Shade Artifact Reduction in CBCT-to-MDCT: Fine-Tuning Based on Style Transfer and Human Feedback

Cone beam computed tomography (CBCT) is widely used in dental treatment due to its low radiation dose and cost. However, it has lower image quality compared to Multi Detector Computed Tomography (MDCT), limiting its use in precision medical examinations. Recent research has focused on using generative models, particularly Cycle-GAN, to transform low-resolution CBCT images into high-resolution MDCT-like images. Although Cycle-GAN has shown promising results, it often produces shading artifacts that compromise image quality. In this paper, we propose a fine-tuning method that integrates human feedback with style transfer techniques to effectively address this issue, thereby improving the model’s adaptability and performance. Our method involves re-training the Cycle-GAN generator to learn and replicate the feature distribution of clean MDCT images, significantly reducing shading artifacts and preserving morphological structures. Experimental results demonstrate that our proposed fine-tuning method effectively reduces artifacts and enhances image quality. Additionally, our selective training technique ensures the preservation of local morphological structures, leading to better outcomes compared to non-selective training methods. This approach provides a reliable and efficient solution for generating high-resolution, artifact-free MDCT-like images from cost-effective CBCT scans, with the potential to greatly benefit clinical diagnostics and patient outcomes.