Improving bone strength prediction in human proximal femur specimens through geometrical characterization of trabecular bone microarchitecture and support vector regression

Multi-view information fusion using multi-view variational autoencoder to predict proximal femoral fracture load

Background

Hip fracture occurs when an applied force exceeds the force that the proximal femur can support (the fracture load or "strength") and can have devastating consequences with poor functional outcomes. Proximal femoral strengths for specific loading conditions can be computed by subject-specific finite element analysis (FEA) using quantitative computerized tomography (QCT) images. However, the radiation and availability of QCT limit its clinical usability. Alternative low-dose and widely available measurements, such as dual energy X-ray absorptiometry (DXA) and genetic factors, would be preferable for bone strength assessment. The aim of this paper is to design a deep learning-based model to predict proximal femoral strength using multi-view information fusion.

Results

We developed new models using multi-view variational autoencoder (MVAE) for feature representation learning and a product of expert (PoE) model for multi-view information fusion. We applied the proposed models to an in-house Louisiana Osteoporosis Study (LOS) cohort with 931 male subjects, including 345 African Americans and 586 Caucasians. We performed genome-wide association studies (GWAS) to select 256 genetic variants with the lowest p-values for each proximal femoral strength and integrated whole genome sequence (WGS) features and DXA-derived imaging features to predict proximal femoral strength. The best prediction model for fall fracture load was acquired by integrating WGS features and DXA-derived imaging features. The designed models achieved the mean absolute percentage error of 18.04%, 6.84% and 7.95% for predicting proximal femoral fracture loads using linear models of fall loading, nonlinear models of fall loading, and nonlinear models of stance loading, respectively.

Conclusion

The proposed models are capable of predicting proximal femoral strength using WGS features and DXA-derived imaging features. Though this tool is not a substitute for predicting FEA using QCT images, it would make improved assessment of hip fracture risk more widely available while avoiding the increased radiation exposure from QCT.

Clinical applications of artificial intelligence in radiology

The rapid growth of medical imaging has placed increasing demands on radiologists. In this scenario, artificial intelligence (AI) has become an attractive partner, one that may complement case interpretation and may aid in various non-interpretive aspects of the work in the radiological clinic. In this review, we discuss interpretative and non-interpretative uses of AI in the clinical practice, as well as report on the barriers to AI's adoption in the clinic. We show that AI currently has a modest to moderate penetration in the clinical practice, with many radiologists still being unconvinced of its value and the return on its investment. Moreover, we discuss the radiologists' liabilities regarding the AI decisions, and explain how we currently do not have regulation to guide the implementation of explainable AI or of self-learning algorithms.

The promise and limitations of artificial intelligence in musculoskeletal imaging

With the recent developments in deep learning and the rapid growth of convolutional neural networks, artificial intelligence has shown promise as a tool that can transform several aspects of the musculoskeletal imaging cycle. Its applications can involve both interpretive and non-interpretive tasks such as the ordering of imaging, scheduling, protocoling, image acquisition, report generation and communication of findings. However, artificial intelligence tools still face a number of challenges that can hinder effective implementation into clinical practice. The purpose of this review is to explore both the successes and limitations of artificial intelligence applications throughout the muscuskeletal imaging cycle and to highlight how these applications can help enhance the service radiologists deliver to their patients, resulting in increased efficiency as well as improved patient and provider satisfaction.

Prediction of femoral strength of elderly men based on quantitative computed tomography images using machine learning

Hip fracture is the most common complication of osteoporosis, and its major contributor is compromised femoral strength. This study aimed to develop practical machine learning models based on clinical quantitative computed tomography (QCT) images for predicting proximal femoral strength. Eighty subjects with entire QCT data of the right hip region were randomly selected from the full MrOS cohorts, and their proximal femoral strengths were calculated by QCT-based finite element analysis (QCT/FEA). A total of 50 parameters of each femur were extracted from QCT images as the candidate predictors of femoral strength, including grayscale distribution, regional cortical bone mapping (CBM) measurements, and geometric parameters. These parameters were simplified by using feature selection and dimensionality reduction. Support vector regression (SVR) was used as the machine learning algorithm to develop the prediction models, and the performance of each SVR model was quantified by the mean squared error (MSE), the coefficient of determination (R² ), the mean bias, and the SD of bias. For feature selection, the best prediction performance of SVR models was achieved by integrating the grayscale value of 30% percentile and specific regional CBM measurements (MSE ≤ 0.016, R² ≥ 0.93); and for dimensionality reduction, the best prediction performance of SVR models was achieved by extracting principal components with eigenvalues greater than 1.0 (MSE ≤ 0.014, R² ≥ 0.93). The femoral strengths predicted from the well-trained SVR models were in good agreement with those derived from QCT/FEA. This study provided effective machine learning models for femoral strength prediction, and they may have great potential in clinical bone health assessments.

