Categorization Of Healthcare Images Using Federated Learning with Pre-Trained Model

Categorization Of Healthcare Images Using Federated Learning with Pre-Trained Model

M.Brahmaiah

Assistant Professor ,Department  of Computer Science and Engineering, R.V.R& J.C College of                              Engineering,chowdavaram,Guntur,Andhrapradesh.

Gorle Nikitha

Balli Hareesh

Nallamothu Nagaraju

Allu Sai Durga

Ch.likita

UG Students, Department of Computer Science and Engineering, R.V.R& J.C College of Engineering,

chowdavaram,Guntur,Andhrapradesh

Abstract:
Classification of medical images is crucial in healthcare, especially for disease diagnosis and treatment planning. However, privacy concerns regarding patient information hinder the use of centralized machine learning models. Federated learning (fl) provides a promising solution by enabling collaborative model training across distributed data while ensuring information confidentiality. This study evaluates the use of Models trained beforehand in fl for categorization of healthcare images, specifically using ct scan images. The local models, based on resnet, contribute to the construction of a global model. Pre-trained models, trained on extensive datasets, improve the operational efficiency and classification effectiveness of fl models without compromising data confidentiality.

Keywords: categorization of healthcare images, Federated learning, Models trained beforehand, EfficientNet, Resnet ,CNN2D, COVID-19, sophisticated neural networks