Hybrid Deep Learning Approach for Non-Hodgkin’s Lymhoma using ViT and ResNet

DOI

10.2991/978-94-6463-866-0_5How to use a DOI?

Keywords

Non-Hodgkin’s Lymphoma; Vision Transformer (ViT); Residual Network (ResNet); Chronic Lymphocytic Leukemia; Follicular Lymphoma; Mantle Cell Lymphoma

Abstract

The subtypes of Non-Hodgkin s lymphoma are very important in analyzing the right treatment plans that would be selected and to know the improvement in the outcomes of patients. Nevertheless, addressing the standard histopathological diagnosis is time consuming and subjective. The paper solutions to the above challenges were proposed by providing a new hybrid deep learning process that entailed the combination of the ViT and ResNet-50 models, deep feature extraction, and deep residual learning. The model was being trained and validated on a series of the histopathological photographs, which provided a test accuracy of 96.70 percent and even outperformed the standalone ViT and ResNet structures as well as the other existing systems.

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  - S. K. Yohesha
AU  - R. Dheepthi
PY  - 2025
DA  - 2025/10/31
TI  - Hybrid Deep Learning Approach for Non-Hodgkin’s Lymhoma using ViT and ResNet
BT  - Proceedings of the International Conference on Intelligent Systems and Digital Transformation (ICISD 2025)
PB  - Atlantis Press
SP  - 36
EP  - 45
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6463-866-0_5
DO  - 10.2991/978-94-6463-866-0_5
ID  - Yohesha2025
ER  -