Artificial intelligence, machine learning and deep learning in musculoskeletal imaging: Current applications

Artificial intelligence is rapidly expanding in all technological fields. The medical field, and especially diagnostic imaging, has been showing the highest developmental potential. Artificial intelligence aims at human intelligence simulation through the management of complex problems. This review describes the technical background of artificial intelligence, machine learning, and deep learning. The first section illustrates the general potential of artificial intelligence applications in the context of request management, data acquisition, image reconstruction, archiving, and communication systems. In the second section, the prospective of dedicated tools for segmentation, lesion detection, automatic diagnosis, and classification of musculoskeletal disorders is discussed.

Influence of thermodisinfection on microstructure of human femoral heads: duration of heat exposition and compressive strength

Allogeneic bone derived from living donors being necessary to match demand for bone transplantation and thermodisinfection of femoral heads is an established sterilization method. During the thermodisinfection the peripheral bone is exposed to maximum 86 °C for 94 min providing 82.5 °C within the center of the femoral head for at least 15 min. This study examined the compression force of the central and representative peripheral regions of native and thermodisinfected human femoral heads to observe wether different duration and intensity of heat exposure might alter mechanic behaviour. Slices from the equatorial region of human femoral heads were taken from each 14 native and thermodisinfected human femoral heads. The central area revealed a significantly higher compression force for native (p ≤ 0.001) and for thermodisinfected bone (p = 0.002 and p = 0.005) compared with peripheral regions since no relevant differences were found between the peripheral and intermediate areas themselves. A small reduction of compression force for thermodisinfected bone was shown since this did not appear significant due to the small number of specimens. The heat exposure did not alter the pre-existing anatomical changes of the microarchitecture of the native femoral heads from the center towards the peripheral regions. The heterogeneity of microstructure of the femoral head might be of interest concerning clinical applications of bone grafts since the difference between native and thermodisinfected bone appears moderate as shown previously. The different quantity of heat exposure did not reveal any significant influence on compression force which might enable thermodisinfection of preformed bone pieces for surgical indications.

Prediction of lumbar vertebral strength of elderly men based on quantitative computed tomography images using machine learning

The parameters extracted from quantitative computed tomography (QCT) images were used to predict vertebral strength through machine learning models, and the highly accurate prediction indicated that it may be a promising approach to assess fracture risk in clinics.

INTRODUCTION

Vertebral fracture is common in elderly populations. The main factor contributing to vertebral fracture is the reduced vertebral strength. This study aimed to predict vertebral strength based on clinical QCT images by using machine learning.

METHODS

Eighty subjects with QCT data of lumbar spine were randomly selected from the MrOS cohorts. L1 vertebral strengths were computed by QCT-based finite element analysis. A total of 58 features of each L1 vertebral body were extracted from QCT images, including grayscale distribution, grayscale values of 39 partitioned regions, BMD_QCT, structural rigidity, axial rigidity, and BMD_QCTA_min. Feature selection and dimensionality reduction were used to simplify the 58 features. General regression neural network and support vector regression models were developed to predict vertebral strength. Performance of prediction models was quantified by the mean squared error, the coefficient of determination, the mean bias, and the SD of bias.

RESULTS

The 58 parameters were simplified to five features (grayscale value of the 60% percentile, grayscale values of three specific partitioned regions, and BMD_QCTA_min) and nine principal components (PCs). High accuracy was achieved by using the five features or the nine PCs to predict vertebral strength.

CONCLUSIONS

This study provided an effective approach to predict vertebral strength and showed that it may have great potential in clinical applications for noninvasive assessment of vertebral fracture risk.

Artificial Intelligence in Musculoskeletal Imaging: Current Status and Future Directions

OBJECTIVE. The objective of this article is to show how artificial intelligence (AI) has impacted different components of the imaging value chain thus far as well as to describe its potential future uses. CONCLUSION. The use of AI has the potential to greatly enhance every component of the imaging value chain. From assessing the appropriateness of imaging orders to helping predict patients at risk for fracture, AI can increase the value that musculoskeletal imagers provide to their patients and to referring clinicians by improving image quality, patient centricity, imaging efficiency, and diagnostic accuracy.

