Vertebral body insufficiency fractures: detection of vertebrae at risk on standard CT images using texture analysis and machine learning

Development and validation of a predictive model for vertebral fracture risk in osteoporosis patients

OBJECTIVE

This study aimed to develop and validate a predictive model for osteoporotic vertebral fractures (OVFs) risk by integrating demographic, bone mineral density (BMD), CT imaging, and deep learning radiomics features from CT images.

METHODS

A total of 169 osteoporosis-diagnosed patients from three hospitals were randomly split into OVFs (n = 77) and Non-OVFs (n = 92) groups for training (n = 135) and test (n = 34). Demographic data, BMD, and CT imaging details were collected. Deep transfer learning (DTL) using ResNet-50 and radiomics features were fused, with the best model chosen via logistic regression. Cox proportional hazards models identified clinical factors. Three models were constructed: clinical, radiomics-DTL, and fusion (clinical-radiomics-DTL). Performance was assessed using AUC, C-index, Kaplan-Meier, and calibration curves. The best model was depicted as a nomogram, and clinical utility was evaluated using decision curve analysis (DCA).

RESULTS

BMD, CT values of paravertebral muscles (PVM), and paravertebral muscles' cross-sectional area (CSA) significantly differed between OVFs and Non-OVFs groups (P < 0.05). No significant differences were found between training and test cohort. Multivariate Cox models identified BMD, CT values of PVM, and CSAPS reduction as independent OVFs risk factors (P < 0.05). The fusion model exhibited the highest predictive performance (C-index: 0.839 in training, 0.795 in test). DCA confirmed the nomogram's utility in OVFs risk prediction.

CONCLUSION

This study presents a robust predictive model for OVFs risk, integrating BMD, CT data, and radiomics-DTL features, offering high sensitivity and specificity. The model's visualizations can inform OVFs prevention and treatment strategies.

Can generative artificial intelligence pass the orthopaedic board examination?

Background

Resident training programs in the US use the Orthopaedic In-Training Examination (OITE) developed by the American Academy of Orthopaedic Surgeons (AAOS) to assess the current knowledge of their residents and to identify the residents at risk of failing the Amerian Board of Orthopaedic Surgery (ABOS) examination. Optimal strategies for OITE preparation are constantly being explored. There may be a role for Large Language Models (LLMs) in orthopaedic resident education. ChatGPT, an LLM launched in late 2022 has demonstrated the ability to produce accurate, detailed answers, potentially enabling it to aid in medical education and clinical decision-making. The purpose of this study is to evaluate the performance of ChatGPT on Orthopaedic In-Training Examinations using Self-Assessment Exams from the AAOS database and approved literature as a proxy for the Orthopaedic Board Examination.

Methods

301 SAE questions from the AAOS database and associated AAOS literature were input into ChatGPT's interface in a question and multiple-choice format and the answers were then analyzed to determine which answer choice was selected. A new chat was used for every question. All answers were recorded, categorized, and compared to the answer given by the OITE and SAE exams, noting whether the answer was right or wrong.

Results

Of the 301 questions asked, ChatGPT was able to correctly answer 183 (60.8%) of them. The subjects with the highest percentage of correct questions were basic science (81%), oncology (72.7%, shoulder and elbow (71.9%), and sports (71.4%). The questions were further subdivided into 3 groups: those about management, diagnosis, or knowledge recall. There were 86 management questions and 47 were correct (54.7%), 45 diagnosis questions with 32 correct (71.7%), and 168 knowledge recall questions with 102 correct (60.7%).

Conclusions

ChatGPT has the potential to provide orthopedic educators and trainees with accurate clinical conclusions for the majority of board-style questions, although its reasoning should be carefully analyzed for accuracy and clinical validity. As such, its usefulness in a clinical educational context is currently limited but rapidly evolving.

Clinical relevance

ChatGPT can access a multitude of medical data and may help provide accurate answers to clinical questions.

Muscle texture features on preoperative MRI for diagnosis and assessment of severity of congenital muscular torticollis

OBJECTIVES

To develop an objective method based on texture analysis on MRI for diagnosis of congenital muscular torticollis (CMT).

