Multimodal Deep Learning and Its Application in Healthcare

Dear Colleagues,

We are pleased to invite you to contribute to this Special Issue entitled "Multimodal Deep Learning and Its Application in Healthcare" in the journal Mathematics.

Recent years have witnessed remarkable progress in deep learning, particularly with the advent of foundation models and multimodal architectures. These models have shown unprecedented capabilities in learning representations across multiple data types such as text, images, signals, and structured data. In healthcare and medicine, where data is often heterogeneous and high-dimensional—ranging from clinical notes and genomic profiles to radiological and pathological images—multimodal learning is particularly transformative.

At the same time, the mathematical underpinnings of these powerful models are still under active development. A better understanding of their theoretical properties, generalization capabilities, and optimization dynamics is critical to ensuring robustness, interpretability, and trustworthiness in medical and healthcare applications.

This special issue aims to bridge the gap between the mathematical theory of deep and foundation models and their applications in multimodal healthcare data. It seeks to explore both rigorous theoretical developments and practical implementations that advance our understanding and use of deep learning in real-world healthcare contexts.

The journal Mathematics focuses on mathematical and theoretical aspects across various scientific fields. Therefore, this special issue is particularly interested in contributions that either:

• Provide mathematical insights into deep learning and multimodal models, including generalization bounds, convergence analyses, optimization theory, or information-theoretic frameworks, or
• Apply these methods to solve important problems in healthcare and biomedical imaging, demonstrating how mathematical foundations contribute to practical advances.

This special issue is expected to gather at least 10 high-quality articles and may be published as a printed book if this goal is achieved.

In this Special Issue, original research articles, theoretical studies, and comprehensive review papers are welcome. Research areas may include (but are not limited to) the following topics:

• Mathematical foundations of deep learning and foundation models
• Theoretical analyses of multimodal architectures (e.g., transformers, diffusion models)
• Convergence theory and generalization bounds for deep neural networks
• Optimization and training dynamics of large-scale models
• Information theory and statistical learning theory in multimodal learning
• Applications of multimodal deep learning in healthcare and medicine
• Medical image analysis using deep learning (e.g., radiology, pathology, 3D reconstruction)
• Fusion of clinical, imaging, and omics data for disease diagnosis and prognosis
• Trustworthy and interpretable AI for healthcare
• Computational models of disease progression using multimodal data

We look forward to receiving your contributions and building a strong collection of high-quality research at the intersection of mathematics, deep learning, and healthcare.

Dr. Xiaoshui Huang
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• multimodal learning
• deep learning theory
• foundation models
• optimization
• generalization
• medical imaging
• healthcare AI
• mathematical modeling
• biomedical data fusion
• theoretical machine learning