Statistical model-based segmentation of the proximal femur in digital antero-posterior (AP) pelvic radiographs

Application of statistical shape modeling to the human hip joint: a scoping review

OBJECTIVE

The objective of this scoping review was to identify all examples of the application of statistical shape models to the human hip joint, with a focus on applications, population, methodology, and validation.

INTRODUCTION

Clinical radiographs are the most common imaging tool for management of hip conditions, but it is unclear whether radiographs can adequately diagnose or predict outcomes of 3D deformity. Statistical shape modeling, a method of describing the variation of a population of shapes using a small number of variables, has been identified as a useful tool to associate 2D images with 3D anatomy. This could allow clinicians and researchers to validate clinical radiographic measures of hip deformity, develop new ones, or predict 3D morphology directly from radiographs. In identifying all previous examples of statistical shape modeling applied to the human hip joint, this review determined the prevalence, strengths, and weaknesses, and identified gaps in the literature.

INCLUSION CRITERIA

Participants included any human population. The concept included development or application of statistical shape models based on discrete landmarks and principal component analysis. The context included sources that exclusively modeled the hip joint. Only peer-reviewed original research journal articles were eligible for inclusion.

METHODS

We searched MEDLINE, Embase, Cochrane CENTRAL, IEEE Xplore, Web of Science Core Collection, OCLC PapersFirst, OCLC Proceedings, Networked Digital Library of Theses and Dissertations, ProQuest Dissertations and Theses Global, and Google Scholar for sources published in English between 1992 and 2021. Two reviewers screened sources against the inclusion criteria independently and in duplicate. Data were extracted by 2 reviewers using a REDCap form designed to answer the review study questions, and are presented in narrative, tabular, and graphical form.

RESULTS

A total of 104 sources were considered eligible based on the inclusion criteria. From these, 122 unique statistical shape models of the human hip were identified based on 86 unique training populations. Models were most often applied as one-off research tools to describe shape in certain populations or to predict outcomes. The demographics of training populations were skewed toward older patients in high-income countries. A mean age between 60 and 79 years was reported in 29 training populations (34%), more than reported in all other age groups combined, and 73 training populations (85%) were reported or inferred to be from Europe and the Americas. Only 4 studies created models in a pediatric population, although 15 articles considered shape variation over time in some way. There were approximately equal numbers of 2D and 3D models. A variety of methods for labeling the training set was observed. Most articles presented some form of validation such as reporting a model's compactness (n = 71), but in-depth validation was rare.

CONCLUSIONS

Despite the high volume of literature concerning statistical shape models of the human hip, there remains a need for further research in key areas. We identified the lack of models in pediatric populations and low- and middle-income countries as a notable limitation to be addressed in future research.

Deep learning-based 2D/3D registration of an atlas to biplanar X-ray images

Purpose

The registration of a 3D atlas image to 2D radiographs enables 3D pre-operative planning without the need to acquire costly and high-dose CT-scans. Recently, many deep-learning-based 2D/3D registration methods have been proposed which tackle the problem as a reconstruction by regressing the 3D image immediately from the radiographs, rather than registering an atlas image. Consequently, they are less constrained against unfeasible reconstructions and have no possibility to warp auxiliary data. Finally, they are, by construction, limited to orthogonal projections.

Methods

We propose a novel end-to-end trainable 2D/3D registration network that regresses a dense deformation field that warps an atlas image such that the forward projection of the warped atlas matches the input 2D radiographs. We effectively take the projection matrix into account in the regression problem by integrating a projective and inverse projective spatial transform layer into the network.

Results

Comprehensive experiments conducted on simulated DRRs from patient CT images demonstrate the efficacy of the network. Our network yields an average Dice score of 0.94 and an average symmetric surface distance of 0.84 mm on our test dataset. It has experimentally been determined that projection geometries with 80\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{\circ }$$\end{document}∘ to 100\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$^{\circ }$$\end{document}∘ projection angle difference result in the highest accuracy.

Conclusion

Our network is able to accurately reconstruct patient-specific CT-images from a pair of near-orthogonal calibrated radiographs by regressing a deformation field that warps an atlas image or any other auxiliary data. Our method is not constrained to orthogonal projections, increasing its applicability in medical practices. It remains a future task to extend the network for uncalibrated radiographs.

Automatic Femoral Deformity Analysis Based on the Constrained Local Models and Hough Forest

Clinically, Taylor spatial frame (TSF) is usually used to correct femoral deformity. The first step in correction is to analyze skeletal deformities and measure the center of rotation of angulation (CORA). Since the above work needs to be done manually, the doctor's workload is heavy. Therefore, an automatic femoral deformity analysis system was proposed. Firstly, the Hough forest and constrained local models were trained on the femur image set. Then, the position and size of the femur in the X-ray image were detected by the trained Hough forest. Furthermore, the position and size were served as the initial values of the trained constrained local models to fit the femoral contour. Finally, the anatomical axis line of the proximal femur and the anatomical axis line of the distal femur could be drawn according to the fitting results. According to these lines, CORA can be found. Compared with manual measurement by doctors, the average error of the hip joint orientation line was 1.7°, the standard deviation was 1.75, the average error of the anatomic axis line of the proximal femur was 2.9°, and the standard deviation was 3.57. The automatic femoral deformity analysis system meets the accuracy requirements of orthopedics and can significantly reduce the workload of doctors.

