A Novel Federated Learning Framework for Sustainable and Efficient Breast Cancer Classification System (FL-L2CNN-BCDet)

Abstract

Artificial intelligence (AI) technologies have vastly improved. AI is now being used in a variety of applications to diagnose Breast Cancer (BC). However, most of the recent research has focused on centralized learning, which can pose privacy risks. In this paper, we propose a novel Federated Learning (FL) framework for the BC classification systems. The main objectives of this research are to improve data security and privacy, increase the accuracy of the Deep Learning (DL) model, and minimize energy consumption and related carbon emissions, which provides a way toward achieving green AI and sustainability goals. However, continuously transmitting model updates between the client and the server may cause lag and escalate host energy consumption. To minimize communication cost and simultaneously achieve the best accuracy, the proposed FL framework develops a new DL architecture for mammography classification, taking into account the optimal number of rounds between client hosts and the central server. The proposed DL architecture employs attention mechanisms, convolutional layers, and LSTMs to extract and analyze features and uses techniques to prevent overfitting and manage imbalanced data. The proposed FL framework is evaluated on three benchmark datasets. The results indicate that the proposed framework is more effective in detecting breast cancer compared to the recent approaches, achieving 95.17%, 100%, and 98.82% on the DDSM, INbreast, and Macrocalcification datasets, respectively.