Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2025.073342
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

A Hybrid Vision Transformer with Attention Architecture for Efficient Lung Cancer Diagnosis

Abdu Salam1, Fahd M. Aldosari2, Donia Y. Badawood3, Farhan Amin4,*, Isabel de la Torre5,*, Gerardo Mendez Mezquita6, Henry Fabian Gongora6
1 Department of Computer Science, Abdul Wali Khan University, Mardan, 23200, Pakistan
2 Department of Computer and Networks Engineering, Umm Alqura University, Makkah, 21955, Saudi Arabia
3 Department of Data Science, Umm Alqura University, Makkah, 21955, Saudi Arabia
4 School of Computer Science and Engineering, Yeungnam University, Gyeongsan, 38541, Republic of Korea
5 Department of Signal Theory and Communications, University of Valladolid, Valladolid, 47011, Spain
6 Universidad Internacional Iberoamericana, Campeche, 24560, México
* Corresponding Author: Farhan Amin. Email: email; Isabel de la Torre. Email: email
(This article belongs to the Special Issue: Advancements in Machine Learning and Artificial Intelligence for Pattern Detection and Predictive Analytics in Healthcare)

Computers, Materials & Continua https://doi.org/10.32604/cmc.2025.073342

Received 16 September 2025; Accepted 17 November 2025; Published online 18 December 2025

Abstract

Lung cancer remains a major global health challenge, with early diagnosis crucial for improved patient survival. Traditional diagnostic techniques, including manual histopathology and radiological assessments, are prone to errors and variability. Deep learning methods, particularly Vision Transformers (ViT), have shown promise for improving diagnostic accuracy by effectively extracting global features. However, ViT-based approaches face challenges related to computational complexity and limited generalizability. This research proposes the DualSet ViT-PSO-SVM framework, integrating a ViT with dual attention mechanisms, Particle Swarm Optimization (PSO), and Support Vector Machines (SVM), aiming for efficient and robust lung cancer classification across multiple medical image datasets. The study utilized three publicly available datasets: LIDC-IDRI, LUNA16, and TCIA, encompassing computed tomography (CT) scans and histopathological images. Data preprocessing included normalization, augmentation, and segmentation. Dual attention mechanisms enhanced ViT’s feature extraction capabilities. PSO optimized feature selection, and SVM performed classification. Model performance was evaluated on individual and combined datasets, benchmarked against CNN-based and standard ViT approaches. The DualSet ViT-PSO-SVM significantly outperformed existing methods, achieving superior accuracy rates of 97.85% (LIDC-IDRI), 98.32% (LUNA16), and 96.75% (TCIA). Cross-dataset evaluations demonstrated strong generalization capabilities and stability across similar imaging modalities. The proposed framework effectively bridges advanced deep learning techniques with clinical applicability, offering a robust diagnostic tool for lung cancer detection, reducing complexity, and improving diagnostic reliability and interpretability.

Keywords

Deep learning; artificial intelligence; healthcare; medical imaging; vision transformer

  • 38

    View

  • 7

    Download

  • 0

    Like

Related articles
Copyright© 2025 Tech Science Press
© 1997-2025 TSP (Henderson, USA) unless otherwise stated

Share Link