Artificial Intelligence in Medical Imaging: Innovations and Diagnostic Applications

Dear Colleagues,

In a range of medical imaging modalities—such as computed tomography (CT), magnetic resonance imaging (MRI), ultrasound, positron emission tomography (PET), pathological imaging, and X-rays—artificial intelligence (AI), and in particular deep learning, has shown impressive performance. Moreover, in contrast to task-specific models, foundation models may be able to help with the complex and multifaceted problems that arise in clinical practice. Also, explainable AI promotes reliable, broadly applicable, and clinically interpretable solutions for accurate diagnosis and treatment, bridging the gap between black-box AI models and practical implementation.

Recently, a novel family of artificial intelligence models called Vision-Language Models (VLMs) have combined natural language comprehension with image analysis. These models can generate, comprehend, or react to clinical narratives in addition to interpreting medical images because they are trained on extensive datasets of matched images and text. VLMs connect visual features to clinical language. Complex tasks like abnormality identification, image labeling, and finding images with similar diagnoses (i.e., cross-modal retrieval) can be automated by VLMs.

This Special Issue encourages original research on AI models for 3D medical image analysis. We particularly encourage contributions that examine theoretical developments, practical applications, or empirical evaluations. These should focus on improving clinical applicability and addressing problems including data variability, annotation scarcity, and multi-modal integration. Techniques that prioritize interpretability, scalability, and robustness must be highlighted in submissions.

The topics of interest include, but are not limited to, the following:

• Advanced multi-modal techniques integrating diverse medical data (MRI, CT, X-ray, ultrasound) for comprehensive analysis.
• Development of AI, foundational, and VLMs models tailored for medical analysis in 2D or 3D data and performance enhancement in multi-modal medical imaging.
• Weakly supervised and semi-supervised learning models for addressing annotation limitations.
• AI, foundational, and VLMs models for early disease detection and personalized diagnostics.
• Real-world clinical validation and applications of AI, foundational models, and VLM models in healthcare environments.
• Explainable AI approaches in medical imaging for clinical interpretability to make medical models more accessible to clinicians, including visualization and feature-attribution tools,
• Development of benchmark datasets and metrics for evaluating AI, foundational models, and VLM models in medical contexts.
• Radiomics and imaging biomarkers derived from deep learning.

Prof. Dr. Ayman El-Baz
Prof. Dr. Moumen Elmelegy
Dr. Asem M. Ali
Dr. Ali H. Mahmoud
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. 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 imaging
• artificial intelligence
• disease diagnosis
• radiomics