Computational identification and quantification of trabecular microarchitecture classes by 3-D texture analysis-based clustering

Machine learning applied to HR-pQCT images improves fracture discrimination provided by DXA and clinical risk factors

BACKGROUND

Traditional analysis of High Resolution peripheral Quantitative Computed Tomography (HR-pQCT) images results in a multitude of cortical and trabecular parameters which would be potentially cumbersome to interpret for clinicians compared to user-friendly tools utilising clinical parameters. A computer vision approach (by which the entire scan is 'read' by a computer algorithm) to ascertain fracture risk, would be far simpler. We therefore investigated whether a computer vision and machine learning technique could improve upon selected clinical parameters in assessing fracture risk.

METHODS

Participants of the Hertfordshire Cohort Study (HCS) attended research visits at which height and weight were measured; fracture history was determined via self-report and vertebral fracture assessment. Bone microarchitecture was assessed via HR-pQCT scans of the non-dominant distal tibia (Scanco XtremeCT), and bone mineral density measurement and lateral vertebral assessment were performed using dual-energy X-ray absorptiometry (DXA) (Lunar Prodigy Advanced). Images were cropped, pre-processed and texture analysis was performed using a three-dimensional local binary pattern method. These image data, together with age, sex, height, weight, BMI, dietary calcium and femoral neck BMD, were used in a random-forest classification algorithm. Receiver operating characteristic (ROC) analysis was used to compare fracture risk identification methods.

RESULTS

Overall, 180 males and 165 females were included in this study with a mean age of approximately 76 years and 97 (28 %) participants had sustained a previous fracture. Using clinical risk factors alone resulted in an area under the curve (AUC) of 0.70 (95 % CI: 0.56-0.84), which improved to 0.71 (0.57-0.85) with the addition of DXA-measured BMD. The addition of HR-pQCT image data to the machine learning classifier with clinical risk factors and DXA-measured BMD as inputs led to an improved AUC of 0.90 (0.83-0.96) with a sensitivity of 0.83 and specificity of 0.74.

CONCLUSION

These results suggest that using a three-dimensional computer vision method to HR-pQCT scanning may enhance the identification of those at risk of fracture beyond that afforded by clinical risk factors and DXA-measured BMD. This approach has the potential to make the information offered by HR-pQCT more accessible (and therefore) applicable to healthcare professionals in the clinic if the technology becomes more widely available.

Artificial intelligence-based radiomics on computed tomography of lumbar spine in subjects with fragility vertebral fractures

PURPOSE

There is emerging evidence that radiomics analyses can improve detection of skeletal fragility. In this cross-sectional study, we evaluated radiomics features (RFs) on computed tomography (CT) images of the lumbar spine in subjects with or without fragility vertebral fractures (VFs).

METHODS

Two-hundred-forty consecutive individuals (mean age 60.4 ± 15.4, 130 males) were evaluated by radiomics analyses on opportunistic lumbar spine CT. VFs were diagnosed in 58 subjects by morphometric approach on CT or XR-ray spine (D4-L4) images. DXA measurement of bone mineral density (BMD) was performed on 17 subjects with VFs.

RESULTS

Twenty RFs were used to develop the machine learning model reaching 0.839 and 0.789 of AUROC in the train and test datasets, respectively. After correction for age, VFs were significantly associated with RFs obtained from non-fractured vertebrae indicating altered trabecular microarchitecture, such as low-gray level zone emphasis (LGLZE) [odds ratio (OR) 1.675, 95% confidence interval (CI) 1.215-2.310], gray level non-uniformity (GLN) (OR 1.403, 95% CI 1.023-1.924) and neighboring gray-tone difference matrix (NGTDM) contrast (OR 0.692, 95% CI 0.493-0.971). Noteworthy, no significant differences in LGLZE (p = 0.94), GLN (p = 0.40) and NGDTM contrast (p = 0.54) were found between fractured subjects with BMD T score < - 2.5 SD and those in whom VFs developed in absence of densitometric diagnosis of osteoporosis.

CONCLUSIONS

Artificial intelligence-based analyses on spine CT images identified RFs associated with fragility VFs. Future studies are needed to test the predictive value of RFs on opportunistic CT scans in identifying subjects with primary and secondary osteoporosis at high risk of fracture.

