Magnetic resonance imaging–based radiation treatment plans for dogs may be feasible with the use of generative adversarial networks
American Journal of Veterinary Research · 2025
DOI: 10.2460/ajvr.24.08.0248 ↗Kurz gefasst
Fachartikel in der Zeitschrift American Journal of Veterinary Research, 2025. Verfasst von Nicola Billings und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering, College of Engineering and Physical Sciences, University of Guelph, Guelph, ON, Canada. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Dog Diseases, Radiotherapy Planning, Computer-Assisted. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Objective
The purpose of this research was to examine the feasibility of utilizing generative adversarial networks (GANs) to generate accurate pseudo-CT images for dogs.
Methods
This study used head standard CT images and T1-weighted transverse with contrast 3-D fast spoiled gradient echo head MRI images from 45 nonbrachycephalic dogs that received treatment between 2014 and 2023. Two conditional GANs (CGANs), one with a U-Net generator and a PatchGAN discriminator and another with a residual neural network (ResNet) U-Net generator and ResNet discriminator were used to generate the pseudo-CT images.
Results
The CGAN with a ResNet U-Net generator and ResNet discriminator had an average mean absolute error of 109.5 ± 153.7 HU, average peak signal-to-noise ratio of 21.2 ± 4.31 dB, normalized mutual information of 0.89 ± 0.05, and dice similarity coefficient of 0.91 ± 0.12. The dice similarity coefficient for the bone was 0.71 ± 0.17. Qualitative results indicated that the most common ranking was “slightly similar” for both models. The CGAN with a ResNet U-Net generator and ResNet discriminator produced more accurate pseudo-CT images than the CGAN with a U-Net generator and PatchGAN discriminator.
Conclusions
The study concludes that CGAN can generate relatively accurate pseudo-CT images but suggests exploring alternative GAN extensions. Clinical Relevance Implementing generative learning into veterinary radiation therapy planning demonstrates the potential to reduce imaging costs and time.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Engineering, College of Engineering and Physical Sciences, University of Guelph, Guelph, ON, Canada.
- Department of Clinical Studies, Ontario Veterinary College, University of Guelph, Guelph, ON, Canada.
- Department of Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada.
- Department of Biomedical Science, Ontario Veterinary College, University of Guelph, Guelph, ON, Canada.
- Department of Oncology, Lakeshore Animal Health Partners, Toronto, ON, Canada.
- Department of Radiogenomics, Sunnybrook Health Sciences Centre, Toronto, ON, Canada.
ORCID-Profile: Ryan Appleby, Christopher Pinard
Zitieren
APA
Billings, N., Appleby, R., Komeili, A., Poirier, V., Pinard, C., & Ukwatta, E. (2025). Magnetic resonance imaging–based radiation treatment plans for dogs may be feasible with the use of generative adversarial networks. American Journal of Veterinary Research. https://doi.org/10.2460/ajvr.24.08.0248
Vancouver
Billings N, Appleby R, Komeili A, Poirier V, Pinard C, Ukwatta E. Magnetic resonance imaging–based radiation treatment plans for dogs may be feasible with the use of generative adversarial networks. American Journal of Veterinary Research. 2025. doi:10.2460/ajvr.24.08.0248
BibTeX
@article{Billings2025,
author = {Billings, Nicola and Appleby, Ryan and Komeili, Amin and Poirier, Valerie and Pinard, Christopher and Ukwatta, Eranga},
title = {Magnetic resonance imaging–based radiation treatment plans for dogs may be feasible with the use of generative adversarial networks},
journal = {American Journal of Veterinary Research},
year = {2025},
doi = {10.2460/ajvr.24.08.0248}
}
EUVIMED