Artificial Intelligence Techniques for Medical Imaging and Computational Biology

Dear Colleagues,

Emerging artificial intelligence techniques are changing medical and biological procedures and are enabling new ways to deal with the wealth of information coming from clinical exams and tests. Notwithstanding, these specific domains generate new challenges where new computational approaches involving machine learning (ML) or computational intelligence (CI) techniques are needed. Starting from the nature of the processed data, the computational approach can require multiple and specific techniques.

Concerning image processing, ML and CI techniques can effectively perform image processing operations (e.g., segmentation, annotation, co-registration, and classification), in the fields of neuroimaging and oncological imaging. Although the manual approach often remains the golden standard in some tasks (e.g., segmentation and annotation), ML can be employed to support the work of researchers and clinicians. Regarding biology, ML- and CI-based strategies have been continuously applied to solve problems in bioinformatics and computational systems biology (e.g., alignments, dimensionality reduction, and parameter estimation).

In addition, these fields often present new clustering and classification challenges, as well as combinatorial problems, which can be effectively addressed using novel strategies based on ML and CI techniques. Frequently used approaches include support vector machines (SVMs) for classification problems, graph-based methods, artificial neural networks (ANNs), evolutionary computation (EC), and swarm intelligence (SI) techniques.

New trends and interesting research topics have shown deep learning (DL) approaches to be very successful in regard to computer vision and bioinformatics tasks, owing to their ability to automatically extract hierarchical descriptive features from input images or gene expression data. They have also been used in the oncological, neuroimaging, and microscopy imaging domains for automatic disease diagnosis, tissue segmentation, and even synthetic image generation.

Some relevant problems arise from the generalization abilities of the employed deep ANNs or CNNs, considering the high number of required parameters and the reduced sample size of the datasets. Consequently, parameter-efficient design paradigms specifically tailored to biomedical applications ought to be devised, such as by exploiting CI-based techniques (e.g., EC, SI, and neuroevolution).

Considering that many of these topics represent hot topics within clinical research, advanced ML techniques can be suitably exploited to combine heterogeneous sources of information, allowing for multiomics data integration. These types of analyses may represent a significant step towards personalized medicine.

We are pleased to invite you to contribute to this Special Issue, which will cover highly relevant scientific aspects in this field.

This Special Issue aims to provide a forum to publish original research papers covering state-of-the-art and novel algorithms, methodologies, and applications of AI methods for biomedical data analysis and processing, ranging from classic ML to DL.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• ML and CI techniques for the segmentation, co-registration, classification, or dimensionality reduction of medical images.
• Generative adversarial models for medical image super-resolution, denoising, and synthesis.
• Deep learning for neuroimaging and oncological imaging analysis.
• Application of graph theory to MRI and functional MRI (fMRI) data.
• Computational modeling and analysis of neuroimaging.
• Radiomic analyses for disease phenotyping.
• Radiogenomics for intra- and intertumoral heterogeneity evaluation.
• CI methods for optimizing biomedical data analysis tasks.
• Integration of multiomics data.
• ML and CI techniques for combinatorial problems in bioinformatics and computational biology.
• Deep neural networks for classification tasks in single-cell data analysis.
• New clustering approaches for single-cell data analysis.
• Feature interpretability.
• Model explainability.
• Graph neural networks.

We look forward to receiving your contributions.

Dr. Carmelo Militello
Dr. Leonardo Rundo
Dr. Andrea Tangherloni
Dr. Fulvio Zaccagna
Dr. Filippo Vella
Dr. Vincenzo Conti
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. Applied Sciences is an international peer-reviewed open access semimonthly 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 2400 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.

• machine learning
• deep learning
• computational intelligence
• biomedical image analysis
• radiomics
• radiogenomics
• bioinformatics
• computational biology
• multiomics data
• single-cell data analysis