Generative models for high-resolution synthetic image of gastric cancer for improved gastric cancer detection

This study proposes to advance the detection of gastric cancer by training YOLOv8 architecture through the generated synthetic gastric cancer images using the StyleGAN3 architecture and evaluating their effectiveness in AI-assisted diagnostics. To address this, the research utilizes styleGAN3 architecture based on generative adversarial networks to produce high-resolution synthetic images that enhance the training datasets for AI models. The study developed an image generative model that creates synthetic gastric cancer images at 1024x1024 resolution and used the pseudolabeling method in a semi-supervised learning method to improve trained detection models. The generative model's image quality is validated through quality metrics of Fréchet Inception Distance, achieved a score of 34.71, it showed indicating high-quality synthesis image. By combining real and synthetic datasets, the researchers developed a gastric cancer detection model with a sensitivity of 90.30%, outperforming models trained solely on real (85.95%) or synthetic data (82.20%). In addition, the generated gastric cancer lesions are like the real lesions, proving that it can be trained by accurately detecting gastric cancer regions in detecting gastric cancer. This approach underscores the potential of synthetic data to enhance diagnostic accuracy in medical imaging, offering a promising solution to the limitations of traditional methods by refining AI diagnostic tools through synthetic data integration.