Assessing the effects of long-term osteoporosis treatment by using conventional spine radiographs: results from a pilot study in a sub-cohort of a large randomized controlled trial

Evaluation of fragility fracture risk using deep learning based on ultrasound radio frequency signal

BACKGROUND

It was essential to identify individuals at high risk of fragility fracture and prevented them due to the significant morbidity, mortality, and economic burden associated with fragility fracture. The quantitative ultrasound (QUS) showed promise in assessing bone structure characteristics and determining the risk of fragility fracture.

AIMS

To evaluate the performance of a multi-channel residual network (MResNet) based on ultrasonic radiofrequency (RF) signal to discriminate fragility fractures retrospectively in postmenopausal women, and compared it with the traditional parameter of QUS, speed of sound (SOS), and bone mineral density (BMD) acquired with dual X-ray absorptiometry (DXA).

METHODS

Using QUS, RF signal and SOS were acquired for 246 postmenopausal women. An MResNet was utilized, based on the RF signal, to categorize individuals with an elevated risk of fragility fracture. DXA was employed to obtain BMD at the lumbar, hip, and femoral neck. The fracture history of all adult subjects was gathered. Analyzing the odds ratios (OR) and the area under the receiver operator characteristic curves (AUC) was done to evaluate the effectiveness of various methods in discriminating fragility fracture.

RESULTS

Among the 246 postmenopausal women, 170 belonged to the non-fracture group, 50 to the vertebral group, and 26 to the non-vertebral fracture group. MResNet was competent to discriminate any fragility fracture (OR = 2.64; AUC = 0.74), Vertebral fracture (OR = 3.02; AUC = 0.77), and non-vertebral fracture (OR = 2.01; AUC = 0.69). After being modified by clinical covariates, the efficiency of MResNet was further improved to OR = 3.31-4.08, AUC = 0.81-0.83 among all fracture groups, which significantly surpassed QUS-SOS (OR = 1.32-1.36; AUC = 0.60) and DXA-BMD (OR = 1.23-2.94; AUC = 0.63-0.76).

CONCLUSIONS

This pilot cross-sectional study demonstrates that the MResNet model based on the ultrasonic RF signal shows promising performance in discriminating fragility fractures in postmenopausal women. When incorporating clinical covariates, the efficiency of the modified MResNet is further enhanced, surpassing the performance of QUS-SOS and DXA-BMD in terms of OR and AUC. These findings highlight the potential of the MResNet as a promising approach for fracture risk assessment. Future research should focus on larger and more diverse populations to validate these results and explore its clinical applications.

State of the Art Imaging of Osteoporosis

Osteoporosis is a common disease, particularly prevalent in geriatric populations, which causes significant worldwide morbidity due to increased bone fragility and fracture risk. Currently, the gold-standard modality for diagnosis and evaluation of osteoporosis progression and treatment relies on dual-energy x-ray absorptiometry (DXA), which measures bone mineral density (BMD) and calculates a score based upon standard deviation of measured BMD from the mean. However, other imaging modalities can also be used to evaluate osteoporosis. Here, we review historical as well as current research into development of new imaging modalities that can provide more nuanced or opportunistic analyses of bone quality, turnover, and density that can be helpful in triaging severity and determining treatment success in osteoporosis. We discuss the use of opportunistic computed tomography (CT) scans, as well as the use of quantitative CT to help determine fracture risk and perform more detailed bone quality analysis than would be allowed by DXA . Within magnetic resonance imaging (MRI), new developments include the use of advanced MRI techniques such as quantitative susceptibility mapping (QSM), magnetic resonance spectroscopy, and chemical shift encoding-based water-fat MRI (CSE-MRI) to enable clinicians improved assessment of nonmineralized bone compartments as well as a way to longitudinally assess bone quality without the repeated exposure to ionizing radiation. Within ultrasound, development of quantitative ultrasound shows promise particularly in future low-cost, broadly available screening tools. We focus primarily on historical and recent developments within radiotracer use as applicable to osteoporosis, particularly in the use of hybrid methods such as NaF-PET/CT, wherein patients with osteoporosis show reduced uptake of radiotracers such as NaF. Use of radiotracers may provide clinicians with even earlier detection windows for osteoporosis than would traditional biomarkers. Given the metabolic nature of this disease, current investigation into the role molecular imaging can play in the prediction of this disease as well as in replacing invasive diagnostic procedures shows particular promise.

Current Applications of Machine Learning in Spine: From Clinical View

STUDY DESIGN

Narrative review.

OBJECTIVES

This review aims to present current applications of machine learning (ML) in spine domain to clinicians.

