Femur statistical atlas construction based on two-level 3D non-rigid registration

Abstract

The statistical atlas is a 3D medical image analysis tool towards more patient-oriented and more efficient diagnosis. The atlas includes information on geometry and their variation across populations. The comparison and information from other patients is very useful for the objective quantitative diagnosis. The statistical atlas can also be used to solve other challenging problems such as image segmentation. As a key to build statistical atlases, 3D registration remains an important yet unsolved problem in the medical image field due to the geometrical complexity of anatomical shapes and computational complexity caused by the enormous size of volume data.Method: In this work we developed a two-level framework to efficiently solve 3D nonrigid registration and applied the method to the problem of building statistical atlases of femur. Compared with a general multi-resolution framework, we employed an interpolation to propagate the matching instead of repeating the registration scheme in each resolution. The registration procedure is divided into two levels: a low-resolution solution to the correspondences and mapping of surface models using Chui and Rangarajan's thin-plate spline (TPS) based algorithm [25], followed by an interpolation to achieve high-resolution matching. After that, principal component analysis (PCA) is used to build the statistical atlas. Experimental results show the shape variation learned from the atlas, and also demonstrate that out method significantly improves efficiency of registration without decreasing accuracy of atlases.

Efficacy of diffeomorphic surface matching and 3D geometric morphometrics for taxonomic discrimination of Early Pleistocene hominin mandibular molars

“…This was done using a leave-one-out crossvalidation with k=3, and evaluated with the balanced accuracy to account for class imbalance. imaging as a means by which to provide information on normative (multidimensional) morphological geometry and its variation in the description of shape (e.g., Chen, 1999;Chen et al, 1999;Däuber et al, 2002;Wu et al, 2009;Davatzikos and Verma, 2010;Fonseca et al, 2011). The statistical atlas represents a smooth probability map of the morphology of a given anatomical structure in a population, where that structure is modelled statistically using the sample of 3D meshes that represent it.…”

Computer Image Registration Techniques Applied to Nuclear Medicine Images

“…It should be noted that, a more complex transformation model implies a higher number of degrees of freedom leading to non-rigid transformations. Image registration algorithms based on non-rigid transformations are required, for example, when the alignment between images of one individual and an atlas needs to be established [31], or when substantial anatomical variability among individuals needs to be accommodated [12,13,32,33]. When compared with rigid transformations, non-rigid based registration algorithms have a higher number of degrees of freedom [34,35].…”

“…Therefore, spline-based geometrical transformations either interpolate or approximate the displacements at control points. Thin-plate splines (TPS) are based on radial basis functions and are used in surface interpolation of scattered data [32,33]. Each basis function contributes to the transformation, and each control point has a global influence on the transformation.…”

Survey of Non-Rigid Registration Tools in Medicine

“…It is an important part of image analysis and used in several disciplines. In the medical field, image registration is a key component in several areas including the fusion of morphologic and functional images [1]; image subtraction [2]; intervention planning [3]; computeraided diagnosis (CAD) and treatment follow-up [4]; intervention simulations [5]; atlas building [6][7][8]; radiation therapy [9]; model-based segmentation [10]; and computational model building [11].…”