Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology
This work addresses the challenge of aligning brain images with tumors for pathological analysis, which is incremental as it builds on existing inpainting methods with symmetry constraints.
The paper tackled the problem of deformable registration between brain MRI images of patients with tumors and healthy subjects by using a multi-step context-aware inpainting framework to generate synthetic tissue in tumor regions, resulting in improved registration with increased PSNR, SSIM, inception score, and reduced L1 error on the BraTS 2018 dataset.
Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis. Since tumor region does not match with any ordinary brain tissue, it has been difficult to deformably register a patients brain to a normal one. Many patient images are associated with irregularly distributed lesions, resulting in further distortion of normal tissue structures and complicating registration's similarity measure. In this work, we follow a multi-step context-aware image inpainting framework to generate synthetic tissue intensities in the tumor region. The coarse image-to-image translation is applied to make a rough inference of the missing parts. Then, a feature-level patch-match refinement module is applied to refine the details by modeling the semantic relevance between patch-wise features. A symmetry constraint reflecting a large degree of anatomical symmetry in the brain is further proposed to achieve better structure understanding. Deformable registration is applied between inpainted patient images and normal brains, and the resulting deformation field is eventually used to deform original patient data for the final alignment. The method was applied to the Multimodal Brain Tumor Segmentation (BraTS) 2018 challenge database and compared against three existing inpainting methods. The proposed method yielded results with increased peak signal-to-noise ratio, structural similarity index, inception score, and reduced L1 error, leading to successful patient-to-normal brain image registration.