What question did this study set out to answer?

The study aims to evaluate the impact of preprocessing pipeline depth on the performance of deep learning models for brain tumor classification.

February 19, 2026Cluster Computing0 citationsOpen Access

Comprehensive evaluation of preprocessing pipeline depth in deep learning-based brain tumor classification using CNN and vision transformer architectures

FSFatma Zehra Solak

Key Points

The study aims to evaluate the impact of preprocessing pipeline depth on the performance of deep learning models for brain tumor classification.
Developed a five-stage preprocessing framework: denoising, contrast enhancement, edge sharpening, gamma correction, normalization.
Applied the framework to a balanced MRI dataset of 8,000 images.
Tested multiple architectures, including CNNs and Vision Transformers, for accuracy and robustness.
Significant accuracy improvement (up to +4.5%) observed with deeper preprocessing stages.
DenseNet121 and ViT Large showed the highest accuracy improvements.
ViT Base R50 and VGG19 identified as the most stable architectures under varying preprocessing conditions.
ViT Base R50 ranked highest for clinical deployment based on a composite clinical balance score.

Abstract

Abstract Brain tumor classification via MRI remains a critical challenge. This study presents a systematic evaluation of how preprocessing pipeline depth influences the performance of deep learning models, including both convolutional neural networks (CNNs) and Vision Transformer (ViT) architectures. A five-stage progressive preprocessing framework (denoising, contrast enhancement, edge sharpening, gamma correction, normalization) was designed and evaluated on a balanced MRI dataset of 8,000 images (glioma, meningioma, pituitary, normal). Comprehensive analysis revealed significant accuracy improvements (up to + 4.5%) with deeper preprocessing, especially for DenseNet121 and ViT Large. Stability analysis identified ViT Base R50 and VGG19 as the most robust architectures across varying preprocessing intensities. A composite clinical balance score, integrating performance, efficiency, and parameter load, ranked ViT Base R50 as the most suitable model for clinical deployment. This study emphasizes the pivotal role of preprocessing and proposes evidence-based guidelines for its design in clinical AI.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper