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

Asiri, Abdullah A.; Shaf, Ahmad; Ali, Tariq; Pasha, Muhammad Ahmad; Aamir, Muhammad; Irfan, Muhammad; Alqahtani, Saeed; Alghamdi, Ahmad Joman; Alghamdi, Ali H.; Alshamrani, Abdullah Fahad A.; Alelyani, Magbool; Alamri, Sultan

doi:10.3390/s23187913

Cited by 14 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

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%

“…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%

See 1 more Smart Citation

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation

Zakariah,

Al-Razgan,

Alfakih

2024

Preprint

View full text Add to dashboard Cite

Brain tumors are one of the leading causes of cancer death; screening early is the best strategy to diagnose and treat brain tumors. Magnetic Resonance Imaging (MRI) is extensively utilized for brain tumor diagnosis; nevertheless, achieving improved accuracy and performance, which is a critical challenge in most of the previously reported automated medical diagnostics, is a difficult problem. The study introduces the Dual Vision Transformer-DSUNET model, which incorporates feature fusion techniques to provide precise and efficient differentiation between brain tumors and other brain regions by leveraging multi-modal MRI data. The impetus for this study arises from the necessity of automating the segmentation process of brain tumors in medical imaging, a critical component in the realms of diagnosis and therapy strategy. To tackle this issue the BRATS 2020 dataset is employed, an extensively utilized dataset for the segmentation of brain tumors. This dataset encompasses multi-modal MRI images, including T1-weighted, T2-weighted, T1Gd (contrast-enhanced), and FLAIR modalities. The proposed model incorporates the dual vision idea to comprehensively capture the heterogeneous properties of brain tumors across several imaging modalities. Moreover, the utilization of feature fusion techniques is implemented to augment the amalgamation of data originating from several modalities, hence enhancing the accuracy and dependability of tumor segmentation. The evaluation of the Dual Vision Transformer-DSUNET model's performance is conducted by employing the Dice Coefficient as a prevalent metric for quantifying segmentation accuracy. The results obtained from the experiment exhibit remarkable performance, with Dice Coefficient values of 91.47% for enhanced tumors, 92.38% for core tumors, and 90.88% for edema. The cumulative Dice score for the entirety of the classes is 91.29%. In addition, the model has a high level of accuracy, roughly 99.93%, which underscores its durability and efficacy in the task of segmenting brain tumors. Experimental findings demonstrate the integrity of the suggested architecture, which has quickly improved the detection accuracy of many brain diseases.

show abstract

Section: Literature Reviewmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation

Zakariah,

Al-Razgan,

Alfakih

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…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%

Automated Ischemic Stroke Classification from MRI Scans: Using a Vision Transformer Approach

Abbaoui,

Retal,

Ziti

et al. 2024

JCM

View full text Add to dashboard Cite

Background: This study evaluates the performance of a vision transformer (ViT) model, ViT-b16, in classifying ischemic stroke cases from Moroccan MRI scans and compares it to the Visual Geometry Group 16 (VGG-16) model used in a prior study. Methods: A dataset of 342 MRI scans, categorized into ‘Normal’ and ’Stroke’ classes, underwent preprocessing using TensorFlow’s tf.data API. Results: The ViT-b16 model was trained and evaluated, yielding an impressive accuracy of 97.59%, surpassing the VGG-16 model’s 90% accuracy. Conclusions: This research highlights the ViT-b16 model’s superior classification capabilities for ischemic stroke diagnosis, contributing to the field of medical image analysis. By showcasing the efficacy of advanced deep learning architectures, particularly in the context of Moroccan MRI scans, this study underscores the potential for real-world clinical applications. Ultimately, our findings emphasize the importance of further exploration into AI-based diagnostic tools for improving healthcare outcomes.

show abstract

“…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%

A fine-tuned vision transformer based enhanced multi-class brain tumor classification using MRI scan imagery

Reddy,

Janapati

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

Brain tumors occur due to the expansion of abnormal cell tissues and can be malignant (cancerous) or benign (not cancerous). Numerous factors such as the position, size, and progression rate are considered while detecting and diagnosing brain tumors. Detecting brain tumors in their initial phases is vital for diagnosis where MRI (magnetic resonance imaging) scans play an important role. Over the years, deep learning models have been extensively used for medical image processing. The current study primarily investigates the novel Fine-Tuned Vision Transformer models (FTVTs)—FTVT-b16, FTVT-b32, FTVT-l16, FTVT-l32—for brain tumor classification, while also comparing them with other established deep learning models such as ResNet50, MobileNet-V2, and EfficientNet - B0. A dataset with 7,023 images (MRI scans) categorized into four different classes, namely, glioma, meningioma, pituitary, and no tumor are used for classification. Further, the study presents a comparative analysis of these models including their accuracies and other evaluation metrics including recall, precision, and F1-score across each class. The deep learning models ResNet-50, EfficientNet-B0, and MobileNet-V2 obtained an accuracy of 96.5%, 95.1%, and 94.9%, respectively. Among all the FTVT models, FTVT-l16 model achieved a remarkable accuracy of 98.70% whereas other FTVT models FTVT-b16, FTVT-b32, and FTVT-132 achieved an accuracy of 98.09%, 96.87%, 98.62%, respectively, hence proving the efficacy and robustness of FTVT’s in medical image processing.

show abstract

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

Cited by 14 publications

References 27 publications

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation

Dual Vision Transformer-DSUNET With Feature Fusion for Brain Tumor Segmentation

Automated Ischemic Stroke Classification from MRI Scans: Using a Vision Transformer Approach

A fine-tuned vision transformer based enhanced multi-class brain tumor classification using MRI scan imagery

Contact Info

Product

Resources

About