Enhancing Brain Tumor Classification Using Vision Transformers with Colormap-Based Feature Representation on BRISC2025 Dataset

Faisal Ahmed

cs.CVMar 22, 2026

Enhancing Brain Tumor Classification Using Vision Transformers with Colormap-Based Feature Representation on BRISC2025 Dataset

Authors: Faisal Ahmed

Organizations: Department of Data Science and Mathematics, Embry-Riddle Aeronautical University, 3700 Willow Creek Rd, Prescott, Arizona 86301, USA

Abstract

Accurate classification of brain tumors from magnetic resonance imaging (MRI) plays a critical role in early diagnosis and effective treatment planning. In this study, we propose a deep learning framework based on Vision Transformers (ViT) enhanced with colormap-based feature representation to improve multi-class brain tumor classification performance. The proposed approach leverages the ability of transformer architectures to capture long-range dependencies while incorporating color mapping techniques to emphasize important structural and intensity variations within MRI scans. Experiments are conducted on the BRISC2025 dataset, which includes four classes: glioma, meningioma, pituitary tumor, and non-tumor cases. The model is trained and evaluated using standard performance metrics such as accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). The proposed method achieves a classification accuracy of 98.90%, outperforming baseline convolutional neural network models including ResNet50, ResNet101, and EfficientNetB2. In addition, the model demonstrates strong generalization capability with an AUC of 99.97%, indicating high discriminative performance across all classes. These results highlight the effectiveness of combining Vision Transformers with colormap-based feature enhancement for accurate and robust brain tumor classification and suggest strong potential for clinical decision support applications.

Figures & tables

Panel of Figure 1 — Figure 1: Representative MRI samples from the BRISC2025 dataset showing the four classification categories: non-tumor, pituitary tumor, meningioma tumor, and glioma tumor. All images are resized to a uniform spatial resolution for consistent model input.

Figure 2: Proposed colormap-enhanced Vision Transformer (ViT) framework for brain tumor classification. The pipeline begins with a grayscale MRI image, which is transformed into a pseudo-color representation to enhance structural patterns and intensity variations. The color-enhanced image is resized to a fixed resolution and divided into non-overlapping patches. Each patch is flattened and linearly projected into a latent embedding space, followed by the addition of positional embeddings and a learnable classification token. The resulting sequence of embedded patches is processed through multiple Transformer encoder layers consisting of multi-head self-attention and feed-forward networks. The final representation of the classification token is passed to a multilayer perceptron (MLP) head to generate the probability distribution over the four tumor classes.

Hyperparameter	Value
Model Backbone	ViT-Base-Patch16-224
Input Image Size	$224\times 224$
Patch Size	$16\times 16$
Number of Classes	4
Batch Size	32
Number of Epochs	50

Table 1: Hyperparameter configuration for the proposed ViT-based model.

Panel of Figure 3 — Figure 3: Evaluation of TDA+DenseNet121 on the OASIS-1 dataset. (a) One-vs-rest ROC curves illustrating discrimination performance across the four Alzheimer’s disease classes. (b) Confusion matrix showing correct and misclassified instances for each class.

OASIS / OASIS-derived MRI Dataset: 4-Class Classification Results
Method	# Classes	Dataset	Prec	Rec	Accuracy	F1-score	AUC
ResNet50 [ 27 ]	4	BRISC2025	98.36	98.36	98.20	98.34	-
ResNet101 [ 27 ]	4	BRISC2025	98.20	98.26	98.09	98.21	-
EfficientNetB2 [ 27 ]	4	BRISC2025	9.851	98.54	98.37	98.52	-
Ours	4	BRISC2025	98.99	98.98	98.90	98.98	99.97

Table 2: Published accuracy results for four-class Alzheimer’s disease classification on OASIS or OASIS-derived MRI datasets.

Explore similar work

Bridging Topology and Deep Representation Learning: A TDA-ViT Fusion Model for Four-Class Brain Tumor Classification
May 30, 2026Faisal AhmedVision Transformer Medical Image Classification
Department of Data Science and Mathematics, Embry-Riddle Aeronautical University, 3700 Willow Creek Rd, Prescott, 86301, Arizona, USA.
an interpretable vision transformer framework for automated brain tumor classification
Apr 23, 2026Chinedu Emmanuel Mbonu, Tochukwu Sunday Belonwu, Okwuchukwu Ejike Chukwuogo +1Vision Transformer Medical Image Classification
Department of Computer Science, Nazarbayev University, Astana · Department of Computer Science, Nnamdi Azikiwe University, Nigeria
Optimized Weighted Voting System for Brain Tumor Classification Using MRI Images
Mar 30, 2026Ha Anh VuBrain Tumor Classification Ensemble Learning
Artificial Intelligence Department, FPT University, Ho Chi Minh City, Vietnam

May 30, 2026J/K move · Enter open · S save

Bridging Topology and Deep Representation Learning: A TDA-ViT Fusion Model for Four-Class Brain Tumor Classification

Faisal Ahmed

Department of Data Science and Mathematics, Embry-Riddle Aeronautical University, 3700 Willow Creek Rd, Prescott, 86301, Arizona, USA.

Vision Transformer Medical Image Classification Brain Tumor Classification Medical Image Representation Learning

Open paper AskPDF arXiv

Accurate brain tumor classification from magnetic resonance imaging (MRI) is a key requirement for early diagnosis and clinical decision-making. Vision Transformers (ViTs) have shown strong performance in medical image analysis by learning global contextual representations, but they often fail to capture intrinsic structural and topological patterns present in tumor regions. To address this limitation, we propose a fusion framework that combines Topological Data Analysis (TDA) features with pretrained Vision Transformer representations for four-class brain tumor classification. In the proposed method, TDA is used to extract complementary topological descriptors that capture geometric structure, connectivity, and shape information from MRI images. In parallel, a pretrained ViT model learns high-level semantic representations from the same images. These two feature spaces are then fused to form a unified and more discriminative representation for classification. The model is evaluated on the BRISC2025 dataset, which contains four brain tumor classes: glioma, meningioma, pituitary tumor, and non-tumor cases. Experimental results show that combining topological and transformer-based features significantly improves performance compared to using either approach alone. The proposed TDA-ViT fusion model achieves an accuracy of 99.10%, precision of 99.27%, recall of 99.15%, F1-score of 99.21%, and an AUC of 99.98%. It also outperforms several state-of-the-art models, including ResNet50, ResNet101, EfficientNetB2, and standalone Vision Transformers. These results demonstrate that topological features provide valuable complementary information that enhances deep representation learning, leading to a robust and highly accurate framework for automated brain tumor classification.

Abstract

Explore similar work

Bridging Topology and Deep Representation Learning: A TDA-ViT Fusion Model for Four-Class Brain Tumor Classification

an interpretable vision transformer framework for automated brain tumor classification

Optimized Weighted Voting System for Brain Tumor Classification Using MRI Images