Machine learning has evolved from pattern recognition and computational learning theory in artificial intelligence, exploring the construction and study of algorithms that learn from data and make predictions. Machine learning is increasingly applied to healthcare, including medical image segmentation, image registration, multimodal image fusion, computer-aided diagnosis, image-guided therapy, image annotation, and image database retrieval, where failure could be fatal.

The purpose of this special issue is to advance scientific research in the broad field of machine learning in healthcare, with focuses on theory, applications, recent challenges, and cutting-edge techniques.

Machine learning techniques (e.g., support vector machines, statistical or mathematical methods, extreme learning machines, deep learning, artificial neural networks, evolutionary algorithms, multiobjective metaheuristics, learning through fuzzy logic, cooperative learning, multiagent learning, and planning) with their theory and applications to the following:

Potential topics include but are not limited to the following:

• Biomedical signal and image processing
• Multimodal information fusion
• Mathematical and statistical models
• Multivariate statistical analysis
• Pattern recognition in biomedical applications
• Advanced computer-aided detection/diagnosis
• Advanced cellular image analysis
• Advanced medical image (database) retrieval
• Advanced medical image reconstruction
• Advanced molecular/pathologic image analysis
• Multimodal neurochemical and/or imaging biomarkers
• Biometrics
• Gait and motion analysis using complex biomedical signals
• Brain computer interfacing
• Clinical big data analytics
• Assistive devices for elderly care and disabled people