Deep Learning of Biomedical Data Analysis (DLBDA)

Dear Colleagues,

Biomedical data can be large, but also have great heterogeneity, from small molecules to omics data, biomedical imaging data, clinical data and electronic medical records. Data quality can also be very heterogeneous, as data types can range from analog to digital and text, and can have a complex association structure, such as sequence, tree and other graphics, the size of which is usually different. Biomedical data also span many orders of magnitude in space and time, covering countless different phenomena. The improvement of sensors and other instruments, computers, databases and the Internet, coupled with the development of new high-throughput methods often lead to a large amount of data. However, even in the era of Big Data, the data pattern is still very changeable in terms of the amount of available data.

With the central position of deep learning in artificial intelligence (AI) and machine learning, it is not surprising that deep learning is widely used in biomedical data analysis. However, what people do not know is that some of the earliest applications of deep learning are in this field, and the complexity of the problems raised by biomedical analysis has inspired the development of new deep learning methods for many years. The core of applying the deep learning method to biomedical data is to develop methods that can deal with different types of data, especially variable size structured data. The breadth, complexity and rapidly expanding scale of biomedical data stimulate the development of new deep learning methods.

Entropy, and information theory in general, has been applied many times to biomedical data analysis, because randomness and complexity are often crucial characteristics in the functioning of the human body. In this context, the recent developments of deep learning techniques, information theoretical learning, and deep neural networks in particular, have drawn the attention of researchers in the field biomedical data analysis. The application of these techniques in biomedical data analysis brings scientific discovery and practical solutions.

This Special Issue focuses on the application of different state-of-the-art deep learning techniques to biomedical data analysis. Submissions must be unpublished in advance and must not currently be considered for publication elsewhere. Topics of interest include, but are not limited to:

• Review of deep learning methods in biomedical data analysis based on information theory;
• Deep learning of biomedical data analysis based on entropy;
• Deep learning of biomedical data analysis based on mutual information;
• Deep learning of biomedical data analysis based on information divergence;
• Deep learning of variable-size structured data based on information theory;
• Deep learning in chemoinformatics, proteomics, and genomics and transcriptomics;
• Deep learning in healthcare-based on information theory.

Prof. Dr. Dhanjoo N. Ghista
Dr. Kelvin Wong
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. Entropy 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 2600 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.

• deep learning
• machine learning
• biomedical data analysis
• information theory
• entropy
• mutual information
• information divergence
• biomedical signal processing
• biomedical image processing
• medical informatics