Exercise and Diet: Uncovering Prospective Mediators of Skeletal Fragility in Bone and Marrow Adipose Tissue

PURPOSE OF REVIEW

To highlight recent basic, translational, and clinical works demonstrating exercise and diet regulation of marrow adipose tissue (MAT) and bone and how this informs current understanding of the relationship between marrow adiposity and musculoskeletal health.

RECENT FINDINGS

Marrow adipocytes accumulate in the bone in the setting of not only hypercaloric intake (calorie excess; e.g., diet-induced obesity) but also with hypocaloric intake (calorie restriction; e.g., anorexia), despite the fact that these states affect bone differently. With hypercaloric intake, bone quantity is largely unaffected, whereas with hypocaloric intake, bone quantity and quality are greatly diminished. Voluntary running exercise in rodents was found to lower MAT and promote bone in eucaloric and hypercaloric states, while degrading bone in hypocaloric states, suggesting differential modulation of MAT and bone, dependent upon whole-body energy status. Energy status alters bone metabolism and bioenergetics via substrate availability or excess, which plays a key role in the response of bone and MAT to mechanical stimuli. Marrow adipose tissue (MAT) is a fat depot with a potential role in-as well as responsivity to-whole-body energy metabolism. Understanding the localized function of this depot in bone cell bioenergetics and substrate storage, principally in the exercised state, will aid to uncover putative therapeutic targets for skeletal fragility.

"Variances" and "in-variances" in hierarchical porosity and composition, across femoral tissues from cow, horse, ostrich, emu, pig, rabbit, and frog

It is very well known that bone is a hierarchically organized material produced by bone cells residing in the fluid environments filling (larger) vascular pores and (smaller) lacunar pores. The extracellular space consists of hydroxyapatite crystals, collagen type I molecules, and water with non-collageneous organics. It is less known to which extent the associated quantities (mineral, organic, and water concentrations; vascular, lacunar, and extracellular porosities) vary across species, organs, and ages. We here investigate the aforementioned quantities across femoral shaft tissues from cow, horse, emu, frog, ostrich, pig, and rabbit; by means of light microscopy and dehydration-demineralization tests; thereby revealing interesting invariances: The extracellular volume fractions of organic matter turn out to be similar across all tested non-amphibian tissues; as do the extracellular volume fractions of hydroxyapatite across all tested mammals. Hence, the chemical composition of the femoral extracellular bone matrix is remarkably "invariant" across differently aged mammals; while the water content shows significant variations, as does the partitions of water between the different pore spaces. The latter exhibit strikingly varying morphologies as well. This finding adds to the ample "universal patterns" in the sense of evolutionary developmental biology; and it provides interesting design requirements for the development of novel biomimetic tissue engineering solutions.

Association of bone mineral density with bone texture attributes extracted using routine magnetic resonance imaging

OBJECTIVE

Dual-energy X-ray absorptiometry (DXA)-derived bone mineral density (BMD) often fails to predict fragility fractures. Quantitative textural analysis using magnetic resonance imaging (MRI) may potentially yield useful radiomic features to predict fractures. We aimed to investigate the correlation between BMD and texture attributes (TAs) extracted from MRI scans and the interobserver reproducibility of the analysis.

METHODS

Forty-nine volunteers underwent lumbar spine 1.5-T MRI and DXA. Three-dimensional (3-D) gray-level co-occurrence matrices were measured from routine sagittal T2 fast spin-echo images using the IBEX software. Twenty-two TAs were extracted from 3-D segmented L3 vertebrae. The estimated concordance coefficient was calculated using linear regression analysis. A Pearson correlation coefficient analysis was performed to evaluate the correlation between BMD and the TAs. Interobserver reproducibility was assessed with the concordance coefficient described by Lin.

