Dear Colleagues,

Medical Imaging has commonly enjoyed leveraging and incorporating techniques from the wider field of Computer Vision. On the one hand, compared to natural images (photography), medical images often present relatively lower variability of anatomy, orientation, and field-of-view; on the other hand, clinical applications necessitate much stricter requirements on accuracy. In many fields, recent neural-network based end-to-end machine learning approaches have shown great success and have had a remarkable impact, especially thanks to availability of large annotated datasets. Their effects in Medical Imaging are also prominent, although the lack of large, curated, annotated datasets and sometimes prohibitive 3D data sizes may pose limitations.

In this Section Collection, we aim to cover recent advances and applications in Medical Imaging. We are particularly interested in exploring novel applications of machine and deep learning approaches, although submissions are open to wider range of medical image processing topics. Some potential areas of interest include methods for dealing with low-number (lack) of annotations; optimal/efficient approaches to procure annotations; scalable methods for multi-organ, multi-tissue analysis applications; approaches to deal with non-normalized sequences/imaging data; and techniques to bring in population information.

So, research articles, reviews and studies in this area of study are welcome. We look forward to receiving your contributions.

Dr. Cong Wang

Section editor