Unsupervised skull segmentation in MR images utilizing modality translation and super-resolution

Skull segmentation from MR images is a complex yet highly desirable task in modern computational medicine. The main challenges are associated with the fact that MRI focuses more on the soft tissues rather than bone structures. While skull segmentation is well-established in CT imaging, the need for MRI-based segmentation arises from the risks associated with CT radiation exposure. In this work, we explore unsupervised skull segmentation by leveraging modality translation methods, transforming the challenge of direct MR segmentation into a more manageable task of modality translation followed by CT-based segmentation. A broad spectrum of deep generative networks is investigated, including generative adversarial networks, denoising diffusion models, and contrastive learning methods, leading to the development of a novel methodology of MRI-based skull segmentation. In this study, we also address the challenge that MR images typically have lower resolution than CT images, while high-resolution CT images are often required for clinical segmentation tasks, hence we additionally employ a robust super-resolution approach. The methodology proposed in this work offers fast inference for volumetric data and outperforms traditional supervised segmentation methods. Additionally, it surpasses a novel foundation medical segmentation model and delivers superior results compared to other modality translation techniques.