RESULTS

The results revealed a fair-to-moderate significant correlation between BMD and 13 TAs (r=-0.20 to 0.39; p<0.05). Eight TAs (autocorrelation, energy, homogeneity 1, homogeneity 1.1, maximum probability, sum average, sum variance, and inverse difference normalized) negatively correlated with BMD (r=-0.20 to -0.38; p<0.05), whereas five TAs (dissimilarity, difference entropy, entropy, sum entropy, and information measure corr 1) positively correlated with BMD (r=0.29-0.39; p<0.05). The interobserver agreement was almost perfect for all significant TAs (95% confidence interval, 0.92-1.00; p<0.05).

CONCLUSION

Specific TAs could be reliably extracted from routine MRI and correlated with BMD. Our results encourage future evaluation of the potential usefulness of quantitative texture measurements from MRI scans for predicting fragility fractures.

A Comparison of Peripheral Imaging Technologies for Bone and Muscle Quantification: A Review of Segmentation Techniques

Musculoskeletal science has developed many overlapping branches, necessitating specialists from 1 area of focus to often require the expertise in others. In terms of imaging, this means obtaining a comprehensive illustration of bone, muscle, and fat tissues. There is currently a lack of a reliable resource for end users to learn about these tissues' imaging and quantification techniques together. An improved understanding of these tissues has been an important progression toward better prediction of disease outcomes and better elucidation of their interaction with frailty, aging, and metabolic disorders. Over the last decade, there have been major advances into the image acquisition and segmentation of bone, muscle, and fat features using computed tomography (CT), magnetic resonance imaging (MRI), and peripheral modules of these systems. Dedicated peripheral quantitative musculoskeletal imaging systems have paved the way for mobile research units, lower cost clinical research facilities, and improved resolution per unit cost paid. The purpose of this review was to detail the segmentation techniques available for each of these peripheral CT and MRI modalities and to describe advances in segmentation methods as applied to study longitudinal changes and treatment-related dynamics. Although the peripheral CT units described herein have established feasible standardized protocols that users have adopted globally, there remain challenges in standardizing MRI protocols for bone and muscle imaging.

Machine learning: from radiomics to discovery and routine

Machine learning is rapidly gaining importance in radiology. It allows for the exploitation of patterns in imaging data and in patient records for a more accurate and precise quantification, diagnosis, and prognosis. Here, we outline the basics of machine learning relevant for radiology, and review the current state of the art, the limitations, and the challenges faced as these techniques become an important building block of precision medicine. Furthermore, we discuss the roles machine learning can play in clinical routine and research and predict how it might change the field of radiology.

Opportunistic osteoporosis screening in multi-detector CT images via local classification of textures

Our study proposed an automatic pipeline for opportunistic osteoporosis screening using 3D texture features and regional vBMD using multi-detector CT images. A combination of different local and global texture features outperformed the global vBMD and showed high discriminative power to identify patients with vertebral fractures.

INTRODUCTION

Many patients at risk for osteoporosis undergo computed tomography (CT) scans, usable for opportunistic (non-dedicated) screening. We compared the performance of global volumetric bone mineral density (vBMD) with a random forest classifier based on regional vBMD and 3D texture features to separate patients with and without osteoporotic fractures.

METHODS

In total, 154 patients (mean age 64 ± 8.5, male; n = 103) were included in this retrospective single-center analysis, who underwent contrast-enhanced CT for other reasons than osteoporosis screening. Patients were dichotomized regarding prevalent vertebral osteoporotic fractures (noFX, n = 101; FX, n = 53). Vertebral bodies were automatically segmented, and trabecular vBMD was calculated with a dedicated phantom. For 3D texture analysis, we extracted gray-level co-occurrence matrix Haralick features (HAR), histogram of gradients (HoG), local binary patterns (LBP), and wavelets (WL). Fractured vertebrae were excluded for texture-feature and vBMD data extraction. The performance to identify patients with prevalent osteoporotic vertebral fractures was evaluated in a fourfold cross-validation.

RESULTS

The random forest classifier showed a high discriminatory power (AUC = 0.88). Parameters of all vertebral levels significantly contributed to this classification. Importantly, the AUC of the proposed algorithm was significantly higher than that of volumetric global BMD alone (AUC = 0.64).

CONCLUSION

The presented classifier combining 3D texture features and regional vBMD including the complete thoracolumbar spine showed high discriminatory power to identify patients with vertebral fractures and had a better diagnostic performance than vBMD alone.

