Colormap-Enhanced Vision Transformers for MRI-Based Multiclass (4-Class) Alzheimer's Disease Classification

2025-12-18

AI Summary

To address the challenge of four-class Alzheimer’s disease (AD) diagnosis—categorizing subjects as non-demented, or exhibiting very mild, mild, or moderate dementia—from structural MRI scans, this paper proposes a colormap-enhanced Vision Transformer (ViT) framework. Methodologically, grayscale brain MRIs are transformed into physiologically informed pseudocolor images (e.g., Jet, Plasma) to enhance subtle microstructural textures and contrast, then fed into a ViT backbone for global contextual modeling; the model is end-to-end fine-tuned on the OASIS-1 dataset using multiclass cross-entropy loss. The key contribution lies in the first integration of perceptually grounded colormap priors with ViT’s long-range dependency modeling, markedly improving sensitivity to early AD neuropathological changes and interpretability. Experimental results demonstrate state-of-the-art performance: 99.79% classification accuracy and 100% AUC—surpassing contemporary CNN- and Siamese-based approaches (96.1%–99.68%).

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Security and Privacy: Data transparency and provenance

Abstract

Magnetic Resonance Imaging (MRI) plays a pivotal role in the early diagnosis and monitoring of Alzheimer's disease (AD). However, the subtle structural variations in brain MRI scans often pose challenges for conventional deep learning models to extract discriminative features effectively. In this work, we propose PseudoColorViT-Alz, a colormap-enhanced Vision Transformer framework designed to leverage pseudo-color representations of MRI images for improved Alzheimer's disease classification. By combining colormap transformations with the global feature learning capabilities of Vision Transformers, our method amplifies anatomical texture and contrast cues that are otherwise subdued in standard grayscale MRI scans. We evaluate PseudoColorViT-Alz on the OASIS-1 dataset using a four-class classification setup (non-demented, moderate dementia, mild dementia, and very mild dementia). Our model achieves a state-of-the-art accuracy of 99.79% with an AUC of 100%, surpassing the performance of recent 2024--2025 methods, including CNN-based and Siamese-network approaches, which reported accuracies ranging from 96.1% to 99.68%. These results demonstrate that pseudo-color augmentation combined with Vision Transformers can significantly enhance MRI-based Alzheimer's disease classification. PseudoColorViT-Alz offers a robust and interpretable framework that outperforms current methods, providing a promising tool to support clinical decision-making and early detection of Alzheimer's disease.

Problem

• Enhances MRI-based Alzheimer's disease classification using colormap transformations
• Addresses subtle brain structural variations challenging for conventional deep learning models
• Improves feature extraction by amplifying anatomical texture and contrast cues

Innovation

• Pseudo-color MRI images enhance anatomical texture and contrast
• Vision Transformers capture global features for Alzheimer's classification
• Combining colormap transformations with ViT improves MRI-based diagnosis accuracy