A Deep Discontinuity-Preserving Image Registration Network
This addresses registration errors at tissue interfaces in medical imaging, such as cardiac and abdominal scans, which is crucial for accurate diagnosis and interventions.
The paper tackled the problem of unrealistic deformation fields in medical image registration by proposing a deep discontinuity-preserving network, achieving significant improvements in accuracy and more realistic deformations on cardiac MR images from the UK Biobank.
Image registration aims to establish spatial correspondence across pairs, or groups of images, and is a cornerstone of medical image computing and computer-assisted-interventions. Currently, most deep learning-based registration methods assume that the desired deformation fields are globally smooth and continuous, which is not always valid for real-world scenarios, especially in medical image registration (e.g. cardiac imaging and abdominal imaging). Such a global constraint can lead to artefacts and increased errors at discontinuous tissue interfaces. To tackle this issue, we propose a weakly-supervised Deep Discontinuity-preserving Image Registration network (DDIR), to obtain better registration performance and realistic deformation fields. We demonstrate that our method achieves significant improvements in registration accuracy and predicts more realistic deformations, in registration experiments on cardiac magnetic resonance (MR) images from UK Biobank Imaging Study (UKBB), than state-of-the-art approaches.