Application of Deep Learning and Convolution Neural Networks for Social Healthcare

Dear Colleagues,

Today, data collection and analysis are becoming increasingly important in a variety of application domains as novel technologies advance. The healthcare domain is one of the research fields that has benefitted the most from the new availability of big sources of data and recent successes in automated data processing, becoming one of the most known and active producers of digital information. Different studies show how the quantity of produced electronic data is increasing over time, with some recent estimates indicating it to exceed the Yottabyte size within the next years.

If the growing amount of available data will help the design of effective disease prevention and therapies’ assessment procedures, it may result in an increased effort that physicians have to undergo to perform a diagnosis. The task is made even more difficult by high inter/intra patient variability, the availability of different image acquisition techniques and the need of being able to take into account media coming from different sensors and sources. Moreover, the rise of software-based tools for diagnosis and prognosis working with multimodal data (such as genomics, radiomics, and proteomics, to name a few) is opening up more and more opportunities.

To face this problem, physicians make use of several tools that assist in the analysis of biomedical data, including both those directly aimed at processing data, such as CAD (computer-aided detection and diagnosis), text miners, etc., and those implicitly supporting the research, such as federated learning, edge computing, etc. Among these, artificial intelligence is without any doubt what has been mostly supporting the recent increase in medical data processing and analysis, with artificial neural networks, including both shallow and deep architectures, playing a leading role.

Thus, the aim of this Special Issue is to gather recent advances in the application of deep learning and convolution neural networks (CNN) for social healthcare, to help advance scientific research within the broad field of medical-data-using machine learning, deep learning and big data techniques. In particular, the aim is to analyze how these techniques can be applied to the entire medical processing chain, from acquisition to retrieval, detection and disease prediction. In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Medical image processing (e.g., classification, segmentation, etc.);
• Bit-omics (e.g., radiomics, genomics, etc.);
• Text mining (e.g., automatic clinical records parsing and analysis);
• Precision and personalised medicine in healthcare;
• Drug discovery and protein analysis (e.g., gene analysis);
• Federated learning (e.g., multi-centre training);
• Trustworthy AI in medicine (e.g. privacy, fairness and equity in medical data processing);
• Secure storage and processing of medical data (including attack and defence strategy);
• Adversarial attacks and poisoning in medical data;
• Information systems ;
• Information retrieval;
• Computer-aided diagnosis (CAD);
• Digital health records (e.g., clinical data processing and storage);
• Multimodal and multiple sources Learning (e.g., multi-protocol processing);
• Green healthcare (e.g. CO2 footprint reduction in medical data processing);
• Synthetic data generation and data augmentation in medicine;
• Social media analysis for social wellness (e.g., rumours, fake news, sentiment analysis about drugs, etc.);
• Long-life learning;
• Edge-computing in medical domain;
• Wearable devices, sensors and their analytics.

We look forward to receiving your contributions.

Dr. Stefano Marrone
Dr. Paolo Soda
Dr. Francesco Flammini
Dr. Ermanno Cordelli
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. Big Data and Cognitive Computing 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 1800 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.

• medical data mining
• federated learning
• trustworthy AI
• multimodal learning
• synthetic data
• precision medicine