2023
DOI: 10.3390/s23187913
|View full text |Cite
|
Sign up to set email alerts
|

Advancing Brain Tumor Classification through Fine-Tuned Vision Transformers: A Comparative Study of Pre-Trained Models

Abdullah A. Asiri,
Ahmad Shaf,
Tariq Ali
et al.

Abstract: This paper presents a comprehensive study on the classification of brain tumor images using five pre-trained vision transformer (ViT) models, namely R50-ViT-l16, ViT-l16, ViT-l32, ViT-b16, and ViT-b32, employing a fine-tuning approach. The objective of this study is to advance the state-of-the-art in brain tumor classification by harnessing the power of these advanced models. The dataset utilized for experimentation consists of a total of 4855 images in the training set and 857 images in the testing set, encom… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2024
2024
2025
2025

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(4 citation statements)
references
References 27 publications
0
4
0
Order By: Relevance
“…The genetic algorithm was also employed to optimize the weights and biases of the initial layer of the CNN. The evaluation metric value of the dice coefficient exceeded 0.90 [11], [12], [13].…”
Section: Literature Reviewmentioning
confidence: 90%
See 1 more Smart Citation
“…The genetic algorithm was also employed to optimize the weights and biases of the initial layer of the CNN. The evaluation metric value of the dice coefficient exceeded 0.90 [11], [12], [13].…”
Section: Literature Reviewmentioning
confidence: 90%
“…HGG, in particular, exhibits a more aggressive nature and is distinguished by its rapid growth. Individuals who receive a diagnosis of high-grade glioma (HGG) generally experience a life expectancy of two years or less [11], [12], [13]. This highlights the significant need for precise and prompt detection to facilitate appropriate treatment and care.…”
Section: Introductionmentioning
confidence: 99%
“…ViTs have demonstrated exceptional performance in various computer vision tasks and exhibit the ability to capture intricate dependencies and patterns within medical images [7]. For instance, Asiri et al [8] conducted a comprehensive study on brain tumor classification using five pre-trained ViT models, achieving a high accuracy of 98.24% with ViT-b32. Their research results surpass those of existing methodologies, demonstrating the potential of ViT models in medical image analysis and providing a benchmark for future brain tumor classification studies.…”
Section: Related Workmentioning
confidence: 99%
“…Abdullah A. Ansari et al. ( 23 ) used a database of 5,712 MRI images and performed classification of brain tumors using a neural network model, with the pre-trained ViTs as the initial layer and introduced BN, Dense layers for task-specification, and developed five models R50-ViT-l16, ViT-l16, ViT-l32, ViT-b16, and ViT-b32. With complex architecture, high accuracy values are gained.…”
Section: Introductionmentioning
confidence: 99%