Texture analysis, bone mineral density, and cortical thickness of the proximal femur: fracture risk prediction

Feasibility of Bone Mineral Density and Bone Microarchitecture Assessment Using Deep Learning With a Convolutional Neural Network

OBJECTIVES

We evaluated the feasibility of using deep learning with a convolutional neural network for predicting bone mineral density (BMD) and bone microarchitecture from conventional computed tomography (CT) images acquired by multivendor scanners.

METHODS

We enrolled 402 patients who underwent noncontrast CT examinations, including L1-L4 vertebrae, and dual-energy x-ray absorptiometry (DXA) examination. Among these, 280 patients (3360 sagittal vertebral images), 70 patients (280 sagittal vertebral images), and 52 patients (208 sagittal vertebral images) were assigned to the training data set for deep learning model development, the validation, and the test data set, respectively. Bone mineral density and the trabecular bone score (TBS), an index of bone microarchitecture, were assessed by DXA. BMDDL and TBSDL were predicted by deep learning with a convolutional neural network (ResNet50). Pearson correlation tests assessed the correlation between BMDDL and BMD, and TBSDL and TBS. The diagnostic performance of BMDDL for osteopenia/osteoporosis and that of TBSDL for bone microarchitecture impairment were evaluated using receiver operating characteristic curve analysis.

RESULTS

BMDDL and BMD correlated strongly (r = 0.81, P < 0.01), whereas TBSDL and TBS correlated moderately (r = 0.54, P < 0.01). The sensitivity and specificity of BMDDL for identifying osteopenia or osteoporosis were 93% and 90%, and 100% and 94%, respectively. The sensitivity and specificity of TBSDL for identifying patients with bone microarchitecture impairment were 73% for all values.

CONCLUSIONS

The BMDDL and TBSDL derived from conventional CT images could identify patients who should undergo DXA, which could be a gatekeeper tool for detecting latent osteoporosis/osteopenia or bone microarchitecture impairment.

Update on Imaging-Based Measurement of Bone Mineral Density and Quality

PURPOSE OF REVIEW

Patients with inflammatory arthropathies have a high rate of fragility fractures. Diagnostic assessment and monitoring of bone density and quality are therefore critically important. Here, we review standard and advanced techniques to measure bone density and quality, specifically focusing on patients with inflammatory arthropathies.

RECENT FINDINGS

Current standard procedures are dual-energy X-ray absorptiometry (DXA) and quantitative computed tomography (QCT). DXA-based newer methods include trabecular bone score (TBS) and vertebral fracture assessment (VFA). More advanced imaging methods to measure bone quality include high-resolution peripheral quantitative computed tomography (HR-pQCT) as well as multi-detector CT (MD-CT) and magnetic resonance imaging (MRI). Quantitative ultrasound has shown promise but is not standard to assess bone fragility. While there are limitations, DXA remains the standard technique to measure density in patients with rheumatological disorders. Newer modalities to measure bone quality may allow better characterization of bone fragility but currently are not standard of care procedures.

Quantification of Volumetric Bone Mineral Density of Proximal Femurs Using a Two-Compartment Model and Computed Tomography Images

Objectives

Dual-energy X-ray absorptiometry (DXA) is frequently used to measure the areal bone mineral density (aBMD) in clinical practice. However, DXA measurements are affected by the bone thickness and the body size and are unable to indicate nonosseous areas within the trabecular bone. This study aims to quantify the volumetric bone mineral density (vBMD) using computed tomography (CT) images and the two-compartment model (TCM) methods.

Methods

The TCM method was proposed and validated by dipotassium phosphate (K₂HPO₄) phantoms and a standard forearm phantom. 28 cases with DXA scans and pelvic CT scans acquired within six months were retrospectively collected. The vBMD calculated by TCM was compared with the aBMD obtained from DXA.

Results

For the K₂HPO₄ phantoms with vBMD ranging from 0.135 to 0.467 g/cm³, the average difference between the real and calculated vBMD was 0.009 g/cm³ and the maximum difference was 0.019 g/cm³. For the standard forearm phantom with vBMD of 0.194, 0.103, and 0.054 g/cm³, the average differences between the real and calculated vBMD were 0.017, 0.014, and 0.011 g/cm³. In the clinical CT image validation, a good linear relationship between vBMD and aBMD was observed with the Pearson correlation coefficient of 0.920 (p < 0.01).