Comparison of non-invasive assessments of strength of the proximal femur

It is not clear which non-invasive method is most effective for predicting strength of the proximal femur in those at highest risk of fracture. The primary aim of this study was to compare the abilities of dual energy X-ray absorptiometry (DXA)-derived aBMD, quantitative computed tomography (QCT)-derived density and volume measures, and finite element analysis (FEA)-estimated strength to predict femoral failure load. We also evaluated the contribution of cortical and trabecular bone measurements to proximal femur strength. We obtained 76 human cadaveric proximal femurs (50 women and 26 men; age 74±8.8years), performed imaging with DXA and QCT, and mechanically tested the femurs to failure in a sideways fall configuration at a high loading rate. Linear regression analysis was used to construct the predictive model between imaging outcomes and experimentally-measured femoral strength for each method. To compare the performance of each method we used 3-fold cross validation repeated 10 times. The bone strength estimated by QCT-based FEA predicted femoral failure load (R²_adj=0.78, 95%CI 0.76-0.80; RMSE=896N, 95%CI 830-961) significantly better than femoral neck aBMD by DXA (R²_adj=0.69, 95%CI 0.66-0.72; RMSE=1011N, 95%CI 952-1069) and the QCT-based model (R²_adj=0.73, 95%CI 0.71-0.75; RMSE=932N, 95%CI 879-985). Both cortical and trabecular bone contribute to femoral strength, the contribution of cortical bone being higher in femurs with lower trabecular bone density. These findings have implications for optimizing clinical approaches to assess hip fracture risk. In addition, our findings provide new insights that will assist in interpretation of the effects of osteoporosis treatments that preferentially impact cortical versus trabecular bone.

Assessing vertebral fracture risk on volumetric quantitative computed tomography by geometric characterization of trabecular bone structure

The current clinical standard for measuring Bone Mineral Density (BMD) is dual X-ray absorptiometry, however more recently BMD derived from volumetric quantitative computed tomography has been shown to demonstrate a high association with spinal fracture susceptibility. In this study, we propose a method of fracture risk assessment using structural properties of trabecular bone in spinal vertebrae. Experimental data was acquired via axial multi-detector CT (MDCT) from 12 spinal vertebrae specimens using a whole-body 256-row CT scanner with a dedicated calibration phantom. Common image processing methods were used to annotate the trabecular compartment in the vertebral slices creating a circular region of interest (ROI) that excluded cortical bone for each slice. The pixels inside the ROI were converted to values indicative of BMD. High dimensional geometrical features were derived using the scaling index method (SIM) at different radii and scaling factors (SF). The mean BMD values within the ROI were then extracted and used in conjunction with a support vector machine to predict the failure load of the specimens. Prediction performance was measured using the root-mean-square error (RMSE) metric and determined that SIM combined with mean BMD features (RMSE = 0.82 ± 0.37) outperformed MDCT-measured mean BMD (RMSE = 1.11 ± 0.33) (p < 10^-4). These results demonstrate that biomechanical strength prediction in vertebrae can be significantly improved through the use of SIM-derived texture features from trabecular bone.

Using Anisotropic 3D Minkowski Functionals for Trabecular Bone Characterization and Biomechanical Strength Prediction in Proximal Femur Specimens

The ability of Anisotropic Minkowski Functionals (AMFs) to capture local anisotropy while evaluating topological properties of the underlying gray-level structures has been previously demonstrated. We evaluate the ability of this approach to characterize local structure properties of trabecular bone micro-architecture in ex vivo proximal femur specimens, as visualized on multi-detector CT, for purposes of biomechanical bone strength prediction. To this end, volumetric AMFs were computed locally for each voxel of volumes of interest (VOI) extracted from the femoral head of 146 specimens. The local anisotropy captured by such AMFs was quantified using a fractional anisotropy measure; the magnitude and direction of anisotropy at every pixel was stored in histograms that served as a feature vectors that characterized the VOIs. A linear multi-regression analysis algorithm was used to predict the failure load (FL) from the feature sets; the predicted FL was compared to the true FL determined through biomechanical testing. The prediction performance was measured by the root mean square error (RMSE) for each feature set. The best prediction performance was obtained from the fractional anisotropy histogram of AMF Euler Characteristic (RMSE = 1.01 ± 0.13), which was significantly better than MDCT-derived mean BMD (RMSE = 1.12 ± 0.16, p<0.05). We conclude that such anisotropic Minkowski Functionals can capture valuable information regarding regional trabecular bone quality and contribute to improved bone strength prediction, which is important for improving the clinical assessment of osteoporotic fracture risk.

