From Code to Clinic: Trustworthy AI for Medical Imaging

Dear Colleagues,

Artificial intelligence is poised to redefine the landscape of medical imaging, offering profound new capabilities for diagnosis, prognosis, and treatment planning. However, the journey from algorithm development to clinical integration—from code to clinic—is fraught with challenges, and prominent among these is the establishment of trust. For these powerful algorithms to transition from computational models to clinical mainstays, they must earn the confidence of practitioners and patients alike. This Special Issue, therefore, seeks to assemble a premier collection of research dedicated to bridging this crucial translational gap, highlighting a new generation of AI that is not only efficacious but is fundamentally reliable, transparent, and fair, thereby fostering clinical confidence and promoting patient benefit.

We welcome contributions across the full spectrum of medical imaging analysis. Recognizing that the scarcity of high-quality, large-scale annotated datasets remains a significant impediment to model training, we strongly encourage submissions that leverage limited-data paradigms. We welcome novel methodologies across the entire learning spectrum, with particular encouragement for submissions that tackle data scarcity through semi-supervised, weakly supervised, self-supervised, and unsupervised approaches. We invite the submission of manuscripts on a range of topics, including, but not limited to, deep learning applications in MRI and CT reconstruction, super resolution, and artefact reduction; innovations in medical image segmentation and registration; and the use of AI for unsupervised anomaly detection. We are also keenly interested in pioneering integrative methodologies that bridge imaging with the broader sphere of multi-omics (e.g., genomics, proteomics, metabolomics), including, but not limited to, sophisticated computational phenotyping methods and the discovery of novel genotype–phenotype associations. A key emphasis will be placed on the core tenets of trustworthy AI. We are particularly interested in submissions that advance the state of the art in explainable AI (XAI), robust uncertainty quantification, fairness, and the mitigation of bias. Furthermore, we are keen to feature leading-edge research in multimodal image analysis and explorations into how burgeoning technologies, such as generative AI and foundation models, can be responsibly adapted for clinical use.

The purpose of this collection is to curate a landmark Issue that showcases cutting-edge research dedicated to making AI in medical imaging a reliable and indispensable tool for clinicians. We look forward to receiving your contributions to this important and timely endeavor.

Dr. Soumick Chatterjee
Guest Editor

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.

• AI in medical imaging
• deep learning in radiology
• clinical AI integration
• translational AI in medicine
• trustworthy AI in healthcare
• explainable AI (XAI) for medical diagnosis
• AI fairness and bias mitigation
• robust uncertainty quantification
• transparent AI models
• self-supervised learning
• weakly supervised learning
• unsupervised learning
• generative AI in medicine
• foundation models for healthcare
• AI and multi-omics integration
• computational phenotyping
• genotype–phenotype AI discovery
• multimodal image analysis
• anomaly detection
• AI for MRI and CT reconstruction
• medical image super resolution
• AI-driven artefact reduction
• medical image segmentation