Conclusions

The proposed TCM method in combination with the homemade cortical bone equivalent phantom provides accurate quantification and spatial distribution of bone mineral content.

PET Radiomics in NSCLC: state of the art and a proposal for harmonization of methodology

Imaging with positron emission tomography (PET)/computed tomography (CT) is crucial in the management of cancer because of its value in tumor staging, response assessment, restaging, prognosis and treatment responsiveness prediction. In the last years, interest has grown in texture analysis which provides an "in-vivo" lesion characterization, and predictive information in several malignances including NSCLC; however several drawbacks and limitations affect these studies, especially because of lack of standardization in features calculation, definitions and methodology reporting. The present paper provides a comprehensive review of literature describing the state-of-the-art of FDG-PET/CT texture analysis in NSCLC, suggesting a proposal for harmonization of methodology.

Advances in imaging approaches to fracture risk evaluation

Fragility fractures are a growing problem worldwide, and current methods for diagnosing osteoporosis do not always identify individuals who require treatment to prevent a fracture and may misidentify those not a risk. Traditionally, fracture risk is assessed using dual-energy X-ray absorptiometry, which provides measurements of areal bone mineral density at sites prone to fracture. Recent advances in imaging show promise in adding new information that could improve the prediction of fracture risk in the clinic. As reviewed herein, advances in quantitative computed tomography (QCT) predict hip and vertebral body strength; high-resolution HR-peripheral QCT (HR-pQCT) and micromagnetic resonance imaging assess the microarchitecture of trabecular bone; quantitative ultrasound measures the modulus or tissue stiffness of cortical bone; and quantitative ultrashort echo-time MRI methods quantify the concentrations of bound water and pore water in cortical bone, which reflect a variety of mechanical properties of bone. Each of these technologies provides unique characteristics of bone and may improve fracture risk diagnoses and reduce prevalence of fractures by helping to guide treatment decisions.

Influence of different mechanical stimuli in a multi-scale mechanobiological isotropic model for bone remodelling

This work represents a study of a mathematical model that describes the biological response to different mechanical stimuli in a cellular dynamics model for bone remodelling. The biological system discussed herein consists of three specialised cellular types, responsive osteoblasts, active osteoblasts and osteoclasts, three types of signalling molecules, transforming growth factor beta (TGF-β), receptor activator of nuclear factor kappa-b ligand (RANKL) and osteoprotegerin (OPG) and the parathyroid hormone (PTH). Three proposals for mechanical stimuli were tested: strain energy density (SED), hydrostatic and deviatoric parts of SED. The model was tested in a two-dimensional geometry of a standard human femur. The spatial discretization was performed by the finite element method while the temporal evolution of the variables was calculated by the 4th order Runge-Kutta method. The obtained results represent the temporal evolution of the apparent density distribution and the mean apparent density and thickness for the cortical bone after 600 days of remodelling simulation. The main contributions of this paper are the coupling of mechanical and biological models and the exploration of how the different mechanical stimuli affect the cellular activity in different types of physical activities. The results revealed that hydrostatic SED stimulus was able to form more cortical bone than deviatoric SED and total SED stimuli. The computational model confirms how different mechanical stimuli can impact in the balance of bone homeostasis.

Axial QCT: clinical applications and new developments

Quantitative computed tomography (QCT) is currently undergoing a renaissance, with an increasing number of studies being published and the definition of both QCT-specific osteoporosis thresholds and treatment criteria. Compared with dual-energy X-ray absorptiometry, the current standard bone mineral density technique, QCT has a number of pertinent advantages, including volumetric measurements, less susceptibility to degenerative spine changes, and higher sensitivity to changes in bone mass. Disadvantages include the higher radiation doses and less experience with fracture prediction and therapy monitoring. Over the last 10 yr, a number of novel applications have been described allowing assessment of bone mineral density and bone quality in larger patient populations, developments that may substantially improve patient care.