Feasibility of opportunistic osteoporosis screening in routine contrast-enhanced multi detector computed tomography (MDCT) using texture analysis

This study investigated the feasibility of opportunistic osteoporosis screening in routine contrast-enhanced MDCT exams using texture analysis. The results showed an acceptable reproducibility of texture features, and these features could discriminate healthy/osteoporotic fracture cohort with an accuracy of 83%.

INTRODUCTION

This aim of this study is to investigate the feasibility of opportunistic osteoporosis screening in routine contrast-enhanced MDCT exams using texture analysis.

METHODS

We performed texture analysis at the spine in routine MDCT exams and investigated the effect of intravenous contrast medium (IVCM) (n = 7), slice thickness (n = 7), the long-term reproducibility (n = 9), and the ability to differentiate healthy/osteoporotic fracture cohort (n = 9 age and gender matched pairs). Eight texture features were extracted using gray level co-occurrence matrix (GLCM). The independent sample t test was used to rank the features of healthy/fracture cohort and classification was performed using support vector machine (SVM).

RESULTS

The results revealed significant correlations between texture parameters derived from MDCT scans with and without IVCM (r up to 0.91) slice thickness of 1 mm versus 2 and 3 mm (r up to 0.96) and scan-rescan (r up to 0.59). The performance of the SVM classifier was evaluated using 10-fold cross-validation and revealed an average classification accuracy of 83%.

CONCLUSIONS

Opportunistic osteoporosis screening at the spine using specific texture parameters (energy, entropy, and homogeneity) and SVM can be performed in routine contrast-enhanced MDCT exams.

Modeling and evaluation of a high-resolution CMOS detector for cone-beam CT of the extremities

PURPOSE

Quantitative assessment of trabecular bone microarchitecture in extremity cone-beam CT (CBCT) would benefit from the high spatial resolution, low electronic noise, and fast scan time provided by complementary metal-oxide semiconductor (CMOS) x-ray detectors. We investigate the performance of CMOS sensors in extremity CBCT, in particular with respect to potential advantages of thin (<0.7 mm) scintillators offering higher spatial resolution.

METHODS

A cascaded systems model of a CMOS x-ray detector incorporating the effects of CsI:Tl scintillator thickness was developed. Simulation studies were performed using nominal extremity CBCT acquisition protocols (90 kVp, 0.126 mAs/projection). A range of scintillator thickness (0.35-0.75 mm), pixel size (0.05-0.4 mm), focal spot size (0.05-0.7 mm), magnification (1.1-2.1), and dose (15-40 mGy) was considered. The detectability index was evaluated for both CMOS and a-Si:H flat-panel detector (FPD) configurations for a range of imaging tasks emphasizing spatial frequencies associated with feature size aobj. Experimental validation was performed on a CBCT test bench in the geometry of a compact orthopedic CBCT system (SAD = 43.1 cm, SDD = 56.0 cm, matching that of the Carestream OnSight 3D system). The test-bench studies involved a 0.3 mm focal spot x-ray source and two CMOS detectors (Dalsa Xineos-3030HR, 0.099 mm pixel pitch) - one with the standard CsI:Tl thickness of 0.7 mm (C700) and one with a custom 0.4 mm thick scintillator (C400). Measurements of modulation transfer function (MTF), detective quantum efficiency (DQE), and CBCT scans of a cadaveric knee (15 mGy) were obtained for each detector.

RESULTS

Optimal detectability for high-frequency tasks (feature size of ~0.06 mm, consistent with the size of trabeculae) was ~4× for the C700 CMOS detector compared to the a-Si:H FPD at nominal system geometry of extremity CBCT. This is due to ~5× lower electronic noise of a CMOS sensor, which enables input quantum-limited imaging at smaller pixel size. Optimal pixel size for high-frequency tasks was <0.1 mm for a CMOS, compared to ~0.14 mm for an a-Si:H FPD. For this fine pixel pitch, detectability of fine features could be improved by using a thinner scintillator to reduce light spread blur. A 22% increase in detectability of 0.06 mm features was found for the C400 configuration compared to C700. An improvement in the frequency at 50% modulation (f50 ) of MTF was measured, increasing from 1.8 lp/mm for C700 to 2.5 lp/mm for C400. The C400 configuration also achieved equivalent or better DQE as C700 for frequencies above ~2 mm-1 . Images of cadaver specimens confirmed improved visualization of trabeculae with the C400 sensor.

