Asynchronous Decentralized Federated Lifelong Learning for Landmark Localization in Medical Imaging

Guangyao Zheng, Michael A. Jacobs, Vladimir Braverman, Vishwa Sanjay Parekh

Keywords: Federated learning, Lifelong learning, Deep reinforcement learning, Landmark localization

TL;DR: A novel method of landmark localization federated learning system that is asynchronous decentralized and has lifelong learning capabilities

Abstract: Federated learning is a recent development in the machine learning area that allows a system of devices to train on one or more tasks without sharing their data to a single location or device. However, this framework still requires a centralized server to consolidate individual models into one synchronously or have inefficient or frail peer-to-peer communication, which are potential bottlenecks for the use of federated learning. In this paper, we propose a novel method of asynchronous decentralized federated lifelong learning (ADFLL) method that inherits the merits of federated learning and can train on multiple tasks simultaneously without the need for a central node or synchronous training, or less-than-desirable peer-to-peer communication. Thus, overcoming the potential drawbacks of conventional federated learning. We demonstrate excellent performance on the brain tumor segmentation (BRATS) dataset for localizing the left ventricle on multiple image sequences and image orientation. Our framework allows agents to achieve the best performance with a mean distance error of 7.81, better than the conventional central aggregation agent's mean distance error of 11.78, and significantly (p=0.01) better than a conventional lifelong reinforcement learning (LL) agent with a distance error of 15.17 after eight rounds of training. In addition, all ADFLL agents have better performance than a conventional reinforcement learning (RL) agent with no LL implementation. In conclusion, we developed an ADFLL framework with excellent performance and speed-up compared to conventional LL agents.