Fig. 4: Grad-CAM visualizations of ResNet50 before and after StyleGAN2-based dataset optimization.
From: Expert-guided StyleGAN2 image generation elevates AI diagnostic accuracy for maxillary sinus lesions
For the two types of lesions, three images were randomly selected from Test Sets 1 and 2 for demonstration. From left to right, columns showed: original test images, ROI before dataset optimization, and ROI after dataset optimization (yellow circles indicated the approximate lesion locations). It was evident that incorporating generated images to optimize the baseline training set enhanced model focus more on lesion areas, thereby improving the reliability of the prediction results.