MATERIAL AND METHODS

The T1- and T2-weighted imaging, Q-dixon, and T1-mapping MRI data of 38 children with CMT were retrospectively analyzed. The region of interest (ROI) was manually drawn at the level of the largest cross-sectional area of the SCM on the affected side. MaZda software was used to obtain the texture features of the T2WI sequences of the ROI in healthy and affected SCM. A radiomics diagnostic model based on muscle texture features was constructed using logistic regression analysis. Fatty infiltration grade was calculated by hematoxylin and eosin staining, and fibrosis ratio by Masson staining. Correlation between the MRI parameters and pathological indicators was analyzed.

RESULTS

There was positive correlation between fatty infiltration grade and mean value, standard deviation, and maximum value of the Q-dixon sequence of the affected SCM (correlation coefficients, 0.65, 0.59, and 0.58, respectively, P < 0.05).Three muscle texture features-S(2,2)SumAverg, S(3,3)SumVarnc, and T2WI extreme difference-were selected to construct the diagnostic model. The model showed significant diagnostic value for CMT (P < 0.05). The area under the curve of the multivariate conditional logistic regression model was 0.828 (95% confidence interval 0.735-0.922); the sensitivity was 0.684 and the specificity 0.868.

CONCLUSION

The radiomics diagnostic model constructed using T2WI muscle texture features and MRI signal values appears to have good diagnostic efficiency. Q-dixon sequence can reflect the fatty infiltration grade of CMT.

Exploring deep learning radiomics for classifying osteoporotic vertebral fractures in X-ray images

Purpose

To develop and validate a deep learning radiomics (DLR) model that uses X-ray images to predict the classification of osteoporotic vertebral fractures (OVFs).

Material and methods

The study encompassed a cohort of 942 patients, involving examinations of 1076 vertebrae through X-ray, CT, and MRI across three distinct hospitals. The OVFs were categorized as class 0, 1, or 2 based on the Assessment System of Thoracolumbar Osteoporotic Fracture. The dataset was divided randomly into four distinct subsets: a training set comprising 712 samples, an internal validation set with 178 samples, an external validation set containing 111 samples, and a prospective validation set consisting of 75 samples. The ResNet-50 architectural model was used to implement deep transfer learning (DTL), undergoing -pre-training separately on the RadImageNet and ImageNet datasets. Features from DTL and radiomics were extracted and integrated using X-ray images. The optimal fusion feature model was identified through least absolute shrinkage and selection operator logistic regression. Evaluation of the predictive capabilities for OVFs classification involved eight machine learning models, assessed through receiver operating characteristic curves employing the "One-vs-Rest" strategy. The Delong test was applied to compare the predictive performance of the superior RadImageNet model against the ImageNet model.

Results

Following pre-training separately on RadImageNet and ImageNet datasets, feature selection and fusion yielded 17 and 12 fusion features, respectively. Logistic regression emerged as the optimal machine learning algorithm for both DLR models. Across the training set, internal validation set, external validation set, and prospective validation set, the macro-average Area Under the Curve (AUC) based on the RadImageNet dataset surpassed those based on the ImageNet dataset, with statistically significant differences observed (P<0.05). Utilizing the binary "One-vs-Rest" strategy, the model based on the RadImageNet dataset demonstrated superior efficacy in predicting Class 0, achieving an AUC of 0.969 and accuracy of 0.863. Predicting Class 1 yielded an AUC of 0.945 and accuracy of 0.875, while for Class 2, the AUC and accuracy were 0.809 and 0.692, respectively.

Conclusion

The DLR model, based on the RadImageNet dataset, outperformed the ImageNet model in predicting the classification of OVFs, with generalizability confirmed in the prospective validation set.

Insights and implications of sexual dimorphism in osteoporosis

Osteoporosis, a metabolic bone disease characterized by low bone mineral density and deterioration of bone microarchitecture, has led to a high risk of fatal osteoporotic fractures worldwide. Accumulating evidence has revealed that sexual dimorphism is a notable feature of osteoporosis, with sex-specific differences in epidemiology and pathogenesis. Specifically, females are more susceptible than males to osteoporosis, while males are more prone to disability or death from the disease. To date, sex chromosome abnormalities and steroid hormones have been proven to contribute greatly to sexual dimorphism in osteoporosis by regulating the functions of bone cells. Understanding the sex-specific differences in osteoporosis and its related complications is essential for improving treatment strategies tailored to women and men. This literature review focuses on the mechanisms underlying sexual dimorphism in osteoporosis, mainly in a population of aging patients, chronic glucocorticoid administration, and diabetes. Moreover, we highlight the implications of sexual dimorphism for developing therapeutics and preventive strategies and screening approaches tailored to women and men. Additionally, the challenges in translating bench research to bedside treatments and future directions to overcome these obstacles will be discussed.