METHODS

We conducted a comprehensive PubMed search of peer-reviewed articles that were published between 2006 and 2020 using terms (spine, spinal, lumbar, cervical, thoracic, machine learning) to examine ML in spine. Then exclude research of other domain, case report, review or meta-analysis, and which without available abstract or full text.

RESULTS

Total 1738 articles were retrieved from database, and 292 studies were finally included. Key findings of current applications were compiled and summarized in this review. Main clinical applications of those techniques including image processing, diagnosis, decision supporting, operative assistance, rehabilitation, surgery outcomes, complications, hospitalization and cost.

CONCLUSIONS

ML had achieved excellent performance and hold immense potential in spine. ML could help clinical staff to improve medical level, enhance work efficiency, and reduce adverse events. However more randomized controlled trials and improvement of interpretability are essential to clinicians accepting models' assistance in real work.

Can machine learning predict pharmacotherapy outcomes? An application study in osteoporosis

BACKGROUND AND OBJECTIVE

The specific aim of this study is to develop machine learning models as a clinical approach for personalized treatment of osteoporosis. The model performance on outcome prediction was compared between four machine learning algorithms.

METHODS

Retrospective, electronic clinical data for patients with suspected or confirmed osteoporosis treated at Wan Fang Hospital between 2011 to 2018 were used as inputs for building the following predictive machine learning models,i.e., artificial neural network (ANN), random forest (RF), support vector machine (SVM) and logistic regression (LR) models. The predicted outcome was defined as an increase/decrease in T-score after treatment. A genetic algorithm was employed to select relevant variables as input features for each model; the leave-one-out method was applied for model building and internal validation. The model with best performance was selected by a separate set of testing. Area under the receiver operating characteristic curve, accuracy, precision, sensitivity and F1 score were calculated to evaluate model performance. Main analysis for all the patients with subclinical or confirmed osteoporosis and subgroup analysis for the patients with confirmed osteoporosis (T score < -2.5) were carried out in this study.

RESULTS

A genetic algorithm was employed to select 12 to 18 features from all 33 variables for the four models. No difference was found in accuracy (ANN, 71.7%; LR, 70.0%; RF, 75.0%; SVM, 66.7%), precision (ANN, 80.0%; LR, 59.3%; RF, 70.0%; SVM, 63.6%), and AUC (ANN, 0.709; LR, 0.731; RF, 0.719; SVM, 0.702) among the ANN, LR, RF and SVM models. Main analysis in performance revealed significant recall in the LR model, as compared to ANN and SVM model; while subgroup revealed significant recall in ANN model, compared to LR and SVM model.

CONCLUSIONS

Machine learning-based models hold potential in forecasting the outcomes of treatment for osteoporosis via early initiation of first-line therapy for patients with subclinical disease; or a switch to second-line treatment for patients with a high risk of impending treatment failure. This convenient approach can assist clinicians in adjusting treatment tailored to individual patient for prevention of disease progression or ineffective therapy.

Artificial intelligence in spine care: current applications and future utility

PURPOSE

The field of artificial intelligence is ever growing and the applications of machine learning in spine care are continuously advancing. Given the advent of the intelligence-based spine care model, understanding the evolution of computation as it applies to diagnosis, treatment, and adverse event prediction is of great importance. Therefore, the current review sought to synthesize findings from the literature at the interface of artificial intelligence and spine research.

METHODS

A narrative review was performed based on the literature of three databases (MEDLINE, CINAHL, and Scopus) from January 2015 to March 2021 that examined historical and recent advancements in the understanding of artificial intelligence and machine learning in spine research. Studies were appraised for their role in, or description of, advancements within image recognition and predictive modeling for spinal research. Only English articles that fulfilled inclusion criteria were ultimately incorporated in this review.

RESULTS

This review briefly summarizes the history and applications of artificial intelligence and machine learning in spine. Three basic machine learning training paradigms: supervised learning, unsupervised learning, and reinforced learning are also discussed. Artificial intelligence and machine learning have been utilized in almost every facet of spine ranging from localization and segmentation techniques in spinal imaging to pathology specific algorithms which include but not limited to; preoperative risk assessment of postoperative complications, screening algorithms for patients at risk of osteoporosis and clustering analysis to identify subgroups within adolescent idiopathic scoliosis. The future of artificial intelligence and machine learning in spine surgery is also discussed with focusing on novel algorithms, data collection techniques and increased utilization of automated systems.

