Machine Learning-Driven Innovations in Biomedical Signal and Image Processing

Dear Colleagues,

The dramatic improvement in biomedical sensing technology has allowed us to acquire more and better information about the human body. The data sources encompass an enormous spectrum of areas, ranging from large phenomena, such as human gait analysis from wearable sensors or eye movement analysis for disease detection, to nanoscale phenomena, such as cell identification in histological microscopy or observing bone growth using micro-CT imaging. Hence, signal and image processing techniques have a central role in the extraction of meaningful information from such sources. In fact, advancements in signal and image processing techniques have allowed us to obtain improvements at a faster pace than the evolution of hardware. Such improvements, in such a wide landscape of data sources, have enhanced the need for advanced and specific technologies, tailored to each situation, either to improve quality or to estimate high-level information.

In addition, in recent years, artificial intelligence has been shown to offer high-performance mechanisms to deal with these situations, offering robust data models that are able to cope with large, nonlinear data spaces. Training algorithms have also become increasingly efficient, being able to keep up with the evolution of data models. Good generalization capabilities and high fidelity can be achieved, even with apparently limited or sparse data. Many of these systems outperform human capacities, and their use is becoming an established standard.

However, with such a fast evolution pace, the application landscape continues to grow, while many challenges still remain. For each type of signal or image source, improvements can be pursued in the following areas:

• Data collection, compression, and visualization;
• Data exploration;
• Feature extraction, selection, enhancement, and analysis;
• Data augmentation;
• Model selection, tuning, and explainability;
• Transfer learning;
• Parameter space exploration.

The possibility of improving disease detection or enhancing therapies, boosting the quality of life of many people, makes this one of the most exciting current research areas.

For this Special Issue, prospective authors are invited to submit innovative research aimed at solving challenges in application areas such as, inter alia, clinical (diagnostic, rehabilitation, and monitoring) and biomedical research (histology, anatomy, physiology) and human–machine interfacing (acquisition technologies and stimulation). Some of the encompassed data sources include, but are not limited to, the following:

• Signals: EEG, EMG, ECG, EOG, electroretinogram (ERG), evoked potentials, local field potentials, deep brain stimulation (open-/closed-loop), magnetoencephalography (MEG), actigraphy, and gait analysis;
• Medical imaging: X-ray, PET, CT or micro-CT, PET-CT, MRI, and SPECT;
• Biological and molecular imaging: photoacoustic/coherence tomography (PAT/OCT), MRS, mass spectrometry, optical imaging, phase-contrast imaging, and laser scanning confocal microscopy (LSCM);
• Human–machine interaction: wearable data (gaze, dynamics, heart rate), stimulation (touch, vision), emotion, disease, and altered states (drunk, sleepiness). 

Dr. Luis Coelho
Prof. Dr. João Paulo Ramos Teixeira
Prof. Dr. João Paulo Pereira do Carmo
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.

• signal processing
• image processing
• machine learning