A Bibliometric Analysis of Artificial Intelligence Applications in Spine Care

BACKGROUND

 With the rapid development of science and technology, artificial intelligence (AI) has been widely used in the diagnosis and prognosis of various spine diseases. It has been proved that AI has a broad prospect in accurate diagnosis and treatment of spine disorders.

METHODS

 On May 7, 2022, the Web of Science (WOS) Core Collection database was used to identify the documents on the application of AI in the field of spine care. HistCite and VOSviewer were used for citation analysis and visualization mapping.

RESULTS

 A total of 693 documents were included in the final analysis. The most prolific authors were Karhade A.V. and Schwab J.H. United States was the most productive country. The leading journal was Spine. The most frequently used keyword was spinal. The most prolific institution was Northwestern University in Illinois, USA. Network visualization map showed that United States was the largest network of international cooperation. The keyword "machine learning" had the strongest total link strengths (TLS) and largest number of occurrences. The latest trends suggest that AI for the diagnosis of spine diseases may receive widespread attention in the future.

CONCLUSIONS

 AI has a wide range of application in the field of spine care, and an increasing number of scholars are committed to research on the use of AI in the field of spine care. Bibliometric analysis in the field of AI and spine provides an overall perspective, and the appreciation and research of these influential publications are useful for future research.

AI algorithms for accurate prediction of osteoporotic fractures in patients with diabetes: an up-to-date review

Osteoporotic fractures impose a substantial burden on patients with diabetes due to their unique characteristics in bone metabolism, limiting the efficacy of conventional fracture prediction tools. Artificial intelligence (AI) algorithms have shown great promise in predicting osteoporotic fractures. This review aims to evaluate the application of traditional fracture prediction tools (FRAX, QFracture, and Garvan FRC) in patients with diabetes and osteoporosis, review AI-based fracture prediction achievements, and assess the potential efficiency of AI algorithms in this population. This comprehensive literature search was conducted in Pubmed and Web of Science. We found that conventional prediction tools exhibit limited accuracy in predicting fractures in patients with diabetes and osteoporosis due to their distinct bone metabolism characteristics. Conversely, AI algorithms show remarkable potential in enhancing predictive precision and improving patient outcomes. However, the utilization of AI algorithms for predicting osteoporotic fractures in diabetic patients is still in its nascent phase, further research is required to validate their efficacy and assess the potential advantages of their application in clinical practice.

Differentiation of benign and malignant vertebral fractures using a convolutional neural network to extract CT-based texture features

PURPOSE

To assess the diagnostic performance of three-dimensional (3D) CT-based texture features (TFs) using a convolutional neural network (CNN)-based framework to differentiate benign (osteoporotic) and malignant vertebral fractures (VFs).

METHODS

A total of 409 patients who underwent routine thoracolumbar spine CT at two institutions were included. VFs were categorized as benign or malignant using either biopsy or imaging follow-up of at least three months as standard of reference. Automated detection, labelling, and segmentation of the vertebrae were performed using a CNN-based framework ( https://anduin.bonescreen.de ). Eight TFs were extracted: Varianceglobal, Skewnessglobal, energy, entropy, short-run emphasis (SRE), long-run emphasis (LRE), run-length non-uniformity (RLN), and run percentage (RP). Multivariate regression models adjusted for age and sex were used to compare TFs between benign and malignant VFs.

RESULTS

Skewnessglobal showed a significant difference between the two groups when analyzing fractured vertebrae from T1 to L6 (benign fracture group: 0.70 [0.64-0.76]; malignant fracture group: 0.59 [0.56-0.63]; and p = 0.017), suggesting a higher skewness in benign VFs compared to malignant VFs.

CONCLUSION

Three-dimensional CT-based global TF skewness assessed using a CNN-based framework showed significant difference between benign and malignant thoracolumbar VFs and may therefore contribute to the clinical diagnostic work-up of patients with VFs.