A Semi-automatic Diagnosis of Hip Dysplasia on X-Ray Films

Background: Diagnosis of hip joint plays an important role in early screening of hip diseases such as coxarthritis, heterotopic ossification, osteonecrosis of the femoral head, etc. Early detection of hip dysplasia on X-ray films may probably conduce to early treatment of patients, which can help to cure patients or relieve their pain as much as possible. There has been no method or tool for automatic diagnosis of hip dysplasia till now.

Results: A semi-automatic method for diagnosis of hip dysplasia is proposed. Considering the complexity of medical imaging, the contour of acetabulum, femoral head, and the upper side of thigh-bone are manually marked. Feature points are extracted according to marked contours. Traditional knowledge-driven diagnostic criteria is abandoned. Instead, a data-driven diagnostic model for hip dysplasia is presented. Angles including CE, sharp, and Tonnis angle which are commonly measured in clinical diagnosis, are automatically obtained. Samples, each of which consists of these three angle values, are used for clustering according to their densities in a descending order. A three-dimensional normal distribution derived from the cluster is built and regarded as the parametric model for diagnosis of hip dysplasia. Experiments on 143 X-ray films including 286 samples (i.e., 143 left and 143 right hip joints) demonstrate the effectiveness of our method. According to the method, a computer-aided diagnosis tool is developed for the convenience of clinicians, which can be downloaded at http://www.bio-nefu.com/HIPindex/. The data used to support the findings of this study are available from the corresponding authors upon request.

Conclusions: This data-driven method provides a more objective measurement of the angles. Besides, it provides a new criterion for diagnosis of hip dysplasia other than doctors' experience deriving from knowledge-driven clinical manual, which actually corresponds to very different way for clinical diagnosis of hip dysplasia.

Convolutional Bayesian Models for Anatomical Landmarking on Multi-Dimensional Shapes

The anatomical landmarking on statistical shape models is widely used in structural and morphometric analyses. The current study focuses on leveraging geometric features to realize an automatic and reliable landmarking. The existing implementations usually rely on classical geometric features and data-driven learning methods. However, such designs often have limitations to specific shape types. Additionally, calculating the features as a standalone step increases the computational cost. In this paper, we propose a convolutional Bayesian model for anatomical landmarking on multi-dimensional shapes. The main idea is to embed the convolutional filtering in a stationary kernel so that the geometric features are efficiently captured and implicitly encoded into the prior knowledge of a Gaussian process. In this way, the posterior inference is geometrically meaningful without entangling with extra features. By using a Gaussian process regression framework and the active learning strategy, our method is flexible and efficient in extracting arbitrary numbers of landmarks. We demonstrate extensive applications on various publicly available datasets, including one brain imaging cohort and three skeletal anatomy datasets. Both the visual and numerical evaluations verify the effectiveness of our method in extracting significant landmarks.

Iterative approach for 3D reconstruction of the femur from un-calibrated 2D radiographic images

Three-dimensional reconstruction of the femur is important for surgical planning in patients with cerebral palsy. This study aimed to reconstruct the three-dimensional femur shape from un-calibrated bi-planar radiographic images using self-calibration to allow for low-dose preoperative planning. The existing self-calibration techniques require anatomical landmarks that are clearly visible on bi-planar images, which are not available on the femur. In our newly developed method, the self-calibration is performed so that the contour of the statistical shape matches the image contour while the statistical shape is concomitantly optimized. The proposed approach uses conventional radiograph systems and can be easily incorporated into existing clinical protocols, as compared to other reconstruction methods.

A complete-pelvis segmentation framework for image-free total hip arthroplasty (THA): methodology and clinical study

BACKGROUND

Complete-pelvis segmentation in antero-posterior pelvic radiographs is required to create a patient-specific three-dimensional pelvis model for surgical planning and postoperative assessment in image-free navigation of total hip arthroplasty.

METHODS

A fast and robust framework for accurately segmenting the complete pelvis is presented, consisting of two consecutive modules. In the first module, a three-stage method was developed to delineate the left hemi-pelvis based on statistical appearance and shape models. To handle complex pelvic structures, anatomy-specific information processing techniques were employed. As the input to the second module, the delineated left hemi-pelvis was then reflected about an estimated symmetry line of the radiograph to initialize the right hemi-pelvis segmentation. The right hemi-pelvis was segmented by the same three-stage method,

RESULTS

Two experiments conducted on respectively 143 and 40 AP radiographs demonstrated a mean segmentation accuracy of 1.61±0.68 mm. A clinical study to investigate the postoperative assessment of acetabular cup orientations based on the proposed framework revealed an average accuracy of 1.2°±0.9° and 1.6°±1.4° for anteversion and inclination, respectively. Delineation of each radiograph costs less than one minute.

CONCLUSIONS

Despite further validation needed, the preliminary results implied the underlying clinical applicability of the proposed framework for image-free THA.