SR4ZCT: Self-supervised Through-plane Resolution Enhancement for CT Images with Arbitrary Resolution and Overlap
This addresses a domain-specific problem for medical imaging practitioners by improving CT image quality for better disease diagnosis, though it is incremental as it builds on existing self-supervised off-axis training methods.
The paper tackles the problem of insufficient through-plane resolution and overlap in CT images, which hinders diagnostic accuracy, by proposing SR4ZCT, a self-supervised method that enhances resolution for arbitrary combinations of resolution and overlap, demonstrating effectiveness on a real-world dataset.
Computed tomography (CT) is a widely used non-invasive medical imaging technique for disease diagnosis. The diagnostic accuracy is often affected by image resolution, which can be insufficient in practice. For medical CT images, the through-plane resolution is often worse than the in-plane resolution and there can be overlap between slices, causing difficulties in diagnoses. Self-supervised methods for through-plane resolution enhancement, which train on in-plane images and infer on through-plane images, have shown promise for both CT and MRI imaging. However, existing self-supervised methods either neglect overlap or can only handle specific cases with fixed combinations of resolution and overlap. To address these limitations, we propose a self-supervised method called SR4ZCT. It employs the same off-axis training approach while being capable of handling arbitrary combinations of resolution and overlap. Our method explicitly models the relationship between resolutions and voxel spacings of different planes to accurately simulate training images that match the original through-plane images. We highlight the significance of accurate modeling in self-supervised off-axis training and demonstrate the effectiveness of SR4ZCT using a real-world dataset.