Intensity-Based Non-rigid Registration Using Adaptive Multilevel Free-Form Deformation with an Incompressibility Constraint
نویسندگان
چکیده
A major problem with non-rigid image registration techniques in many applications is their tendency to reduce the volume of contrast-enhancing structures [10]. Contrast enhancement is an intensity inconsistency, which is precisely what intensity-based registration algorithms are designed to minimize. Therefore, contrast-enhanced structures typically shrink substantially during registration, which affects the use of the resulting transformation for volumetric analysis, image subtraction, and multispectral classification. A common approach to address this problem is to constrain the deformation. In this paper we present a novel incompressibility constraint approach that is based on the Jacobian determinant of the deformation and can be computed rapidly. We apply our intensity-based non-rigid registration algorithm with this incompressibility constraint to two clinical applications (MR mammography, CT-DSA) and demonstrate that it produces high-quality deformations (as judged by visual assessment) while preserving the volume of contrast-enhanced structures.
منابع مشابه
Non-rigid image registration of brain magnetic resonance images using graph-cuts
We present a graph-cuts basedmethod for non-rigid medical image registration on brain magnetic resonance images. In this paper, the non-rigid medical image registration problem is reformulated as a discrete labeling problem. Based on a voxel-to-voxel intensity similarity measure, each voxel in the source image is assigned a displacement label, which represents a displacement vector indicating w...
متن کاملModeling Liver Motion and Deformation During the Respiratory Cycle Using Intensity-Based Free-FormRegistration of Gated MR Images
Introduction Stereotactic radiosurgery has been used to treat cranial lesions for more than a decade. This type of image-guided procedure matches preoperative image data and the physical space occupied by the patient using the fact that the brain inside a closed cranium is approximately rigid. We are interested in treating extracranial lesions such as metastases and primary tumors in the liver....
متن کاملUsing K-means Clustering and MI for Non-rigid Registration of MRI and CT
Mutual information (MI) based registration methods are susceptible to the variation of the intensity of the image. We present a multi-modality MRI-CT non-rigid registration method by combining Kmeans clustering technique with mutual information. This method makes use of K-means clustering to determine variant bin sizes in CT image. The resulting clustered (labeled) CT image is non-rigidly regis...
متن کاملComparison and evaluation of rigid and non-rigid registration of breast MR images
In this paper we present a new approach for the non-rigid registration of contrast-enhanced breast MRI. A hierarchical transformation model of the motion of the breast has been developed: The global motion of the breast is modelled by an a ne transformation while the local breast motion is described by a free-form deformation (FFD) based on B-splines. Normalised mutual information is used as a ...
متن کاملHybrid Multimodal Registration of Carotid Magnetic Resonance and Ultrasound Images Using Free-Form Deformation
In this work, a hybrid approach for the multimodal registration of carotid magnetic resonance and ultrasound images is described. Multimodal registration is vital for integrating or fusing complementary information from different sources into a composite form. It will provide synergistic information about the objects under examination and thus, help in the assessment of carotid artery disease. ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2001