5 datasets found

MRI image super-resolution, CT image denoising, PET image synthesis, and all-in-one medical image restoration

The proposed dataset for pathological image super-resolution, which consists of 3249x3249 pathological images and 113 testing images.

The proposed dataset for CT image denoising, which consists of 512x512 CT images and 9 training images.

The proposed dataset for PET image synthesis, which consists of 115 HQ PET images and 90 training images.

The proposed region attention transformer (RAT) for medical image restoration, which conducts attention within similar semantic regions, facilitating pixels with similar...