Computer Vision in Osteoporotic Vertebral Fracture Risk Prediction: A Systematic Review

Osteoporotic vertebral fractures (OVFs) are a significant health concern linked to increased morbidity, mortality, and diminished quality of life. Traditional OVF risk assessment tools like bone mineral density (BMD) only capture a fraction of the risk profile. Artificial intelligence, specifically computer vision, has revolutionized other fields of medicine through analysis of videos, histopathology slides and radiological scans. In this review, we provide an overview of computer vision algorithms and current computer vision models used in predicting OVF risk. We highlight the clinical applications, future directions and limitations of computer vision in OVF risk prediction.

MRI-based radiomics assessment of the imminent new vertebral fracture after vertebral augmentation

BACKGROUND

Imminent new vertebral fracture (NVF) is highly prevalent after vertebral augmentation (VA). An accurate assessment of the imminent risk of NVF could help to develop prompt treatment strategies.

PURPOSE

To develop and validate predictive models that integrated the radiomic features and clinical risk factors based on machine learning algorithms to evaluate the imminent risk of NVF.

MATERIALS AND METHODS

In this retrospective study, a total of 168 patients with painful osteoporotic vertebral compression fractures treated with VA were evaluated. Radiomic features of L1 vertebrae based on lumbar T2-weighted images were obtained. Univariate and LASSO-regression analyses were applied to select the optimal features and construct radiomic signature. The radiomic signature and clinical signature were integrated to develop a predictive model by using machine learning algorithms including LR, RF, SVM, and XGBoost. Receiver operating characteristic curve and calibration curve analyses were used to evaluate the predictive performance of the models.

RESULTS

The radiomic-XGBoost model with the highest AUC of 0.93 of the training cohort and 0.9 of the test cohort among the machine learning algorithms. The combined-XGBoost model with the best performance with an AUC of 0.9 in the training cohort and 0.9 in the test cohort. The radiomic-XGBoost model and combined-XGBoost model achieved better performance to assess the imminent risk of NVF than that of the clinical risk factors alone (p < 0.05).

CONCLUSION

Radiomic and machine learning modeling based on T2W images of preoperative lumbar MRI had an excellent ability to evaluate the imminent risk of NVF after VA.

The value of radiomics-based CT combined with machine learning in the diagnosis of occult vertebral fractures

PURPOSE

To develop and evaluate the performance of radiomics-based computed tomography (CT) combined with machine learning algorithms in detecting occult vertebral fractures (OVFs).

MATERIALS AND METHODS

128 vertebrae including 64 with OVF confirmed by magnetic resonance imaging and 64 corresponding control vertebrae from 57 patients who underwent chest/abdominal CT scans, were included. The CT radiomics features on mid-axial and mid-sagittal plane of each vertebra were extracted. The fractured and normal vertebrae were randomly divided into training set and validation set at a ratio of 8:2. Pearson correlation analyses and least absolute shrinkage and selection operator were used for selecting sagittal and axial features, respectively. Three machine-learning algorithms were used to construct the radiomics models based on the residual features. Receiver operating characteristic (ROC) analysis was used to verify the performance of model.

RESULTS

For mid-axial CT imaging, 6 radiomics parameters were obtained and used for building the models. The logistic regression (LR) algorithm showed the best performance with area under the ROC curves (AUC) of training and validation sets of 0.682 and 0.775. For mid-sagittal CT imaging, 5 parameters were selected, and LR algorithms showed the best performance with AUC of training and validation sets of 0.832 and 0.882. The LR model based on sagittal CT yielded the best performance, with an accuracy of 0.846, sensitivity of 0.846, and specificity of 0.846.

CONCLUSION

Machine learning based on CT radiomics features allows for the detection of OVFs, especially the LR model based on the radiomics of sagittal imaging, which indicates it is promising to further combine with deep learning to achieve automatic recognition of OVFs to reduce the associated secondary injury.

Machine learning model for the prediction of gram-positive and gram-negative bacterial bloodstream infection based on routine laboratory parameters

BACKGROUND

Bacterial bloodstream infection is responsible for the majority of cases of sepsis and septic shock. Early recognition of the causative pathogen is pivotal for administration of adequate empiric antibiotic therapy and for the survival of the patients. In this study, we developed a feasible machine learning (ML) model to predict gram-positive and gram-negative bacteremia based on routine laboratory parameters.

