Demonstrating the successful application of synthetic learning in spine surgery for training multi–center models with increased patient privacy

Abstract

From real–time tumor classification to operative outcome prediction, applications of machine learning to neurosurgery are powerful. However, the translation of many of these applications are restricted by the lack of “big data” in neurosurgery. Important restrictions in patient privacy and sharing of imaging data reduce the diversity of the datasets used to train resulting models and therefore limit generalizability. Synthetic learning is a recent development in machine learning that generates synthetic data from real data and uses the synthetic data to train downstream models while preserving patient privacy. Such an approach has yet to be successfully demonstrated in the spine surgery domain. Spine radiographs were collected from the VinDR–SpineXR dataset, with 1470 labeled as abnormal and 2303 labeled as normal. A conditional generative adversarial network (GAN) was trained on the radiographs to generate a spine radiograph and normal/abnormal label. A modified conditional GAN (SpineGAN) was trained on the same task. A convolutional neural network (CNN) was trained using the real data to label abnormal radiographs. A CNN was trained to label abnormal radiographs using synthetic images from the GAN and in a separate experiment from SpineGAN. Using the real radiographs, an AUC of 0.856 was achieved in abnormality classification. Training on synthetic data generated by the standard GAN (AUC of 0.814) and synthetic data generated by our SpineGAN (AUC of 0.830) resulted in similar classifier performance. SpineGAN generated images with higher FID and lower precision scores, but with higher recall and increased performance when used for synthetic learning. The successful application of synthetic learning was demonstrated in the spine surgery domain for the classification of spine radiographs as abnormal or normal. A modified domain–relevant GAN is introduced for the generation of spine images, evidencing the importance of domain–relevant generation techniques in synthetic learning. Synthetic learning can allow neurosurgery to use larger and more diverse patient imaging sets to train more generalizable algorithms with greater patient privacy.

The Emerging Applications of Synthetic Data in Neurosurgery Research and Practice: A Systematic Review

“…Additionally, the foray into synthetic learning for spine surgery by Ethan Schonfeld and Anand Veeravagu (2023) tackles the challenge posed by the scarcity of extensive datasets, attributed to privacy and data sharing restrictions. The creation of SpineGAN for synthetic radiograph generation exemplifies how synthetic data can surmount traditional hindrances, promoting enhanced model training while safeguarding patient confidentiality, indicative of a wider trend towards ethical medical research enhancement through synthetic data and AI.…”

“…Complementing this, Schonfeld et al (2023) explore the generation of synthetic datasets designed to enhance the diversity of training cases for predictive models without breaching privacy protocols. By enabling the inclusion of a broader array of clinical scenarios, these synthetic datasets facilitate a more comprehensive understanding of patient outcomes, thereby broadening the scope of research questions that can be addressed within the constraints of privacy regulations.…”

Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations

“…One solution, synthetic learning, is to share synthetic data that represents the clinical information of patient data but preserves its privacy; efforts have begun to use GANs to generate synthetic data and to allow sharing across institutions. This approach has been proven to be unbiased and downstream models trained on the synthetic data have achieved high performance on brain tumors [ 98 ], nuclei segmentation [ 98 ], and spine radiograph abnormality classification [ 99 ]. The current most popular method to preserve data privacy while allowing for the training of complex networks across institutions is termed federated learning (FL).…”