Hybrid Attention Vision Transformer for Enhanced Lung Cancer Detection

DOI

10.2991/978-94-6463-718-2_58How to use a DOI?

Keywords

Hybrid Attention Vision Transformers; Lung Cancer Detection; Medical Imaging; Attention Mechanism; Transfer Learning; Multi-modal Data; Real-time Processing; Early Diagnosis; Computational Efficiency; Clinical Deployment; Personalized Treatment

Abstract

The use of Hybrid Attention Vision Transformers (HViTs) is emerging as a powerful technique to improve the accuracy and efficiency when it comes to lung cancer detection. These models generalize across patient populations and clinical settings through application of large, diverse datasets within training, enabling them to function well. HViTs otherwise have flexible representation that captures complex features in the multi-modal clinical images, because of which, it can derive better correlations than conventional models in identifying early-stage lung cancer. The ability to leverage left and right contextual information through 1D convolutions also improves detection accuracy across challenging cases, while attention enables the model to focus on features that matter in the context of the organization. Their high computational cost notwithstanding, ever more powerful hardware is now widely available to deploy these models in the clinic. In addition, transfer learning enables the adaptation of generalized models to specific medical datasets, which mitigates the requirement for large-scale labeled data and expedites deployment. Fine-grained real-time processing specifically on the clinical task guarantees timely decision-making, and the combination of multi-modal data enhances the diagnosis and prognosis. Overall, these models could transform the way lung cancer is discovered and give clinicians a device for early diagnosis and individualized treatment that they can trust, as they are continually validated in the natural world.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - J. Nirmala Gandhi
AU  - K. Venkatesh Guru
AU  - Y. Varun
AU  - K. Vasanth
AU  - P. Vimal
AU  - K. Madheswaran
PY  - 2025
DA  - 2025/05/23
TI  - Hybrid Attention Vision Transformer for Enhanced Lung Cancer Detection
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 671
EP  - 682
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_58
DO  - 10.2991/978-94-6463-718-2_58
ID  - Gandhi2025
ER  -