CONCLUSIONS

The small pixel size of CMOS detectors yields improved performance in high-resolution extremity CBCT compared to a-Si:H FPDs, particularly when coupled with a custom 0.4 mm thick scintillator. The results indicate that adoption of a CMOS detector in extremity CBCT can benefit applications in quantitative imaging of trabecular microstructure in humans.

Contribution of high resolution peripheral quantitative CT to the management of bone and joint diseases

Many imaging modalities have been described to diagnose and monitor osteoporosis (OP), osteoarthritis and inflammatory rheumatic diseases. Over the last ten years, High Resolution peripheral Quantitative Computerized Tomography (HR-pQCT) was shown to be a precise and non invasive technique to study bone and joint diseases in clinical research. It allows the study of both cortical and trabecular bone microarchitecture at the distal tibia and radius, and further applications have been developed such as the study of mechanical properties by the finite element analysis. Thus, in case-control and cross-sectional studies, microarchitecture parameters discriminated fractured individuals independently of areal BMD. Also, microstructure parameters can predict incident fracture in postmenopausal women. In metabolic diseases associated with bone fragility, HR-pQCT may also be used to explore bone changes. In joint disease studies, HR-pQCT was a remarkable tool to assess bone erosion and joint space narrowing at the hand. This article gives an overview of this imaging technique.

Musculoskeletal imaging in preventive medicine

The aim is to review the modalities in musculoskeletal imaging with view on the prognostic impact for the patient's and for social outcome and with view on three major fields of preventive medicine: nutrition and metabolism, sports, and patient education. The added value provided by preventive imaging is (1) to monitor bone health and body composition with a broad spectrum of biomarkers, (2) to detect and quantify variants or abnormalities of nerves, muscles, tendons, bones, and joints with a risk of overuse, rupture, or fracture, and (3) to develop radiology reports from the widely used narrative format to structured text and multimedia datasets. The awareness problem is a term for describing the underreporting and the underdiagnosis of fragility fractures in osteoporosis.

Two-wave behavior under various conditions of transition area from cancellous bone to cortical bone

The two-wave phenomenon, the wave separation of a single ultrasonic pulse in cancellous bone, is expected to be a useful tool for the diagnosis of osteoporosis. However, because actual bone has a complicated structure, precise studies on the effect of transition conditions between cortical and cancellous parts are required. This study investigated how the transition condition influenced the two-wave generation using three-dimensional X-ray CT images of an equine radius and a three-dimensional simulation technique. As a result, any changes in the boundary between cortical part and trabecular part, which gives the actual complex structure of bone, did not eliminate the generation of either the primary wave or the secondary wave at least in the condition of clear trabecular alignment. The results led us to the possibility of using the two-wave phenomenon in a diagnostic system for osteoporosis in cases of a complex boundary.

Advanced CT based in vivo methods for the assessment of bone density, structure, and strength

Based on spiral 3D tomography a large variety of applications have been developed during the last decade to asses bone mineral density, bone macro and micro structure, and bone strength. Quantitative computed tomography (QCT) using clinical whole body scanners provides separate assessment of trabecular, cortical, and subcortical bone mineral density (BMD) and content (BMC) principally in the spine and hip, although the distal forearm can also be assessed. Further bone macrostructure, for example bone geometry or cortical thickness can be quantified. Special high resolution peripheral CT (hr-pQCT) devices have been introduced to measure bone microstructure for example the trabecular architecture or cortical porosity at the distal forearm or tibia. 3D CT is also the basis for finite element analysis (FEA) to determine bone strength. QCT, hr-pQCT, and FEM are increasingly used in research as well as in clinical trials to complement areal BMD measurements obtained by the standard densitometric technique of dual x-ray absorptiometry (DXA). This review explains technical developments and demonstrates how QCT based techniques advanced our understanding of bone biology.