Supervised vs. Unsupervised GAN for Pseudo-CT Synthesis in Brain MR-Guided Radiotherapy

Purpose Radiotherapy is a crucial treatment for brain tumor malignancies. To address the limitations of CT-based treatment planning, recent research has explored MR-only radiotherapy, requiring precise MR-to-CT synthesis. This study compares two deep learning approaches, supervised (Pix2Pix) and unsupervised (CycleGAN), for generating pseudo-CT (pCT) images from T1- and T2-weighted MR sequences. Methods and Materials: 3270 paired T1 and T2 weighted MRI images are collected and registered with corresponding CT images. After preprocessing a supervised pCT generative model was trained using a "pix2pix" model, and an unsupervised generative network (CycleGan), was also trained for the purpose of comparing pCT quality against the pix2pix. To assess the differences between pCT images and reference CT images, three key metrics (SSIM, PSNR and MAE) are used. Results The average of SSIM, PSNR and MAE for pix2pix on T1 images was 0.964 ± 0.03, 32.812 ± 5.21 and 79.681 ± 9.52 HU respectively. Statistical analysis revealed that Pix2Pix significantly outperformed CycleGAN in generating high-fidelity pCT images (p < 0.05). There was no notable difference in the effectiveness of T1-weighted versus T2-weighted MR images for generating pCT (p > 0.05). Conclusion Both supervised and unsupervised methods demonstrated the capability to generate accurate pCT images from conventional T1- and T2-weighted MR sequences. While supervised methods like Pix2Pix achieve higher accuracy, unsupervised approaches such as CycleGAN offer greater flexibility by eliminating the need for paired training data, making them suitable for applications where paired data is unavailable.