Combining Imaging Intelligence and Privacy-Preserving Demographic Learning for Reliable Lung Cancer Diagnosis

View at publisher Summarise with VIRAT
Authors: M. Vijaya Sudha, Bala K
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The issue of early and accurate diagnosis of lung cancer is a worldwide issue in health care and developing approaches that are not discriminatory and privacy-invasion are a priority. This paper suggests a multimodal model of learning that combines the transfer learning of radiographic images with federated learning of distributed demographic data to increase the predictive accuracy without infringing patient privacy. The model allows joint training of models in various healthcare settings without exchanging sensitive information, which helps to be inclusive of diverse populations. Experimental analysis of datasets of public chest X-rays and demographic data is shown to be better than regular centralized models and leads to high accuracy, recall, and F1score. The offered strategy outlines the promise of accountable and evidence-based intelligence to develop fair, sustainable, and reliable medical interventions.

Fields of Study & Subjects

Privacy-Preserving Technologies in Data AI in cancer detection Radiomics and Machine Learning in Medical Imaging

Publication details

Journal / source
International Conference on Intelligent Sustainable Systems (ICISS)
Pages
1144–1150
Publication date
4 March 2026
Language
EN