Mechanical torque measurement in the proximal femur correlates to failure load and bone mineral density ex vivo

Knowledge of local bone quality is essential for surgeons to determine operation techniques. A device for intraoperative measurement of local bone quality has been developed by the AO-Research Foundation (Densi - Probe®). We used this device to experimentally measure peak breakaway torque of trabecular bone in the proximal femur and correlated this with local bone mineral density (BMD) and failure load. Bone mineral density of 160 cadaver femurs was measured by ex situ dualenergy X-ray absorptiometry. The failure load of all femurs was analyzed by side-impact analysis. Femur fractures were fixed and mechanical peak torque was measured with the DensiProbe® device. Correlation was calculated whereas correlation coefficient and significance was calculated by Fisher’s Ztransformation. Moreover, linear regression analysis was carried out. The unpaired Student’s t-test was used to assess the significance of differences. The Ward triangle region had the lowest BMD with 0.511 g/cm² (±0.17 g/cm²), followed by the upper neck region with 0.546 g/cm² (±0.16 g/cm²), trochanteric region with 0.685 g/cm² (±0.19 g/cm²) and the femoral neck with 0.813 g/cm² (±0.2 g/cm²). Peak torque of DensiProbe® in the femoral head was 3.48 Nm (±2.34 Nm). Load to failure was 4050.2 N (±1586.7 N). The highest correlation of peak torque measured by Densi Probe® and load to failure was found in the femoral neck (r=0.64, P<0.001). The overall correlation of mechanical peak torque with T-score was r=0.60 (P<0.001). A correlation was found between mechanical peak torque, load to failure of bone and BMD in vitro. Trabecular strength of bone and bone mineral density are different aspects of bone strength, but a correlation was found between them. Mechanical peak torque as measured may contribute additional information about bone strength, especially in the perioperative testing.

Osteoporosis imaging: state of the art and advanced imaging

Osteoporosis is becoming an increasingly important public health issue, and effective treatments to prevent fragility fractures are available. Osteoporosis imaging is of critical importance in identifying individuals at risk for fractures who would require pharmacotherapy to reduce fracture risk and also in monitoring response to treatment. Dual x-ray absorptiometry is currently the state-of-the-art technique to measure bone mineral density and to diagnose osteoporosis according to the World Health Organization guidelines. Motivated by a 2000 National Institutes of Health consensus conference, substantial research efforts have focused on assessing bone quality by using advanced imaging techniques. Among these techniques aimed at better characterizing fracture risk and treatment effects, high-resolution peripheral quantitative computed tomography (CT) currently plays a central role, and a large number of recent studies have used this technique to study trabecular and cortical bone architecture. Other techniques to analyze bone quality include multidetector CT, magnetic resonance imaging, and quantitative ultrasonography. In addition to quantitative imaging techniques measuring bone density and quality, imaging needs to be used to diagnose prevalent osteoporotic fractures, such as spine fractures on chest radiographs and sagittal multidetector CT reconstructions. Radiologists need to be sensitized to the fact that the presence of fragility fractures will alter patient care, and these fractures need to be described in the report. This review article covers state-of-the-art imaging techniques to measure bone mineral density, describes novel techniques to study bone quality, and focuses on how standard imaging techniques should be used to diagnose prevalent osteoporotic fractures.

Osteoporosis imaging: state of the art and advanced imaging

Osteoporosis is becoming an increasingly important public health issue, and effective treatments to prevent fragility fractures are available. Osteoporosis imaging is of critical importance in identifying individuals at risk for fractures who would require pharmacotherapy to reduce fracture risk and also in monitoring response to treatment. Dual x-ray absorptiometry is currently the state-of-the-art technique to measure bone mineral density and to diagnose osteoporosis according to the World Health Organization guidelines. Motivated by a 2000 National Institutes of Health consensus conference, substantial research efforts have focused on assessing bone quality by using advanced imaging techniques. Among these techniques aimed at better characterizing fracture risk and treatment effects, high-resolution peripheral quantitative computed tomography (CT) currently plays a central role, and a large number of recent studies have used this technique to study trabecular and cortical bone architecture. Other techniques to analyze bone quality include multidetector CT, magnetic resonance imaging, and quantitative ultrasonography. In addition to quantitative imaging techniques measuring bone density and quality, imaging needs to be used to diagnose prevalent osteoporotic fractures, such as spine fractures on chest radiographs and sagittal multidetector CT reconstructions. Radiologists need to be sensitized to the fact that the presence of fragility fractures will alter patient care, and these fractures need to be described in the report. This review article covers state-of-the-art imaging techniques to measure bone mineral density, describes novel techniques to study bone quality, and focuses on how standard imaging techniques should be used to diagnose prevalent osteoporotic fractures.