Predicting the shapes of bones at a joint: application to the shoulder

Abstract

This paper presents a novel method to explore the intrinsic morphological correlation between the bones of a shoulder joint (humerus and scapula). To model this correlation, canonical correlation analysis (CCA) is used. We also propose a technique to predict a three-dimensional (3D) bone shape from its adjoining segment at a joint based on partial least squares regression (PLS). The high dimensional 3D surface information of a bone is represented by a few variables using principal component analysis, which also captures the pattern of variability of the shapes in our datasets. Our results show that the humerus set and scapula set have highly linear morphological relationship and that the correlation information can be used as a classifier. In this study, primate shoulder bone datasets were categorised into two clusters: great apes (including humans) and monkeys. A leave one out experiment was performed to test the robustness of this prediction method. The prediction behaviour using this method shows statistically significantly better results than using the mean shape from the training set.

A scapular coordinate frame for clinical and kinematic analyses

“…This increases the cost of the planned treatment and might introduce ionising radiation to the patient that is not normally included as part of normal clinical practice. An alternative approach to using landmarks would be to use statistical shape modelling or morphing technology to register either a 2-D x-ray or scan, or some digitised surface landmarks to a computational representation of scapular morphology (Yang et al, 2008) Other limitations include the use of landmarks that are not readily accessible, or the arbitrary nature of some of the landmark choices.…”

Prediction of In Vivo Knee Joint Kinematics Using a Combined Dual Fluoroscopy Imaging and Statistical Shape Modeling Technique

“…SSM method has been investigated for decades to provide an efficient way for 3D model construction of a bony segment using its 2D X-ray images [8][9][10][11][12][13][14]. For example, subject-specific bony surface models of the distal femur can be constructed using single-or multiplanar fluoroscopic images of the femur and a generic 3D bony database of the knee with various accuracies [9,12,15].…”

Patient-Specific Modelling in Orthopedics: From Image to Surgery

“…time, cost and exposure to unacceptable levels of ionizing radiation) preclude their widespread use, on the other hand 2D medical imaging modalities such as X-rays, ultrasound or fluoroscopy, or direct pointer digitization can be used to derive patient-specific information pre-or intraoperatively from the patient's anatomy for the purpose of 3D reconstruction. The acquired patient-specific data can be processed and used to deform a shape model to finally reconstruct the patient's anatomy  Predicting the shape of one bone from the observation of another from the same joint (Yang et al 2008)  Segmentation (Baldwin et al 2010, Behiels et al 2002, Heimann et al 2009, Tang and Ellis 2005, SSM allows encapsulation of prior anatomical knowledge for compensating low contrast and/or high levels of noise in the images, such models can achieve robust segmentation by constraining the possible shapes Taylor 2004, Cootes et al 1995)  Design of prosthesis and biomechanical finite element analysis (Bryan et al 2009)  Aiding in the detection of pathologies related to shape (e.g. cam impingement, osteoarthritis), anatomical differences related to sex and aging (Styner et al 2005).…”