Machine learning in neurosurgery is limited by challenges in assembling large, high-quality imaging datasets. Synthetic data offers a scalable, privacy-preserving solution. We evaluated the feasibility of generating realistic lateral cervical spine radiographs using a denoising diffusion probabilistic model (DDPM) trained on 4,963 images from the Cervical Spine X-ray Atlas. Model performance was monitored via training/validation loss and Frechet inception distance, and synthetic image quality was assessed in a blinded "clinical Turing test" with six neuroradiologists and two spine-fellowship trained neurosurgeons. Experts reviewed 50 quartets containing one real and three synthetic images, identifying the real image and rating realism on a 4-point Likert scale. Experts correctly identified the real image in 29% of trials (Fleiss' kappa=0.061). Mean realism scores were comparable between real (3.323) and synthetic images (3.228, 3.258, and 3.320; p=0.383, 0.471, 1.000). Nearest-neighbor analysis found no evidence of memorization. We also provide a dataset of 20,063 synthetic radiographs. These results demonstrate that DDPM-generated cervical spine X-rays are statistically indistinguishable in realism and quality from real clinical images, offering a novel approach to creating large-scale neuroimaging datasets for ML applications in landmarking, segmentation, and classification.
@article{arxiv.2510.22166,
title = {Expert Validation of Synthetic Cervical Spine Radiographs Generated with a Denoising Diffusion Probabilistic Model},
author = {Austin A. Barr and Brij S. Karmur and Anthony J. Winder and Eddie Guo and John T. Lysack and James N. Scott and William F. Morrish and Muneer Eesa and Morgan Willson and David W. Cadotte and Michael M. H. Yang and Ian Y. M. Chan and Sanju Lama and Garnette R. Sutherland},
journal= {arXiv preprint arXiv:2510.22166},
year = {2025}
}