Abstract
Artificial Intelligence (AI) methods need to learn from an adequately large
dataset to achieve clinical-grade accuracy and validation, which is vital in the
healthcare field. However, sensitive medical data is usually fragmented, and not shared
due to security and patient privacy policies. In this context, our work aims at
classifying abdominal and chest radiographs by applying Federated Learning (FL)
without exchanging patient data. FL framework has been implemented on distributed
data across multiple clients. In the framework, a multilayer perceptron is used as a deep
learning model for the classification task. FL is a novel approach in which machine
learning models are built with the collaboration of multiple clients controlled by a
central server or service provider. FL model ensures data privacy and security by
retaining the training data decentralized. FL model provides security and privacy for
patients by training individual models in distributed clients and sharing merely the
model weights.
Related Books
Virtual Reality, Artificial Intelligence and Specialized Logistics in Healthcare
Disease Prediction using Machine Learning, Deep Learning and Data Analytics
A Handbook of Attention Deficit Hyperactivity Disorder (ADHD) in the Interdisciplinary Perspective
Frontiers in Occupational Health and Safety
Frontiers in Occupational Health and Safety
Mental Health Promotion in Schools
Mental Health Promotion in Schools
Whole Person Self-Healing: A Science and Art
Transforming Sexual Health in Scotland: Cultural, Organisational and Partnership Approaches
An Ecological Perspective on Health Promotion Systems, Settings and Social Processes