METHODS

Data for 2118 patients with bacteremia were obtained from the Medical Information Mart for Intensive Care dataset. Patients were randomly split into the training set and test set by stratified sampling, and 374 routine laboratory blood test variables were retrieved. Variables with missing values in more than 40% of the patients were excluded. Pearson correlation test was employed to eliminate redundant features. Five ML algorithms were used to build the model based on the selected features. Additionally, 132 patients with bacteremia who were treated at Qilu Hospital of Shandong University were included in an independent test cohort to evaluate the model.

RESULTS

After feature selection, 32 variables remained. All the five ML algorithms performed well in terms of discriminating between gram-positive and gram-negative bacteremia, but the performance of convolutional neural network (CNN) and random forest (RF) were better than other three algorithms. Consider of the interpretability of models, RF was chosen for further test (ROC-AUC = 0.768; 95%CI = 0.715-0.798, with a sensitivity of 75.20% and a specificity of 63.79%). To expand the application of the model, a decision tree (DT) was built utilizing the major variables, and it achieved an AUC of 0.679 (95%CI = 0.632-0.723), a sensitivity of 66%, and a specificity of 67.82% in the test cohort. When tested in the Qilu Hospital cohort, the ROC-AUC of the RF and DT models were 0.666 (95%CI = 0.579-0.746) and 0.615 (95%CI = 0.526-0.698), respectively. Finally, a software was developed to make the RF- and DT-based prediction models easily accessible.

CONCLUSION

The present ML-based models could effectively discriminate between gram-positive and gram-negative bacteremia based on routine laboratory blood test results. This simple model would be beneficial in terms of guiding timely antibiotic selection and administration in critically ill patients with bacteremia before their pathogen test results are available.

MRI-Based Radiomics Analysis of Levator Ani Muscle for Predicting Urine Incontinence after Robot-Assisted Radical Prostatectomy

BACKGROUND

The exact role of the levator ani (LA) muscle in male continence remains unclear, and so this study aims to shed light on the topic by characterizing MRI-derived radiomic features of LA muscle and their association with postoperative incontinence in men undergoing prostatectomy.

METHOD

In this retrospective study, 140 patients who underwent robot-assisted radical prostatectomy (RARP) for prostate cancer using preoperative MRI were identified. A biomarker discovery approach based on the optimal biomarker (OBM) method was used to extract features from MRI images, including morphological, intensity-based, and texture-based features of the LA muscle, along with clinical variables. Mathematical models were created using subsets of features and were evaluated based on their ability to predict continence outcomes.

RESULTS

Univariate analysis showed that the best discriminators between continent and incontinent patients were patients age and features related to LA muscle texture. The proposed feature selection approach found that the best classifier used six features: age, LA muscle texture properties, and the ratio between LA size descriptors. This configuration produced a classification accuracy of 0.84 with a sensitivity of 0.90, specificity of 0.75, and an area under the ROC curve of 0.89.

CONCLUSION

This study found that certain patient factors, such as increased age and specific texture properties of the LA muscle, can increase the odds of incontinence after RARP. The results showed that the proposed approach was highly effective and could distinguish and predict continents from incontinent patients with high accuracy.

Opportunistic Computed Tomography Screening for Osteoporosis and Fracture

Osteoporosis is underdiagnosed and undertreated, leading to loss of treatment for the patient and high costs for the health care system. Routine thoracic and/or abdominal computed tomography (CT) performed for other indications can screen opportunistically for osteoporosis with no extra cost, time, or irradiation. Various methods can quantify fracture risk on opportunistic clinical CT: vertebral Hounsfield unit bone mineral density (BMD), usually of L1; BMD measurement with asynchronous or internal calibration; quantitative CT; bone texture assessment; and finite element analysis. Screening for osteoporosis and vertebral fractures on opportunistic CT is a promising approach, providing automated fracture risk scores by means of artificial intelligence, thus enabling earlier management.

