Machine Learning Methods in Biomedical Imaging

Dear Colleagues,

The field of biomedical imaging is ever-growing with new applications proposed and adopted each year in all aspects of healthcare and biomedical research. The complexity and interconnectedness of the information contained in the biomedical imaging ecosystem has enhanced the clinical decision process, and has diversified the scientific method and how it is applied to medicine and research. This is a golden age for wide-spread applications of artificial intelligence technology, which taking advantage of computing performance advances and big data availability, has been proven to perform as well or better compared to human experts in pattern detection and classification, output consistency, and robustness against confounding factors.

Machine learning methods evolved from original artificial intelligence standards, as scientists optimized algorithms capable of learning from training data sets in order to make inferences for various given problems. Proposed for large scale deployment in healthcare imaging for chronic disease screening and early detection (cardiac disease and cancer), machine learning technologies are experiencing a dynamic expansion in the world of biomedical research. All aspects of image formation, processing and analysis of pre- and clinical studies, pathology and microscopy images, with applications in and beyond medicine, biological and pharmaceutical research, with modalities ranging from x-ray, MRI, molecular imaging, optical, ultrasound, at macroscopic and microscopic scales, all have been the subject of machine learning algorithmic implementation. The global expanse machine learning applications in biomedical imaging research is a testament to the resources that the scientific community is vesting towards overcoming the challenges of bringing these paradigm changing advances from research laboratories to clinical applications.

In this special issue “Machine Learning Methods in Biomedical Imaging”, we captured a snapshot of current efforts that are being made to commit these algorithms to a new evolution step in healthcare standards, one where the clinical process is enhanced by the sublimation of prior knowledge. In defining the scope of the special issue, it was obvious that while the machine learning algorithms architecture and typical deployment converged to certain patterns, their applications were utmost diverse. Therefore, we present topics of interest including but not limited to:

• Biomedical image segmentation
• Biomedical image classification
• Biomedical image registration
• Biomedical image denoising
• Biomedical image synthesis (e.g., intra- or inter-modalities)
• Biomedical image reconstruction
• Biomedical image representation and compression
• Biomedical image restoration and enhancement
• Biomedical image argumentation/generation
• Motion/time series biomedical analysis
• Quantitative biomedical image analysis/quantitative imaging biomarkers
• Radiomics and texture representation/analysis.

Dr. Marian Axente
Dr. Xiaofeng Yang
Dr. Yibo Xie
Dr. Suk Whan Yoon
Guest Editors

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. Bioengineering is an international peer-reviewed open access monthly 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 2700 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.

• AI
• machine learning
• deep learning
• biomedical image analysis