With the ever-increasing volume of health-related data, accurate diagnosis based on biomedical intelligence is a new avenue for healthcare development and communication. Biomedical imaging and deep learning have been extensively researched to assist clinicians in making the best diagnosis, treatment, and prevention plans. Notably, accurate diagnosis frequently relies on multi-modal data acquired from numerous sources or sensors. The practice of biological intelligence is founded on big data prescriptive and predictive analytics. Biomedical intelligence systems are comprised of hardware, computational models, databases, and software that maximise the acquisition, transmission, processing, storage, retrieval, analysis, and interpretation of massive amounts of multimodal health-related data. To achieve patient centric healthcare, these systems are currently used in solutions that incorporate a number of technologies, including machine learning (particularly deep learning), artificial intelligence, computer vision, Internet of Things, E-Health, bioinformatics, sensors, and so on. It is projected that the efficiency, accuracy, predictive value, and benefits of biological intelligence would improve dramatically in the next years.

Recent advances in multimodal computing for biological analysis offer a viable alternative for health communication and pathologic diagnosis. As a result, one of the most important scientific subjects in biological diagnosis and data analysis is how to execute efficient multimodal computing to increase user experience and diagnostic accuracy.

This Special Issue aims to provide a forum for biomedical or health communication researchers to share their state-of-the-art theories and methodologies in the multi-modal computing sector, taking into account the underexplored techniques on trustworthy multimodal medical analysis. We invite academic and industrial researchers to contribute high quality original research and review articles in order to promote the research and implementation of multi-modal biological intelligence systems.

Potential topics include but are not limited to the following:

• Machine and deep learning-based multi-modal computing for medical imaging
• New theories and applications of multi-modal biomedical fusion for accurate clinical diagnoses
• Artificial intelligence-based image processing and diagnostic analysis of multi-modal medical imaging data
• Automatic multimodal computing in disease diagnosis and health communications
• Self-supervised, semi-supervised, or unsupervised learning methods for biomedical imaging data
• Wireless networks for biomedical data augmentation and processing
• Reinforcement learning for security, privacy, and trust on bio-medical images
• Collection, analysis, and mining of large-scale multi-modal biomedical databases
• Visualization and understanding of multi-modal biomedical data in healthcare
• New collections on multi-modal/multi-view learning/biomedical engineering