Femoral neck width genetic risk score is a novel independent risk factor for hip fractures.

Femoral neck width (FNW) derived from DXA scans may provide a useful adjunct to hip fracture prediction. Therefore, we investigated whether FNW is related to hip fracture risk independently of femoral neck bone mineral density (FN-BMD), using a genetic approach. FNW was derived from points automatically placed on the proximal femur using hip DXA scans from 38 150 individuals (mean age 63.8 yr, 48.0% males) in UK Biobank (UKB). Genome-wide association study (GWAS) identified 71 independent genome-wide significant FNW SNPs, comprising genes involved in cartilage differentiation, hedgehog, skeletal development, in contrast to SNPs identified by FN-BMD GWAS which primarily comprised runx1/Wnt signaling genes (MAGMA gene set analyses). FNW and FN-BMD SNPs were used to generate genetic instruments for multivariable Mendelian randomization. Greater genetically determined FNW increased risk of all hip fractures (odds ratio [OR] 1.53; 95% CI, 1.29-1.82 per SD increase) and femoral neck fractures (OR 1.58;1.30-1.92), but not trochanteric or forearm fractures. In contrast, greater genetically determined FN-BMD decreased fracture risk at all 4 sites. FNW and FN-BMD SNPs were also used to generate genetic risk scores (GRSs), which were examined in relation to incident hip fracture in UKB (excluding the FNW GWAS population; n = 338 742, 3222 cases) using a Cox proportional hazards model. FNW GRS was associated with increased risk of all incident hip fractures (HR 1.08;1.05-1.12) and femoral neck fractures (hazard ratio [HR] 1.10;1.06-1.15), but not trochanteric fractures, whereas FN-BMD GRS was associated with reduced risk of all hip fracture types. We conclude that the underlying biology regulating FNW and FN-BMD differs, and that DXA-derived FNW is causally related to hip fractures independently of FN-BMD, adding information beyond FN-BMD for hip fracture prediction. Hence, FNW derived from DXA analyses or a FNW GRS may contribute clinically useful information beyond FN-BMD for hip fracture prediction.

Femoral neck width (FNW) derived from DXA scans may provide useful information about hip fracture prediction, over and above that provided by BMD measurements. Therefore, we investigated whether FNW is related to hip fracture risk independently of BMD, using a genetic approach. FNW was derived from points automatically placed on the hip in DXA scans obtained from 38 150 individuals (mean age 63.8 yr, 48.0% males) in UK Biobank. Seventy-one distinct genetic factors were found to be associated with FNW. Individuals who were predicted by their genes to have greater FNW had a higher risk of hip but not forearm fractures. In contrast, those with greater genetically determined BMD of the femoral neck had a lower risk of both hip and forearm fractures. We conclude that the underlying biology regulating FNW and BMD of the femoral neck differs, and that FNW derived from DXA analyses may contribute clinically useful information beyond BMD for hip fracture prediction.

Machine Learning-Derived Acetabular Dysplasia and Cam Morphology Are Features of Severe Hip Osteoarthritis: Findings From UK Biobank.

The contribution of shape changes to hip osteoarthritis (HOA) remains unclear, as is the extent to which these vary according to HOA severity. In the present study, we used statistical shape modeling (SSM) to evaluate relationships between hip shape and HOA of different severities using UK Biobank DXA images. We performed a cross-sectional study in individuals with left hip dual-energy X-ray absorptiometry (DXA) scans. Statistical shape modeling (SSM) was used to quantify hip shape. Radiographic HOA (rHOA) was classified using osteophyte size and number and joint space narrowing. HOA outcomes ranged in severity from moderate (grade 2) to severe (grade ≥3) rHOA, hospital-diagnosed HOA, and subsequent total hip replacement (THR). Confounder-adjusted logistic regression between the top 10 hip shape modes (HSMs) and OA outcomes was performed. Further models adjusted for alpha angle (AA) and lateral center-edge angle (LCEA), reflecting acetabular dysplasia and cam morphology, respectively. Composite HSM figures were produced combining HSMs associated with separate OA outcomes. A total of 40,311 individuals were included (mean 63.7 years, 47.8% male), of whom 5.7% had grade 2 rHOA, 1.7% grade ≥3 rHOA, 1.3% hospital-diagnosed HOA, and 0.6% underwent THR. Composite HSM figures for grade 2 rHOA revealed femoral neck widening, increased acetabular coverage, and enlarged lesser and greater trochanters. In contrast, grade ≥3 rHOA, hospital-diagnosed HOA, and THR were suggestive of cam morphology and reduced acetabular coverage. Associations between HSMs depicting cam morphology and reduced acetabular coverage and more severe HOA were attenuated by AA and LCEA adjustment, respectively. Relationships between hip shape and HOA differed according to severity. Notably, cam morphology and acetabular dysplasia were features of severe HOA, but unrelated to moderate disease, suggesting possible prognostic utility. © 2022 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

Predicting the mechanical hip-knee-ankle angle accurately from standard knee radiographs: a cross-validation experiment in 100 patients.

