Synthetic Skull CT Generation with Generative Adversarial Networks to Train Deep Learning Models for Clinical Transcranial Ultrasound

TL;DR

This paper introduces SkullGAN, a generative adversarial network that creates synthetic skull CT images to facilitate training deep learning models for transcranial ultrasound, addressing data scarcity and privacy issues.

Contribution

SkullGAN is a novel GAN architecture designed to generate realistic synthetic skull CT slices for medical training and research, reducing reliance on real patient data.

Findings

Synthetic images have similar radiological features to real skulls.

t-SNE analysis shows real and synthetic data are indistinguishable.

Radiologists achieved 60% accuracy in identifying real vs. synthetic images.

Abstract

Deep learning offers potential for various healthcare applications, yet requires extensive datasets of curated medical images where data privacy, cost, and distribution mismatch across various acquisition centers could become major problems. To overcome these challenges, we propose a generative adversarial network (SkullGAN) to create large datasets of synthetic skull CT slices, geared towards training models for transcranial ultrasound. With wide ranging applications in treatment of essential tremor, Parkinson's, and Alzheimer's disease, transcranial ultrasound clinical pipelines can be significantly optimized via integration of deep learning. The main roadblock is the lack of sufficient skull CT slices for the purposes of training, which SkullGAN aims to address. Actual CT slices of 38 healthy subjects were used for training. The generated synthetic skull images were then evaluated based on skull density ratio, mean thickness, and mean intensity. Their fidelity was further analyzed using t-distributed stochastic neighbor embedding (t-SNE), Fr\'echet inception distance (FID) score, and visual Turing test (VTT) taken by four staff clinical radiologists. SkullGAN-generated images demonstrated similar quantitative radiological features to real skulls. t-SNE failed to separate real and synthetic samples from one another, and the FID score was 49. Expert radiologists achieved a 60\% mean accuracy on the VTT. SkullGAN makes it possible for researchers to generate large numbers of synthetic skull CT segments, necessary for training neural networks for medical applications involving the human skull, such as transcranial focused ultrasound, mitigating challenges with access, privacy, capital, time, and the need for domain expertise.