Enhanced Deep Learning Methodologies and MRI Selection Techniques for Dementia Diagnosis in the Elderly Population

2024-07-24

arXiv.org

AI Summary

To address the dual challenges of insufficient accuracy and poor interpretability in early Alzheimer’s disease diagnosis using 3D brain MRI, this paper proposes a region-aware slice selection and confidence-driven tri-model ensemble framework. Methodologically, it introduces an adaptive key-region slice filtering mechanism; establishes a collaborative decision-making committee comprising Dem3D ResNet, CNN, and EfficientNet, integrated via confidence-weighted fusion; and incorporates Grad-CAM for interpretable clinical inference. Evaluated on the OASIS and ADNI datasets, the framework achieves 94.12% classification accuracy—significantly outperforming state-of-the-art methods. Ablation studies and XAI visualizations validate the efficacy and generalizability of each component. By jointly optimizing diagnostic accuracy, robustness, and clinical trustworthiness, this work establishes a novel paradigm for AI-assisted early dementia screening.

Technology Category

• Machine Learning: Ensemble Methods
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Algorithmic accountability and transparency on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Dementia, a debilitating neurological condition affecting millions worldwide, presents significant diagnostic challenges. In this work, we introduce a novel methodology for the classification of demented and non-demented elderly patients using 3D brain Magnetic Resonance Imaging (MRI) scans. Our approach features a unique technique for selectively processing MRI slices, focusing on the most relevant brain regions and excluding less informative sections. This methodology is complemented by a confidence-based classification committee composed of three custom deep learning models: Dem3D ResNet, Dem3D CNN, and Dem3D EfficientNet. These models work synergistically to enhance decision-making accuracy, leveraging their collective strengths. Tested on the Open Access Series of Imaging Studies(OASIS) dataset, our method achieved an impressive accuracy of 94.12%, surpassing existing methodologies. Furthermore, validation on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset confirmed the robustness and generalizability of our approach. The use of explainable AI (XAI) techniques and comprehensive ablation studies further substantiate the effectiveness of our techniques, providing insights into the decision-making process and the importance of our methodology. This research offers a significant advancement in dementia diagnosis, providing a highly accurate and efficient tool for clinical applications.

Problem

• Developing a deep learning framework for dementia diagnosis in elderly patients
• Optimizing MRI slice selection to focus on relevant brain regions
• Achieving high diagnostic accuracy with explainable AI techniques

Innovation

• Deep learning framework for dementia diagnosis using MRI
• Selective processing of MRI slices focusing on relevant regions
• Confidence-based classification committee with three deep learning models