Automated Opportunistic Trabecular Volumetric Bone Mineral Density Extraction Outperforms Manual Measurements for the Prediction of Vertebral Fractures in Routine CT

Opportunistic osteoporosis screening using multidetector CT-scans (MDCT) and convolutional neural network (CNN)-derived segmentations of the spine to generate volumetric bone mineral density (vBMD) bears the potential to improve incidental osteoporotic vertebral fracture (VF) prediction. However, the performance compared to the established manual opportunistic vBMD measures remains unclear. Hence, we investigated patients with a routine MDCT of the spine who had developed a new osteoporotic incidental VF and frequency matched to patients without incidental VFs as assessed on follow-up MDCT images after 1.5 years. Automated vBMD was generated using CNN-generated segmentation masks and asynchronous calibration. Additionally, manual vBMD was sampled by two radiologists. Automated vBMD measurements in patients with incidental VFs at 1.5-years follow-up (n = 53) were significantly lower compared to patients without incidental VFs (n = 104) (83.6 ± 29.4 mg/cm³ vs. 102.1 ± 27.7 mg/cm³, p < 0.001). This comparison was not significant for manually assessed vBMD (99.2 ± 37.6 mg/cm³ vs. 107.9 ± 33.9 mg/cm³, p = 0.30). When adjusting for age and sex, both automated and manual vBMD measurements were significantly associated with incidental VFs at 1.5-year follow-up, however, the associations were stronger for automated measurements (β = -0.32; 95% confidence interval (CI): -20.10, 4.35; p < 0.001) compared to manual measurements (β = -0.15; 95% CI: -11.16, 5.16; p < 0.03). In conclusion, automated opportunistic measurements are feasible and can be useful for bone mineral density assessment in clinical routine.

Development and validation of a machine learning model to predict imminent new vertebral fractures after vertebral augmentation

BACKGROUND

Accurately predicting the occurrence of imminent new vertebral fractures (NVFs) in patients with osteoporotic vertebral compression fractures (OVCFs) undergoing vertebral augmentation (VA) is challenging with yet no effective approach. This study aim to examine a machine learning model based on radiomics signature and clinical factors in predicting imminent new vertebral fractures after vertebral augmentation.

METHODS

A total of 235 eligible patients with OVCFs who underwent VA procedures were recruited from two independent institutions and categorized into three groups, including training set (n = 138), internal validation set (n = 59), and external validation set (n = 38). In the training set, radiomics features were computationally retrieved from L1 or adjacent vertebral body (T12 or L2) on T1-w MRI images, and a radiomics signature was constructed using the least absolute shrinkage and selection operator algorithm (LASSO). Predictive radiomics signature and clinical factors were fitted into two final prediction models using the random survival forest (RSF) algorithm or COX proportional hazard (CPH) analysis. Independent internal and external validation sets were used to validate the prediction models.

RESULTS

The two prediction models were integrated with radiomics signature and intravertebral cleft (IVC). The RSF model with C-indices of 0.763, 0.773, and 0.731 and time-dependent AUC (2 years) of 0.855, 0.907, and 0.839 (p < 0.001 for all) was found to be better predictive than the CPH model in training, internal and external validation sets. The RSF model provided better calibration, larger net benefits (determined by decision curve analysis), and lower prediction error (time-dependent brier score of 0.156, 0.151, and 0.146, respectively) than the CPH model.

CONCLUSIONS

The integrated RSF model showed the potential to predict imminent NVFs following vertebral augmentation, which will aid in postoperative follow-up and treatment.

Differentiation of acute and chronic vertebral compression fractures using conventional CT based on deep transfer learning features and hand-crafted radiomics features

BACKGROUND

We evaluated the diagnostic efficacy of deep learning radiomics (DLR) and hand-crafted radiomics (HCR) features in differentiating acute and chronic vertebral compression fractures (VCFs).

METHODS

A total of 365 patients with VCFs were retrospectively analysed based on their computed tomography (CT) scan data. All patients completed MRI examination within 2 weeks. There were 315 acute VCFs and 205 chronic VCFs. Deep transfer learning (DTL) features and HCR features were extracted from CT images of patients with VCFs using DLR and traditional radiomics, respectively, and feature fusion was performed to establish the least absolute shrinkage and selection operator. The MRI display of vertebral bone marrow oedema was used as the gold standard for acute VCF, and the model performance was evaluated using the receiver operating characteristic (ROC).To separately evaluate the effectiveness of DLR, traditional radiomics and feature fusion in the differential diagnosis of acute and chronic VCFs, we constructed a nomogram based on the clinical baseline data to visualize the classification evaluation. The predictive power of each model was compared using the Delong test, and the clinical value of the nomogram was evaluated using decision curve analysis (DCA).