Background and purpose - Being able to predict the hip-knee-ankle angle (HKAA) from standard knee radiographs allows studies on malalignment in cohorts lacking full-limb radiography. We aimed to develop an automated image analysis pipeline to measure the femoro-tibial angle (FTA) from standard knee radiographs and test various FTA definitions to predict the HKAA. Patients and methods - We included 110 pairs of standard knee and full-limb radiographs. Automatic search algorithms found anatomic landmarks on standard knee radiographs. Based on these landmarks, the FTA was automatically calculated according to 9 different definitions (6 described in the literature and 3 newly developed). Pearson and intra-class correlation coefficient [ICC]) were determined between the FTA and HKAA as measured on full-limb radiographs. Subsequently, the top 4 FTA definitions were used to predict the HKAA in a 5-fold cross-validation setting. Results - Across all pairs of images, the Pearson correlations between FTA and HKAA ranged between 0.83 and 0.90. The ICC values from 0.83 to 0.90. In the cross-validation experiments to predict the HKAA, these values decreased only minimally. The mean absolute error for the best method to predict the HKAA from standard knee radiographs was 1.8° (SD 1.3). Interpretation - We showed that the HKAA can be automatically predicted from standard knee radiographs with fair accuracy and high correlation compared with the true HKAA. Therefore, this method enables research of the relationship between malalignment and knee pathology in large (epidemiological) studies lacking full-limb radiography.

Fully Automatic System for Accurate Localisation and Analysis of Cephalometric Landmarks in Lateral Cephalograms.

Cephalometric tracing is a standard analysis tool for orthodontic diagnosis and treatment planning. The aim of this study was to develop and validate a fully automatic landmark annotation (FALA) system for finding cephalometric landmarks in lateral cephalograms and its application to the classification of skeletal malformations. Digital cephalograms of 400 subjects (age range: 7-76 years) were available. All cephalograms had been manually traced by two experienced orthodontists with 19 cephalometric landmarks, and eight clinical parameters had been calculated for each subject. A FALA system to locate the 19 landmarks in lateral cephalograms was developed. The system was evaluated via comparison to the manual tracings, and the automatically located landmarks were used for classification of the clinical parameters. The system achieved an average point-to-point error of 1.2 mm, and 84.7% of landmarks were located within the clinically accepted precision range of 2.0 mm. The automatic landmark localisation performance was within the inter-observer variability between two clinical experts. The automatic classification achieved an average classification accuracy of 83.4% which was comparable to an experienced orthodontist. The FALA system rapidly and accurately locates and analyses cephalometric landmarks in lateral cephalograms, and has the potential to significantly improve the clinical work flow in orthodontic treatment.

A benchmark for comparison of dental radiography analysis algorithms.

Dental radiography plays an important role in clinical diagnosis, treatment and surgery. In recent years, efforts have been made on developing computerized dental X-ray image analysis systems for clinical usages. A novel framework for objective evaluation of automatic dental radiography analysis algorithms has been established under the auspices of the IEEE International Symposium on Biomedical Imaging 2015 Bitewing Radiography Caries Detection Challenge and Cephalometric X-ray Image Analysis Challenge. In this article, we present the datasets, methods and results of the challenge and lay down the principles for future uses of this benchmark. The main contributions of the challenge include the creation of the dental anatomy data repository of bitewing radiographs, the creation of the anatomical abnormality classification data repository of cephalometric radiographs, and the definition of objective quantitative evaluation for comparison and ranking of the algorithms. With this benchmark, seven automatic methods for analysing cephalometric X-ray image and two automatic methods for detecting bitewing radiography caries have been compared, and detailed quantitative evaluation results are presented in this paper. Based on the quantitative evaluation results, we believe automatic dental radiography analysis is still a challenging and unsolved problem. The datasets and the evaluation software will be made available to the research community, further encouraging future developments in this field. (http://www-o.ntust.edu.tw/~cweiwang/ISBI2015/).

Robust and Accurate Shape Model Matching Using Random Forest Regression-Voting.

A widely used approach for locating points on deformable objects in images is to generate feature response images for each point, and then to fit a shape model to these response images. We demonstrate that Random Forest regression-voting can be used to generate high quality response images quickly. Rather than using a generative or a discriminative model to evaluate each pixel, a regressor is used to cast votes for the optimal position of each point. We show that this leads to fast and accurate shape model matching when applied in the Constrained Local Model framework. We evaluate the technique in detail, and compare it with a range of commonly used alternatives across application areas: the annotation of the joints of the hands in radiographs and the detection of feature points in facial images. We show that our approach outperforms alternative techniques, achieving what we believe to be the most accurate results yet published for hand joint annotation and state-of-the-art performance for facial feature point detection.