CONCLUSION

Improvements to modern-day computing and accessibility to various imaging modalities allow for innovative discoveries that may arise, for example, from management. Given the imminent future of AI in spine surgery, it is of great importance that practitioners continue to inform themselves regarding AI, its goals, use, and progression. In the future, it will be critical for the spine specialist to be able to discern the utility of novel AI research, particularly as it continues to pervade facets of everyday spine surgery.

Posterior instrumented fusion on lumbar stenosis syndrome can bring benefit to proximal degenerative kyphosis: A CONSORT-compliant article

ABSTRACT

The effect on degenerative thoracolumbar kyphosis (DTLK) after short-segment instrument for lumbar spinal stenosis syndrome (LSS) remains controversial. Based on the biomechanics and compensatory of the global spino-pelvic alignment, it was assumed that the interference on the lumbar spine, instead of the thoracolumbar segment, could still make a difference on the proximal spine.To explore whether DTLK could improve with only surgery for LSS and identify influencing factors on postoperative TLK.The study was performed from January 2016 to December 2018. Sixty-nine participants (25 male) diagnosed LSS with DTLK were enrolled and surgery was only for LSS. Radiological parameters included TLK, lumbar lordosis, pelvic incidence, pelvic tilt, sacral slope, and osteoporosis. Clinical outcomes were visual analogue scale and Oswestry disability index. According to lower instrumented vertebrae (LIV) on L5 or S1, inter-group comparisons were performed between LIV on L5 (L5 group) and S1 (S1 group).Demographics were well-matched between L5 and S1 group with a mean follow-up of 24.3 ± 12.1 (m). TLK improved with a mean of 16.2 ± 7.6 (°) (P < .001). There was no significance on radiological and clinical parameters between L5 and S1 groups except for a larger pelvic tilt in S1 group (P = .046). Visual analogue scale (P = .787) and Oswestry disability index (P = .530) were both indifferent between normal TLK and DTLK at last (P > .05). Postoperative TLK was affected by osteoporosis and sacral slope, the latter was dominated by pelvic incidence and pelvic rotation. Osteoporosis was the risk factor for TLK correction (P = .001, odd risk = 9.58).DTLK decreased if instrument only performed for LSS, where TLK and clinical outcomes are comparably affected whether L5 or S1 is selected as LIV. This study supplements the compensatory mechanism of spino-pelvic alignment, especially for cases with severe osteoporosis.

Analysis of bone architecture using fractal-based TX-Analyzer™ in adult patients with osteogenesis imperfecta

BACKGROUND

Osteogenesis imperfecta (OI) is a rare genetic disorder characterized by impaired bone quality and quantity. Established imaging techniques have limited reliability in OI. The TX-Analyzer™ is a new, fractal-based software allowing a non-invasive assessment of bone structure based on conventional radiographs. We explored whether the TX-Analyzer™ can discriminate OI patients and healthy controls. Furthermore, we investigated the correlation between TX-Analyzer™ parameters and (i) bone mineral density (BMD) by Dual Energy X-ray Absorptiometry (DXA), (ii) trabecular bone score (TBS), and (iii) bone microstructure by high-resolution peripheral quantitative computed tomography (HR-pQCT).

MATERIAL AND METHODS

Data of 29 adult OI patients were retrospectively analyzed. Standard radiographs of the thoracic and lumbar spine were evaluated using the TX-Analyzer™. Bone Structure Value (BSV), Bone Variance Value (BVV), and Bone Entropy Value (BEV) were measured at the vertebral bodies T7 to L5. Data were compared to a healthy, age- and gender-matched control group (n = 58). BMD by DXA, TBS, and trabecular bone microstructure by means of HR-pQCT were correlated to TX-Analyzer™ parameters in OI patients. The accuracy of the TX-Analyzer™ parameters in detecting OI was assessed with area under curve (AUC) analysis of receiver operating characteristic (ROC).

RESULTS

BEV of the thoracic and the lumbar spine were significantly lower in OI patients compared to controls (both p < 0.001). BEV of the thoracic spine was significantly correlated to TBS (ρ = 0.427, p = 0.042) as well as trabecular number (Tb.N) at the radius (ρ = 0.603, p = 0.029) and inhomogeneity of the trabecular network (Tb.1/N.SD) at the radius (ρ = -0.610, p = 0.027), when assessed by HR-pQCT. No correlations were found between BEV and BMD by DXA. BEV of the thoracic and the lumbar spine had an AUC of 0.81 (95% confidence interval [CI] 0.67-0.94, p < 0.001) and 0.73 (95% CI 0.56-0.89, p = 0.008), respectively. BSV and BVV did not differ between OI patients and controls.

CONCLUSION

The software TX-Analyzer™ is able to discriminate patients with OI from healthy controls. ROC curves of BEV values suggest a suitable clinical applicability. Low to no correlations with conventional methods suggest, that the TX-Analyzer™ may indicate a new and independent examination tool in OI.

