Artificial Intelligence in Biomedical Imaging and Signal Processing

Dear Colleagues,

Advances in signal processing techniques have transformed the use of artificial intelligence in diagnosing several diseases using biomedical images. The emergence of powerful High-Performance Computing systems (HPCs) has opened new doors for the processing of large amounts of medical data including images. The availability of these large image datasets has resulted in increasing applications of several deep learning techniques such as Convolutional Neural Networks and Vision Transformers for pattern recognition, disease classification, and image segmentation.  The application of these AI methods has continued to gain popularity in several areas in the medical field where imaging is used as a form of diagnosis. Several forms of images from different electronics machines has been used for this purpose including X-ray, CT, MRI, Ultrasound, Infra-red, etc. Additionally, multimodal imaging, which combines data from multiple imaging forms, is increasingly being explored to provide more comprehensive diagnostic insights and improve the accuracy of AI-driven diagnoses.

The impacts of artificial intelligence such as machine learning and deep learning algorithms have enhanced overall performance analysis by using varieties of data such as biomedical data, sound and signal data, wearable sensor data, medical records, etc. The adoption of these algorithms has improved the performance rate and computational complexity through the use of HPC, thus enhancing real-time disease diagnosis.

With all of these advances and their advantages comes several challenges such as overcoming issues of limited or imbalance class, image quality and feature variability issues; thus, there is a need for improved feature extraction and segmentation approaches. Finally, the need for advanced DL or ML techniques using efficient finetuning and parameter selection will not only achieve reliable diagnostic results but also improve model generalization and mitigate overfitting. Moreover, in the case of multimodal imaging, integrating data from different modalities presents its own set of challenges, as each modality has distinct characteristics and resolutions, making it difficult to harmonize the data for accurate feature extraction and analysis.

Despite these challenges, opportunities abound for progress in developing bespoke artificial intelligence technologies for medical images to diagnose patient outcomes. Research should focus on applying artificial intelligence methods by proposing relevant image processing techniques, enhancing feature extraction methods, and advancing segmentation and augmentation approaches.

Topics of interest include the following:

• Artificial intelligence in medical images;
• Real-time detection and image processing;
• Image segmentation in medical scans;
• AI-assisted detection tools;
• Advanced augmentation for medical images;
• AI Ethics: AI deployment in medical imaging;
• Explainable AI in medical diagnosis;
• Multimodal fusion AI for medical diagnosis.

Dr. Olusola Oluwakemi Abayomi-Alli
Dr. Olamilekan Shobayo
Guest Editors

Modupe Odusami
Guest Editor Assistant

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. Diagnostics 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 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.

• medical image processing
• healthcare
• artificial intelligence
• machine learning
• deep learning
• computer vision
• AI-assisted
• explainable ai
• segmentation
• augmentation
• multimodal fusion