8 datasets found

Medical Image Registration via Neural Fields

A large-scale lung nodule dataset with pathology- or follow-up-confirmed benign/malignant labels for low-dose and noncontrast CTs.

A public benchmark brain MR-CT registration dataset named SR-Reg is utilized in this paper.

The WORD dataset is used for deformable image registration. The dataset consists of 150 abdominal CT scans from 150 patients with 30495 slices.

The Swin Transformer-based TransMorph dataset is used for deformable image registration. The dataset consists of 50 abdominal CT scans, each scan with 13 organ annotations.

Multi-modal volume registration by maximization of mutual information.

General vision encoders like DINOv2 and SAM have recently transformed computer vision. Even though they are trained on natural images, encoder models have excelled in medical...

Medical image registration aims to identify the spatial deformation between images of the same anatomical region and is fundamental to image-based diagnostics and therapy.