Fractal-Based Analysis of Bone Microstructure in Crohn's Disease: A Pilot Study

Crohn's disease (CD) is associated with bone loss and increased fracture risk. TX-Analyzer™ is a new fractal-based technique to evaluate bone microarchitecture based on conventional radiographs. The aim of the present study was to evaluate the TX-Analyzer™ of the thoracic and lumbar spine in CD patients and healthy controls (CO) and to correlate the parameters to standard imaging techniques. 39 CD patients and 39 age- and sex-matched CO were analyzed. Demographic parameters were comparable between CD and CO. Bone structure value (BSV), bone variance value (BVV) and bone entropy value (BEV) were measured at the vertebral bodies of T7 to L4 out of lateral radiographs. Bone mineral density (BMD) and trabecular bone score (TBS) by dual energy X-ray absorptiometry (DXA) were compared to TX parameters. BSV and BVV of the thoracic spine of CD were higher compared to controls, with no difference in BEV. Patients were further divided into subgroups according to the presence of a history of glucocorticoid treatment, disease duration > 15 years and bowel resection. BEV was significantly lower in CD patients with these prevalent risk factors, with no differences in BMD at all sites. Additionally, TBS was reduced in patients with a history of glucocorticoid treatment. Despite a not severely pronounced bone loss in this population, impaired bone quality in CD patients with well-known risk factors for systemic bone loss was assessed by TX-Analyzer™.

Deep Learning for Osteoporosis Classification Using Hip Radiographs and Patient Clinical Covariates

This study considers the use of deep learning to diagnose osteoporosis from hip radiographs, and whether adding clinical data improves diagnostic performance over the image mode alone. For objective labeling, we collected a dataset containing 1131 images from patients who underwent both skeletal bone mineral density measurement and hip radiography at a single general hospital between 2014 and 2019. Osteoporosis was assessed from the hip radiographs using five convolutional neural network (CNN) models. We also investigated ensemble models with clinical covariates added to each CNN. The accuracy, precision, recall, specificity, negative predictive value (npv), F1 score, and area under the curve (AUC) score were calculated for each network. In the evaluation of the five CNN models using only hip radiographs, GoogleNet and EfficientNet b3 exhibited the best accuracy, precision, and specificity. Among the five ensemble models, EfficientNet b3 exhibited the best accuracy, recall, npv, F1 score, and AUC score when patient variables were included. The CNN models diagnosed osteoporosis from hip radiographs with high accuracy, and their performance improved further with the addition of clinical covariates from patient records.

Artificial intelligence, osteoporosis and fragility fractures

PURPOSE OF REVIEW

Artificial intelligence tools have found new applications in medical diagnosis. These tools have the potential to capture underlying trends and patterns, otherwise impossible with previous modeling capabilities. Machine learning and deep learning models have found a role in osteoporosis, both to model the risk of fragility fracture, and to help with the identification and segmentation of images.

RECENT FINDINGS

Here we survey the latest research in the artificial intelligence application to the prediction of osteoporosis that has been published between January 2017 and March 2019. Around half of the articles that are covered here predict (by classification or regression) an indicator of osteoporosis, such as bone mass or fragility fractures; the other half of studies use tools for automatic segmentation of the images of patients with or at risk of osteoporosis. The data for these studies include diverse signal sources: acoustics, MRI, CT, and of course, X-rays.

SUMMARY

New methods for automatic image segmentation, and prediction of fracture risk show promising clinical value. Though these recent developments have had a successful initial application to osteoporosis research, their development is still under improvement, such as accounting for positive/negative class bias. We urge care when reporting accuracy metrics, and when comparing such metrics between different studies.

Quantification in Musculoskeletal Imaging Using Computational Analysis and Machine Learning: Segmentation and Radiomics

Although still limited in clinical practice, quantitative analysis is expected to increase the value of musculoskeletal (MSK) imaging. Segmentation aims at isolating the tissues and/or regions of interest in the image and is crucial to the extraction of quantitative features such as size, signal intensity, or image texture. These features may serve to support the diagnosis and monitoring of disease. Radiomics refers to the process of extracting large amounts of features from radiologic images and combining them with clinical, biological, genetic, or any other type of complementary data to build diagnostic, prognostic, or predictive models. The advent of machine learning offers promising prospects for automatic segmentation and integration of large amounts of data. We present commonly used segmentation methods and describe the radiomics pipeline, highlighting the challenges to overcome for adoption in clinical practice. We provide some examples of applications from the MSK literature.