacy protection and the quality of the trained model. Still, with the sparse vector technique, the federated learning system can provide rigorous privacy protection with only a reasonably small cost in model performances.

Deep learning is a technique for automatically extracting knowledge from medical data, the NVIDIA team explained. Federated learning has the potential of effectively aggregating knowledge across institutions learned locally from private data, thus further improving the accuracy, robustness, and generalization ability of the deep models, they added.

“This research is an important step towards the deployment of secure federated learning, which will enable data-driven precision medicine at large scale,” the NVIDIA researchers stated.

For more information: www.nvidia.com

Related Content

Samsung to highlight its medical imaging portfolio with its latest radiology innovations in ultrasound, digital radiography and mobile computed tomography
News | Radiology Imaging | December 02, 2020
December 2, 2020 — Samsung Electronics Co., Ltd.
 Riverain Technologies will showcase its artificial intelligence solutions and enhancements at the now-virtual 2020 Radiological Society of North America Annual Meeting (RSNA).
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Riverain Technologies will showcase its...
Studies show new deep-learning algorithm helps radiologists detect breast cancers in their early stages when used with the Genius 3D Mammography exam
News | Breast Imaging | December 02, 2020
December 2, 2020 — Hologic, Inc., an innovative medical technology company primarily focused on improving women’s hea
Glassbeam Clinsights can help imaging departments capture service data to enhance operational efficiencies
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Hospitals and institutions face a significant challenge each year when it comes to the financial i
 Philips highlighted its expanding enterprise imaging informatics portfolio that is enabling healthcare providers to advance digital health transformation at RSNA 2020.
News | Enterprise Imaging | December 02, 2020
December 2, 2020 — Philips highlighted its expanding...
Lunit’s algorithm showed the best performance compared to other commercialized AI algorithms, ultimately reducing the workload of radiologists to classify mammography screenings
News | Artificial Intelligence | December 02, 2020
December 2, 2020 — Recent studies have shown that Lunit’s AI solution is as accurate as average radiologists when it
A cut-away view of the two cabins that compose the "CT-in-a-box" solution from GE to rapidly deploy CT scanners at hospitals amid a COVID surge. The CT room is completely separate from the control room to aid in sanitation and keeping technologists away from COVID patients.

A cut-away view of the two cabins that compose the "CT-in-a-box" solution from GE to rapidly deploy CT scanners at hospitals amid a COVID surge. The CT room is completely separate from the control room to aid in sanitation and keeping technologists away from COVID patients. Image by GE Healthcare.

Feature | Coronavirus (COVID-19) | December 01, 2020
December 1, 2020 — As hospitals see an influx of...
The GE Healthcare Allia IGS 71 angiography system. #RSNA #RSNA20 #RSNA2020

The GE Healthcare Allia IGS 71 angiography system.

News | Angiography | December 01, 2020
December 3, 2020 — GE Healthcare is introducing a new, smaller and lighter weight robotic driven ...
Medical imaging artificial intelligence (AI) vendor Avicenna.AI today announced its FDA-cleared CINA Head triage AI solution will be offered by cloud-based imaging platform Arterys. Supporting the treatment of stroke and neurovascular emergencies, CINA Head detects intracranial hemorrhages (ICHs) and large vessel occlusions (LVOs) from CT-scan imaging. #RSNA20 #RSNA2020

Medical imaging artificial intelligence (AI) vendor Avicenna.AI announced its FDA-cleared CINA Head triage AI solution will be offered by cloud-based imaging platform Arterys. Supporting the treatment of stroke and neurovascular emergencies, CINA Head detects intracranial hemorrhages (ICHs) and large vessel occlusions (LVOs) from CT-scan imaging.
 

News | Stroke | December 01, 2020
December 1, 2020 – Medical imaging ...