A Generative Imputation Method for Multimodal Alzheimer's Disease Diagnosis

2025-08-12

AI Summary

To address the prevalent issue of missing modalities (e.g., absent T1-weighted MRI or functional connectivity data) in multimodal Alzheimer’s disease (AD) diagnosis, this paper proposes a generative adversarial network (GAN)-based cross-modal imputation method. The method conditions on available modalities to reconstruct missing ones, preserving critical pathological features and inter-modal consistency while significantly reducing information bias inherent in conventional imputation techniques. Innovatively, it jointly models anatomical structure (via T1-weighted MRI) and functional network connectivity, enabling complementary, disease-specific generation. Evaluated on AD classification, the proposed approach achieves a 9.0% accuracy improvement over state-of-the-art imputation baselines. This enhancement substantially boosts the robustness and diagnostic performance of multimodal AD assessment under incomplete data conditions.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Multimodal data analysis can lead to more accurate diagnoses of brain disorders due to the complementary information that each modality adds. However, a major challenge of using multimodal datasets in the neuroimaging field is incomplete data, where some of the modalities are missing for certain subjects. Hence, effective strategies are needed for completing the data. Traditional methods, such as subsampling or zero-filling, may reduce the accuracy of predictions or introduce unintended biases. In contrast, advanced methods such as generative models have emerged as promising solutions without these limitations. In this study, we proposed a generative adversarial network method designed to reconstruct missing modalities from existing ones while preserving the disease patterns. We used T1-weighted structural magnetic resonance imaging and functional network connectivity as two modalities. Our findings showed a 9% improvement in the classification accuracy for Alzheimer's disease versus cognitive normal groups when using our generative imputation method compared to the traditional approaches.

Problem

• Address incomplete multimodal data in Alzheimer's diagnosis
• Overcome limitations of traditional imputation methods like bias
• Improve classification accuracy using generative adversarial networks

Innovation

• Generative adversarial network for missing data
• Reconstructs missing modalities preserving disease patterns
• Improves classification accuracy by 9%