Artificial Intelligence for Medical Imaging and Applications

Dear Colleagues,

Advanced medical imaging modalities and computational technologies have revolutionized medical procedures and patient care. Artificial intelligence (AI), particularly deep learning and foundation models, has rapidly developed and could transform the capabilities of the medical field in understanding, interpreting, and analyzing complex medical images and videos. It has the potential to improve disease diagnoses and clinical intervention procedures, offering high-quality training and patient care.

However, fully realizing the benefits of AI-assisted medical applications is hindered by significant challenges, including data scarcity for model training and the lack of concern for the distinctive properties and characteristics of medical images, tomograms, and endoscopic videos compared to general photos and videos. Furthermore, different imaging sequences, contrast phases or modalities, as well as text descriptions and metadata, when interpreted as a whole, provide rich synergistic information with the added diagnostic insight or complementary value. Finally, research in the field of medical imaging and interventional procedures should address ethical considerations and validation through real-world applications. In addition, AI-assisted medical imaging can be used to monitor the efficacy of therapeutic interventions over time with real-world implementation.

This Special Issue of the Journal of Imaging seeks original works that showcase innovative research results, transformative projects, surveys, real-world medical applications, and user experiences that advance the use of artificial intelligence for medical imaging and applications.

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

• AI-based lesion detection in medical images and videos;
• Synthetic data generation and cross-validation;
• Clinical reporting using vision language generative AI;
• The AI interpretation of tomographic images from CT and MRI;
• Multimodal medical data fusion;
• Visual questions and answering about medical image and video content;
• Medical content retrieval;
• Object detection and tracking;
• Simultaneous multimodality model training and fine turning;
• Supervised learning for medial image and video understanding;
• Self-supervised and contrastive learning for medical image and video understanding;
• Medical image pre-processing for deep learning models and applications;
• The segmentation of anatomic structures;
• Automatic annotation and captioning medical images and videos;
• Color space conversion and texture enhancement for medical images and videos;
• Large-scale pretraining for medical images and videos;
• Vision language model reasoning for medical applications;
• 3D medical image analysis with deep learning models;
• Medical image analysis with LLMs;
• Multimodal datasets for medical applications;
• AI-assisted real-time procedures;
• Metadata embedding in medical images and videos;
• An assessment of AI models in clinical workflows;
• AI-enhanced educational content generation;
• Simulated image, video, and 3D data generation from text input;
• Open-source datasets;
• 3D medical visualization and modeling;
• Multimodal transformers for integrating clinical text and medical images;
• Interactive diagnosis systems with LLM-based clinical decision support;
• Image denoising, super-resolution, and synthesis techniques for enhancing medical images and videos;
• Temporal transformer models for disease progression prediction in longitudinal imaging;
• The cross-domain generalization of medical AI models using foundation model adaptation;
• Conversational agents for patient education and preoperative planning via multimodal AI;
• AI-driven augmented and virtual reality for clinical environments, procedural guidance, and medical training.

Prof. Dr. Wen Tang
Dr. Jinhua Liu
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. Journal of Imaging 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.

• artificial intelligence
• deep learning
• machine learning
• computer vision, image processing and computer graphics
• medical image and video analysis
• multimodal foundation model
• gaussian splatting
• neural rendering
• lesion detection
• organ segmentation surgical tool tracking
• computer-aided diagnosis
• medical visualization
• surgical navigation
• clinical integration
• bid data in medical imaging
• virtual and augmented reality