Health Care and Medical System for Early Detection of Lung Cancer Using Integrated Intelligent Techniques

Document Type

Conference Proceeding

Source of Publication

International Conference on Ubiquitous and Future Networks Icufn

Publication Date

9-30-2025

Abstract

In recent years, non-communicable diseases, particularly cancer, have seen a significant rise in prevalence, with lung cancer posing a major challenge in diagnostics and detection. Timely identification of lung cancer can potentially improve public health outcomes and save lives by enabling physicians to provide targeted treatments. Accurate classification of lung cancer using medical imaging data can reduce mortality rates associated with the disease. Despite significant advancements in convolutional neural networks (CNN) for lung cancer detection, predicting lung cancer remains challenging due to the complexity of CT scans. Many models face challenges related to insufficient labeled data and overfitting, which hinder accuracy. We introduced the 4DCNN model to address these issues, with and without data augmentation. Our model outperformed previous approaches, achieving exceptional results with an accuracy of 99.05%, precision of 97.55%, recall of 98.51%, and F1-score of 97.99% in classifying Normal vs. Adenocarcinoma. The developed lung cancer diagnostic model also demonstrated superior performance across three additional lung cancer classes when all performance indicators were evaluated.

ISBN

[9798331524876]

ISSN

2165-8528

Publisher

IEEE

First Page

311

Last Page

315

Disciplines

Computer Sciences | Medicine and Health Sciences

Keywords

Artificial intelligence, Health Care, Intelligent diagnosis, Lung cancer, Medical Informatics

Scopus ID

105018737609

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS