Vijayakumar, P (2025) Enriched lung cancer classification approach using an optimized hybrid deep learning approach. Scientific Reports, 15 (1). ISSN 2045-2322
Enriched lung cancer classification approach using an optimized hybrid deep learning approach.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.
Download (6MB)
Abstract
One of the most destructive diseases worldwide, lung cancers, early detection enhances survival rates1. Benign or malignant can be cells classified as. Inspired or non-cancers are benign cells, while cancers or malignant cells, proliferate in the lungs. Detecting these malignant cells early is vital for the body to mount a successful defence. However, differentiating between benign and malignant nodules is challenging, as they often share similar characteristics, though differences may exist in their location, shape, and structure. Early and accurate identification of these differences is crucial2,3. This challenge is tackled using several diagnostic techniques, CT and Magnetic Resonance Imaging (MRI). Of these, CT and chest X-ray radiography are especially important to early cancer detection because of their capacity to represent different types of cancerous tissues through anatomical imaging. Other imaging modalities cannot match the efficacy of CT for evaluating lung diseases. However, most physicians currently treat aggressive and nonaggressive cancer cell types by relying on intrusive techniques4. However, these techniques are not enough to distinguish malignant from benign cancers which have certain common features.
| Item Type: | Article |
|---|---|
| Subjects: | A Artificial Intelligence and Data Science > Deep Learning C Computer Science and Engineering > Health Care, Disease |
| Divisions: | Electronics and Communication Engineering |
| Depositing User: | Dr Krishnamurthy V |
| Date Deposited: | 13 Nov 2025 09:53 |
| Last Modified: | 13 Nov 2025 09:53 |
| URI: | https://ir.psgitech.ac.in/id/eprint/1546 |
Dimensions
Dimensions