RESULTS

Fifty DTL features were obtained from DLR, 41 HCR features were obtained from traditional radiomics, and 77 features fusion were obtained after feature screening and fusion of the two. The area under the curve (AUC) of the DLR model in the training cohort and test cohort were 0.992 (95% confidence interval (CI), 0.983-0.999) and 0.871 (95% CI, 0.805-0.938), respectively. While the AUCs of the conventional radiomics model in the training cohort and test cohort were 0.973 (95% CI, 0.955-0.990) and 0.854 (95% CI, 0.773-0.934), respectively. The AUCs of the features fusion model in the training cohort and test cohort were 0.997 (95% CI, 0.994-0.999) and 0.915 (95% CI, 0.855-0.974), respectively. The AUCs of nomogram constructed by the features fusion in combination with clinical baseline data were 0.998 (95% CI, 0.996-0.999) and 0.946 (95% CI, 0.906-0.987) in the training cohort and test cohort, respectively. The Delong test showed that the differences between the features fusion model and the nomogram in the training cohort and the test cohort were not statistically significant (P values were 0.794 and 0.668, respectively), and the differences in the other prediction models in the training cohort and the test cohort were statistically significant (P < 0.05). DCA showed that the nomogram had high clinical value.

CONCLUSION

The features fusion model can be used for the differential diagnosis of acute and chronic VCFs, and its differential diagnosis ability is improved when compared with that when either radiomics is used alone. At the same time, the nomogram has a high predictive value for acute and chronic VCFs and can be a potential decision-making tool to assist clinicians, especially when a patient is unable to undergo spinal MRI examination.

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.

Prediction of osteoporosis using radiomics analysis derived from single source dual energy CT

BACKGROUND

With the aging population of society, the incidence rate of osteoporosis is increasing year by year. Early diagnosis of osteoporosis plays a significant role in the progress of disease prevention. As newly developed technology, computed tomography (CT) radiomics could discover radiomic features difficult to recognize visually, providing convenient, comprehensive and accurate osteoporosis diagnosis. This study aimed to develop and validate a clinical-radiomics model based on the monochromatic imaging of single source dual-energy CT for osteoporosis prediction.

METHODS

One hundred sixty-four participants who underwent both single source dual-energy CT and quantitative computed tomography (QCT) lumbar-spine examination were enrolled in a study cohort including training datasets (n = 114 [30 osteoporosis and 84 non-osteoporosis]) and validation datasets (n = 50 [12 osteoporosis and 38 non-osteoporosis]). One hundred seven radiomics features were extracted from 70-keV monochromatic CT images. With QCT as the reference standard, a radiomics signature was built by using least absolute shrinkage and selection operator (LASSO) regression on the basis of reproducible features. A clinical-radiomics model was constructed by incorporating the radiomics signature and a significant clinical predictor (age) using multivariate logistic regression analysis. Model performance was assessed by its calibration, discrimination and clinical usefulness.

RESULTS

The radiomics signature comprised 14 selected features and showed good calibration and discrimination in both training and validation cohorts. The clinical-radiomics model, which incorporated the radiomics signature and a significant clinical predictor (age), also showed good discrimination, with an area under the receiver operating characteristic curve (AUC) of 0.938 (95% confidence interval, 0.903-0.952) in the training cohort and an AUC of 0.988 (95% confidence interval, 0.967-0.998) in the validation cohort, and good calibration. The clinical-radiomics model stratified participants into groups with osteoporosis and non-osteoporosis with an accuracy of 94.0% in the validation cohort. Decision curve analysis (DCA) demonstrated that the radiomics signature and the clinical-radiomics model were clinically useful.

CONCLUSIONS

The clinical-radiomics model incorporating the radiomics signature and a clinical parameter had a good ability to predict osteoporosis based on dual-energy CT monoenergetic imaging.

Vertebral trabecular bone texture analysis in opportunistic MRI and CT scan can distinguish patients with and without osteoporotic vertebral fracture: A preliminary study

PURPOSE

To investigate the potential of texture parameters from opportunistic MRI and CT for the detection of patients with vertebral fragility fracture, to design a decision tree and to compute a Random Forest analysis for the prediction of fracture risk.

METHODS

One hundred and eighty vertebrae of sixty patients with at least one (30) or without (30) a fragility fracture were retrospectively assessed. Patients had a DXA, an MRI and a CT scan from the three first lumbar vertebrae. Vertebrae texture analysis was performed in routine abdominal or lumbar CT and lumbar MRI using 1st and 2nd order texture parameters. Hounsfield Unit Bone density (HU BD) was also measured on CT-scan images.

