Chapter

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011

Volume 6892 of the series Lecture Notes in Computer Science pp 541-548

Non-local Shape Descriptor: A New Similarity Metric for Deformable Multi-modal Registration

  • Mattias P. HeinrichAffiliated withLancaster UniversityCarnegie Mellon UniversityInstitute of Biomedical Engineering, University of OxfordOxford University Centre for Functional MRI of the Brain
  • , Mark JenkinsonAffiliated withCarnegie Mellon UniversityOxford University Centre for Functional MRI of the Brain
  • , Manav BhushanAffiliated withLancaster UniversityCarnegie Mellon UniversityInstitute of Biomedical Engineering, University of OxfordOxford University Centre for Functional MRI of the Brain
  • , Tahreema MatinAffiliated withCarnegie Mellon UniversityDepartment of Radiology Churchill Hospital
  • , Fergus V. GleesonAffiliated withCarnegie Mellon UniversityDepartment of Radiology Churchill Hospital
  • , J. Michael BradyAffiliated withCarnegie Mellon UniversityDepartment of Radiation Oncology and Biology, University of Oxford
  • , Julia A. SchnabelAffiliated withLancaster UniversityInstitute of Biomedical Engineering, University of Oxford

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Deformable registration of images obtained from different modalities remains a challenging task in medical image analysis. This paper addresses this problem and proposes a new similarity metric for multi-modal registration, the non-local shape descriptor. It aims to extract the shape of anatomical features in a non-local region. By utilizing the dense evaluation of shape descriptors, this new measure bridges the gap between intensity-based and geometric feature-based similarity criteria. Our new metric allows for accurate and reliable registration of clinical multi-modal datasets and is robust against the most considerable differences between modalities, such as non-functional intensity relations, different amounts of noise and non-uniform bias fields. The measure has been implemented in a non-rigid diffusion-regularized registration framework. It has been applied to synthetic test images and challenging clinical MRI and CT chest scans. Experimental results demonstrate its advantages over the most commonly used similarity metric - mutual information, and show improved alignment of anatomical landmarks.