Chapter

Biomedical Image Registration

Volume 6204 of the series Lecture Notes in Computer Science pp 1-12

Unifying Vascular Information in Intensity-Based Nonrigid Lung CT Registration

  • Kunlin CaoAffiliated withDepartment of Electrical and Computer Engineering
  • , Kai DingAffiliated withDepartment of Biomedical Engineering, The University of Iowa
  • , Gary E. ChristensenAffiliated withDepartment of Electrical and Computer Engineering
  • , Madhavan L. RaghavanAffiliated withDepartment of Biomedical Engineering, The University of Iowa
  • , Ryan E. AmelonAffiliated withDepartment of Biomedical Engineering, The University of Iowa
  • , Joseph M. ReinhardtAffiliated withDepartment of Electrical and Computer Engineering

Abstract

Image registration plays an important role within pulmonary image analysis. Accurate registration is critical to post-analysis of lung mechanical properties. To improve registration accuracy, we utilize the rich information of vessel locations and shapes, and introduce a new similarity criterion, sum of squared vesselness measure difference (SSVMD). This metric is added to three existing intensity-based similarity criteria for nonrigid lung CT image registration to show its ability in improving matching accuracy. The registration accuracy is assessed by landmark error calculation and distance map visualization on vascular tree. The average landmark errors are reduced by over 20% and are within 0.7 mm after adding SSVMD constraint to three existing intensity-based similarity metrics. Visual inspection shows matching accuracy improvements in the lung regions near the thoracic cage and near the diaphragm. Experiments also show this vesselness constraint makes the Jacobian map of transformations physiologically more plausible and reliable.