Indexed distribution analysis for improved significance testing of spatially heterogeneous parameter maps: application to dynamic contrast-enhanced MRI biomarkers.

PURPOSE: To develop significance testing methodology applicable to spatially heterogeneous parametric maps of biophysical and physiological measurements arising from imaging studies. THEORY: Heterogeneity can confound statistical analyses. Indexed distribution analysis (IDA) transforms a reference distribution, establishing correspondences across parameter maps to which significance tests are applied. METHODS: Well-controlled simulated and clinical K(trans) data from a dynamic contrast-enhanced magnetic resonance imaging study of bevacizumab were analyzed using conventional significance tests of parameter averages, histogram analysis, and IDA. Repeated pretreatment scans provided negative control; a post treatment scan provided positive control. RESULTS: Histogram analysis was insensitive to simulated and known effects. Simulation: conventional analysis identified treatment effect (P ≈ 5 × 10(-4)) and direction, but underestimated magnitude (relative error 67-81%); IDA identified treatment effect (P = 0.001), magnitude, direction, and spatial extent (100% accuracy). Bevacizumab: conventional analysis was sensitive to treatment effect (P = 0.01; 95% confidence interval on K(trans) decrease: 23-37%); IDA was sensitive to treatment effect (P < 0.05; K(trans) decrease approximately 25%), inferred its spatial extent to be 94-96%, and inferred that K(trans) decrease is independent of baseline value, an inference that conventional and histogram analyses cannot make. CONCLUSIONS: In the presence of heterogeneity, IDA can accurately infer the magnitude, direction, and spatial extent of between samples of parametric maps, which can be visualized spatially with respect to the original parameter maps.

Accurate bone segmentation in 2D radiographs using fully automatic shape model matching based on regression-voting.

Recent work has shown that using Random Forests (RFs) to vote for the optimal position of model feature points leads to robust and accurate shape model matching. This paper applies RF regression-voting as part of a fully automatic shape model matching (FASMM) system to three different radiograph segmentation problems: the proximal femur, the bones of the knee joint and the joints of the hand. We investigate why this approach works so well and demonstrate that the performance comes from a combination of three properties: (i) The integration of votes from multiple regions around the model point. (ii) The combination of multiple independent votes from each tree. (iii) The use of a coarse to fine strategy. We show that each property can improve performance, and that the best performance comes from using all three. We demonstrate that FASMM based on RF regression-voting generalises well across application areas, achieving state of the art performance in each of the three segmentation problems. This FASMM system provides an accurate and time-efficient way for the segmentation of bony structures in radiographs.

An evaluation of four automatic methods of segmenting the subcortical structures in the brain.

The automation of segmentation of subcortical structures in the brain is an active research area. We have comprehensively evaluated four novel methods of fully automated segmentation of subcortical structures using volumetric, spatial overlap and distance-based measures. Two methods are atlas-based - classifier fusion and labelling (CFL) and expectation-maximisation segmentation using a brain atlas (EMS), and two incorporate statistical models of shape and appearance - profile active appearance models (PAM) and Bayesian appearance models (BAM). Each method was applied to the segmentation of 18 subcortical structures in 270 subjects from a diverse pool varying in age, disease, sex and image acquisition parameters. Our results showed that all four methods perform on par with recently published methods. CFL performed better than the others according to all three classes of metrics. In summary over all structures, the ranking by the Dice coefficient was CFL, BAM, joint EMS and PAM. The Hausdorff distance ranked the methods as CFL, joint PAM and BAM, EMS, whilst percentage absolute volumetric difference ranked them as joint CFL and PAM, joint BAM and EMS. Furthermore, as we had four methods of performing segmentation, we investigated whether the results obtained by each method were more similar to each other than to the manual segmentations using Williams' Index. Reassuringly, the Williams' Index was close to 1 for most subjects (mean=1.02, sd=0.05), indicating better agreement of each method with the gold standard than with the other methods. However, 2% of cases (mainly amygdala and nucleus accumbens) had values outside 3 standard deviations of the mean.

Segmentation of lumbar vertebrae using part-based graphs and active appearance models.

