Machine learning (ML) is the study of computer algorithms that learn automatically through experience. ML is a subset of artificial intelligence. ML algorithms build a mathematical model based on sample data, e.g., "data-driven models," to make decisions or diagnoses on unseen new samples. On the other side, ML is closely related to the field of optimization. Many ML models are formulated to minimize some loss function, i.e., unobserved generalization error, on a set of independent training samples.

The difference between the two fields arises from the goal of generalization. While optimization algorithms attempt to minimize the loss on a training set (empirical risk), ML is concerned with minimizing the loss on the test set (actual risk). In other words, ML provides a framework for studying the problem of inference whilst the field of optimization is focused on the development of algorithms for hyperparameter tuning.

ML holds excellent promise as an addition to the arsenal of analysis and comprehension tools for medical images. Besides, ML can accomplish many tasks, such as registration, preprocessing, classification, prediction, inference, etc.

This special issue plans to report the recent progresses on optimization algorithms and machine learning techniques in medical image analysis. The medical data can be obtained from single/multiple imaging modalities, such as computed tomography, magnetic resonance imaging, positron emission tomography, ultrasound, single photon emission computed tomography, photoacoustic tomography, magnetic particle imaging, optical microscopy and tomography, electron tomography, and atomic force microscopy, etc.

The ultimate goal of this special issue is to promote research and development of optimization and machine learning theories and their applications in medical image analysis by publishing high-quality research articles and surveys in this rapidly growing interdisciplinary field.

Topics of interest should include, but not be limited to
• Supervised/unsupervised learning on registration, preprocessing, classification, and prediction over medical images analysis
• Deep learning for medical image/video analysis
• Machine learning and optimization of big data in imaging
• Segmentation, registration, and fusion of medical images
• Validation of ML results on medical image analysis
• Explainable ML on medical image analysis
• Transfer learning on medical image analysis
• Explainable ML on medical image analysis
• Computer-aided diagnosis
• Image formation/reconstruction and image quality assessment
• Visualization in medical imaging