A review of deep learning-based information fusion techniques for multimodal medical image classification

TL;DR

This review comprehensively analyzes deep learning-based multimodal fusion techniques in medical image classification, highlighting architectures, challenges, and future directions including Transformer-based methods.

Contribution

It systematically categorizes fusion schemes, evaluates their performance, and discusses challenges and future prospects in multimodal medical image classification.

Findings

Input, intermediate, and output fusion schemes are effective in different scenarios.

Transformer-based fusion techniques show promising potential for future applications.

Handling incomplete data remains a key challenge in multimodal fusion.

Abstract

Multimodal medical imaging plays a pivotal role in clinical diagnosis and research, as it combines information from various imaging modalities to provide a more comprehensive understanding of the underlying pathology. Recently, deep learning-based multimodal fusion techniques have emerged as powerful tools for improving medical image classification. This review offers a thorough analysis of the developments in deep learning-based multimodal fusion for medical classification tasks. We explore the complementary relationships among prevalent clinical modalities and outline three main fusion schemes for multimodal classification networks: input fusion, intermediate fusion (encompassing single-level fusion, hierarchical fusion, and attention-based fusion), and output fusion. By evaluating the performance of these fusion techniques, we provide insight into the suitability of different network architectures for various multimodal fusion scenarios and application domains. Furthermore, we delve into challenges related to network architecture selection, handling incomplete multimodal data management, and the potential limitations of multimodal fusion. Finally, we spotlight the promising future of Transformer-based multimodal fusion techniques and give recommendations for future research in this rapidly evolving field.