Clustered Iterative Sub-Atlas Registration for Improved Deformable Registration Using Statistical Shape Models

Purpose: Statistical atlases provide a valuable basis for registration and guidance in orthopaedic surgery - for example, automatic anatomical segmentation and planning via atlas-to-patient registration. We report the construction of a statistical shape model for the pelvis containing annotations of common surgical trajectories and investigate a novel method for deformable registration that takes advantage of sub-types that may exist within the atlas and uses them in active shape model registration according to sub-atlas similarity of principal components between atlas members and the target (patient) pelvis. Methods: CT images from 41 subjects (21 males, 20 females) were derived from the Cancer Imaging Archive (TCIA) and segmented using manual/semi-automatic methods. A statistical shape model was constructed and incorporated in an active shape model (ASM) registration framework for atlas-to-patient registration. Further, we introduce a registration method that exploits clusters in the underlying distribution to iteratively perform registrations after selecting a patient relevant cluster (sub-atlas) that represents similar shape characteristics to the image being registered. Experiments were performed to evaluate surface-to-surface and atlas-to patient registration algorithms using this clustered iterative model. Initial investigation of improved registration based on using similar shapes, was first explored through the use of gender as a categorical way of selecting a possible sub-atlas for registration. Results: The RMSE surface-to-surface registration error (mean +/- std) was reduced from (2.1 +/- 0.2) mm when registering according to the entire atlas (N=40 members) to (1.8 +/- 0.1) mm when registering within clusters based on similarity of principal components (N=20 members), showing improved accuracy (p<0.001) with fewer atlas members - an efficiency gained by virtue of the proposed approach. The atlas showed clear clusters in the first two principal components corresponding to gender, and the proposed method demonstrated improved accuracy when using ASM registration as well as when applied to a coherent-point drift (CPD) non-rigid deformable registration. Conclusions: The proposed framework improved atlas-to-patient registration accuracy and increased the efficiency of statistical shape models (i.e., equivalent registration using fewer atlas members) by guiding member selection according to similarity in principal components.