The aim of the work is to provide a fully automatic method of segmenting vertebrae in spinal radiographs. This is of clinical relevance to the diagnosis of osteoporosis by vertebral fracture assessment, and to grading incident fractures in clinical trials. We use a parts based model of small vertebral patches (e.g., corners). Many potential candidates are found in a global search using multi-resolution normalised correlation. The ambiguity in the possible solution is resolved by applying a graphical model of the connections between parts, and applying geometric constraints. The resulting graph optimisation problem is solved using loopy belief propagation. The minimum cost solution is used to initialize a second phase of active appearance model search. The method is applied to a clinical data set of computed radiography images of lumbar spines. The accuracy of this fully automatic method is assessed by comparing the results to a gold standard of manual annotation by expert radiologists.

Quantitative vertebral fracture detection on DXA images using shape and appearance models.

RATIONALE AND OBJECTIVES: Current quantitative morphometric methods of vertebral fracture detection lack specificity, particularly with mild fractures. We use more detailed shape and texture information to develop quantitative classifiers. MATERIALS AND METHODS: The detailed shape and appearance of vertebrae on 360 lateral dual energy x-ray absorptiometry scans were statistically modeled, thus producing a set of shape and appearance parameters for each vertebra. The vertebrae were given a "gold standard" classification using a consensus reading by two radiologists. Linear discriminants were trained on the vertebral shape and appearance parameters. RESULTS: The appearance-based classifiers gave significantly better specificity than shape-based methods in all regions of the spine (overall specificity 92% at a sensitivity of 95%), while using the full shape parameters slightly improved specificity in the thoracic spine compared with using three standard height ratios. The main improvement was in the detection of mild fractures. Performance varied over different regions of the spine. False-positive rates at 95% sensitivity for the lumbar, mid-thoracic (T12-T10) and upper thoracic (T9-T7) regions were 2.9%, 14.6%, and 5.5%, respectively, compared with 6.4%, 32.6%, and 21.1% for three-height morphometry. CONCLUSION: The appearance and shape parameters of statistical models could provide more powerful quantitative classifiers of osteoporotic vertebral fracture, particularly mild fractures. False positive rates can be substantially reduced at high sensitivity by using an appearance-based classifier, because this can better distinguish between mild fractures and some kinds of non-fracture shape deformities.

A unified information-theoretic approach to groupwise non-rigid registration and model building.

The non-rigid registration of a group of images shares a common feature with building a model of a group of images: a dense, consistent correspondence across the group. Image registration aims to find the correspondence, while modelling requires it. This paper presents the theoretical framework required to unify these two areas, providing a groupwise registration algorithm, where the inherently groupwise model of the image data becomes an integral part of the registration process. The performance of this algorithm is evaluated by extending the concepts of generalisability and specificity from shape models to image models. This provides an independent metric for comparing registration algorithms of groups of images. Experimental results on MR data of brains for various pairwise and groupwise registration algorithms is presented, and demonstrates the feasibility of the combined registration/modelling framework, as well as providing quantitative evidence for the superiority of groupwise approaches to registration.

Shape discrimination in the hippocampus using an MDL model.

We extend recent work on building 3D statistical shape models, automatically, from sets of training shapes and describe an application in shape analysis. Using an existing measure of model quality, based on a minimum description length criterion, and an existing method of surface re-parameterisation, we introduce a new approach to model optimisation that is scalable, more accurate, and involves fewer parameters than previous methods. We use the new approach to build a model of the right hippocampus, using a training set of 82 shapes, manually segmented from 3D MR images of the brain. We compare the results with those obtained using another previously published method for building 3D models, and show that our approach results in a model that is significantly more specific, general, and compact. The two models are used to investigate the hypothesis that there are differences in hippocampal shape between age-matched schizophrenic and normal control subgroups within the training set. Linear discriminant analysis is used to find the combination of shape parameters that best separates the two subgroups. We perform an unbiased test that shows there is a statistically significant shape difference using either shape model, but that the difference is more significant using the model built using our approach. We show also that the difference between the two subgroups can be visualised as a mode of shape variation.

A minimum description length approach to statistical shape modeling.

We describe a method for automatically building statistical shape models from a training set of example boundaries/surfaces. These models show considerable promise as a basis for segmenting and interpreting images. One of the drawbacks of the approach is, however, the need to establish a set of dense correspondences between all members of a set of training shapes. Often this is achieved by locating a set of "landmarks" manually on each training image, which is time consuming and subjective in two dimensions and almost impossible in three dimensions. We describe how shape models can be built automatically by posing the correspondence problem as one of finding the parameterization for each shape in the training set. We select the set of parameterizations that build the "best" model. We define "best" as that which minimizes the description length of the training set, arguing that this leads to models with good compactness, specificity and generalization ability. We show how a set of shape parameterizations can be represented and manipulated in order to build a minimum description length model. Results are given for several different training sets of two-dimensional boundaries, showing that the proposed method constructs better models than other approaches including manual landmarking-the current gold standard. We also show that the method can be extended straightforwardly to three dimensions.