Generative Models for Medical Image Creation and Translation: A Scoping Review
Sensors · 2026
DOI: 10.3390/s26030862 ↗Kurz gefasst
Scoping Review in der Zeitschrift Sensors, 2026. Verfasst von Haowen Pang und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China. Hauptthemen laut MEDLINE: Autoencoder, Diagnostic Imaging, Generative Adversarial Networks, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 301 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Generative models play a pivotal role in the field of medical imaging. This paper provides an extensive and scholarly review of the application of generative models in medical image creation and translation. In the creation aspect, the goal is to generate new images based on potential conditional variables, while in translation, the aim is to map images from one or more modalities to another, preserving semantic and informational content. The review begins with a thorough exploration of a diverse spectrum of generative models, including Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Diffusion Models (DMs), and their respective variants. The paper then delves into an insightful analysis of the merits and demerits inherent to each model type. Subsequently, a comprehensive examination of tasks related to medical image creation and translation is undertaken. For the creation aspect, papers are classified based on downstream tasks such as image classification, segmentation, and others. In the translation facet, papers are classified according to the target modality. A chord diagram depicting medical image translation across modalities, including Magnetic Resonance Imaging (MRI), Computed Tomography (CT), Cone Beam CT (CBCT), X-ray radiography, Positron Emission Tomography (PET), and ultrasound imaging, is presented to illustrate the direction and relative quantity of previous studies. Additionally, the chord diagram of MRI image translation across contrast mechanisms is also provided. The final section offers a forward-looking perspective, outlining prospective avenues and implementation guidelines for future research endeavors.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China.
- School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, China.
- School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China.
- School of Health Management, China Medical University, Shenyang 110042, China.
- Key Laboratory of Intelligent Computing in Medical Image, Ministry of Education, Northeastern University, Shenyang 110819, China.
- Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA.
ORCID-Profile: Yanan Wu, Yudong Yao, Chuyang Ye, Shouliang Qi
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Pang, H., Zhang, T., Wu, Y., Chen, S., Qian, W., Yao, Y., Ye, C., Monkam, P., & Qi, S. (2026). Generative Models for Medical Image Creation and Translation: A Scoping Review. Sensors. https://doi.org/10.3390/s26030862
Vancouver
Pang H, Zhang T, Wu Y, Chen S, Qian W, Yao Y, et al. Generative Models for Medical Image Creation and Translation: A Scoping Review. Sensors. 2026. doi:10.3390/s26030862
BibTeX
@article{Pang2026,
author = {Pang, Haowen and Zhang, Tiande and Wu, Yanan and Chen, Shannan and Qian, Wei and Yao, Yudong and Ye, Chuyang and Monkam, Patrice and Qi, Shouliang},
title = {Generative Models for Medical Image Creation and Translation: A Scoping Review},
journal = {Sensors},
year = {2026},
doi = {10.3390/s26030862}
}
EUVIMED