Investigating the use of texture features for analysis of breast lesions on contrast-enhanced cone beam CT

Cone beam computed tomography (CBCT) has found use in mammography for imaging the entire breast with sufficient spatial resolution at a radiation dose within the range of that of conventional mammography. Recently, enhancement of lesion tissue through the use of contrast agents has been proposed for cone beam CT. This study investigates whether the use of such contrast agents improves the ability of texture features to differentiate lesion texture from healthy tissue on CBCT in an automated manner. For this purpose, 9 lesions were annotated by an experienced radiologist on both regular and contrast-enhanced CBCT images using two-dimensional (2D) square ROIs. These lesions were then segmented, and each pixel within the lesion ROI was assigned a label - lesion or non-lesion, based on the segmentation mask. On both sets of CBCT images, four three-dimensional (3D) Minkowski Functionals were used to characterize the local topology at each pixel. The resulting feature vectors were then used in a machine learning task involving support vector regression with a linear kernel (SVRlin) to classify each pixel as belonging to the lesion or non-lesion region of the ROI. Classification performance was assessed using the area under the receiver-operating characteristic (ROC) curve (AUC). Minkowski Functionals derived from contrast-enhanced CBCT images were found to exhibit significantly better performance at distinguishing between lesion and non-lesion areas within the ROI when compared to those extracted from CBCT images without contrast enhancement (p < 0.05). Thus, contrast enhancement in CBCT can improve the ability of texture features to distinguish lesions from surrounding healthy tissue.

Predicting the Biomechanical Strength of Proximal Femur Specimens with Minkowski Functionals and Support Vector Regression

Regional trabecular bone quality estimation for purposes of femoral bone strength prediction is important for improving the clinical assessment of osteoporotic fracture risk. In this study, we explore the ability of 3D Minkowski Functionals derived from multi-detector computed tomography (MDCT) images of proximal femur specimens in predicting their corresponding biomechanical strength. MDCT scans were acquired for 50 proximal femur specimens harvested from human cadavers. An automated volume of interest (VOI)-fitting algorithm was used to define a consistent volume in the femoral head of each specimen. In these VOIs, the trabecular bone micro-architecture was characterized by statistical moments of its BMD distribution and by topological features derived from Minkowski Functionals. A linear multi-regression analysis and a support vector regression (SVR) algorithm with a linear kernel were used to predict the failure load (FL) from the feature sets; the predicted FL was compared to the true FL determined through biomechanical testing. The prediction performance was measured by the root mean square error (RMSE) for each feature set. The best prediction result was obtained from the Minkowski Functional surface used in combination with SVR, which had the lowest prediction error (RMSE = 0.939 ± 0.345) and which was significantly lower than mean BMD (RMSE = 1.075 ± 0.279, p<0.005). Our results indicate that the biomechanical strength prediction can be significantly improved in proximal femur specimens with Minkowski Functionals extracted from on MDCT images used in conjunction with support vector regression.

Phase contrast imaging X-ray computed tomography: Quantitative characterization of human patellar cartilage matrix with topological and geometrical features

Current assessment of cartilage is primarily based on identification of indirect markers such as joint space narrowing and increased subchondral bone density on x-ray images. In this context, phase contrast CT imaging (PCI-CT) has recently emerged as a novel imaging technique that allows a direct examination of chondrocyte patterns and their correlation to osteoarthritis through visualization of cartilage soft tissue. This study investigates the use of topological and geometrical approaches for characterizing chondrocyte patterns in the radial zone of the knee cartilage matrix in the presence and absence of osteoarthritic damage. For this purpose, topological features derived from Minkowski Functionals and geometric features derived from the Scaling Index Method (SIM) were extracted from 842 regions of interest (ROI) annotated on PCI-CT images of healthy and osteoarthritic specimens of human patellar cartilage. The extracted features were then used in a machine learning task involving support vector regression to classify ROIs as healthy or osteoarthritic. Classification performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC). The best classification performance was observed with high-dimensional geometrical feature vectors derived from SIM (0.95 ± 0.06) which outperformed all Minkowski Functionals (p < 0.001). These results suggest that such quantitative analysis of chondrocyte patterns in human patellar cartilage matrix involving SIM-derived geometrical features can distinguish between healthy and osteoarthritic tissue with high accuracy.