RESULTS

Twelve texture parameters, Z-score and HU BD were significantly different between the two groups whereas T score and BMD were not. The inter observer reproducibility was good to excellent. Decision tree showed that age and HU BD were the most relevant factors to predict the fracture risk with a 93 % sensitivity and 56 % specificity. AUC was 0.91 in MRI and 0.92 in CT-scan using the Random Forest analysis. The corresponding sensitivity and specificity were 72 % and 93 % in MRI and 83 and 89 % in CT.

CONCLUSIONS

This study is the first to compare texture indices computed from opportunistic CT and MR images. Age and HU-BD together with selected texture parameters could be used to assess risk fracture. Machine learning algorithm can detect fracture risk in opportunistic CT and MR imaging and might be of high interest for the diagnosis of osteoporosis.

Radiomics and Deep Learning for Disease Detection in Musculoskeletal Radiology: An Overview of Novel MRI- and CT-Based Approaches

ABSTRACT

Radiomics and machine learning-based methods offer exciting opportunities for improving diagnostic performance and efficiency in musculoskeletal radiology for various tasks, including acute injuries, chronic conditions, spinal abnormalities, and neoplasms. While early radiomics-based methods were often limited to a smaller number of higher-order image feature extractions, applying machine learning-based analytic models, multifactorial correlations, and classifiers now permits big data processing and testing thousands of features to identify relevant markers. A growing number of novel deep learning-based methods describe magnetic resonance imaging- and computed tomography-based algorithms for diagnosing anterior cruciate ligament tears, meniscus tears, articular cartilage defects, rotator cuff tears, fractures, metastatic skeletal disease, and soft tissue tumors. Initial radiomics and deep learning techniques have focused on binary detection tasks, such as determining the presence or absence of a single abnormality and differentiation of benign versus malignant. Newer-generation algorithms aim to include practically relevant multiclass characterization of detected abnormalities, such as typing and malignancy grading of neoplasms. So-called delta-radiomics assess tumor features before and after treatment, with temporal changes of radiomics features serving as surrogate markers for tumor responses to treatment. New approaches also predict treatment success rates, surgical resection completeness, and recurrence risk. Practice-relevant goals for the next generation of algorithms include diagnostic whole-organ and advanced classification capabilities. Important research objectives to fill current knowledge gaps include well-designed research studies to understand how diagnostic performances and suggested efficiency gains of isolated research settings translate into routine daily clinical practice. This article summarizes current radiomics- and machine learning-based magnetic resonance imaging and computed tomography approaches for musculoskeletal disease detection and offers a perspective on future goals and objectives.

A Predictive Clinical-Radiomics Nomogram for Differentiating Tuberculous Spondylitis from Pyogenic Spondylitis Using CT and Clinical Risk Factors

OBJECTIVE

The study aimed to develop and validate a nomogram model with clinical risk factors and radiomic features for differentiating tuberculous spondylitis (TS) from pyogenic spondylitis (PS).

METHODS

A total of 254 patients with TS (n = 141) or PS (n = 113) were randomly divided into training (n = 180) and validation (n = 74) groups. In addition, 43 patients (TS = 22 and PS = 21) were collected to construct a test cohort. t-test analysis, de-redundancy analysis, and minimum absolute shrinkage and selection operator (lasso) algorithm were utilized on the training set to obtain the optimal radiomics features from computed tomography (CT) for constructing the radiomics model and determine the radiomics score (Rad-score). Eight clinical risk predictors were identified to develop the clinical model. Combined with clinical risk predictors and Rad-scores, a nomogram model was constructed using multivariate logistic regression analysis.

RESULTS

A total of 1781 features were extracted, and 12 optimal radiomic features were utilized to construct the radiomic model and determine the Rad-score. The combined clinical radiomics model revealed good discrimination performance in both the training cohort and the validation cohort (AUC = 0.891 and 0.830) and was superior to the clinical (AUC = 0.807 and 0.785) and radiomics (AUC = 0.796 and 0.811) models. The calibration curve and DCA also depicted that the nomogram had better clinical efficacy. The discriminative performance of the model is well validated in the test cohort (AUC=0.877).

CONCLUSION

The clinical radiomic nomogram could serve as a promising predictive tool for differentiating TS from PS, which could be helpful for clinical decision-making.

A computed tomography-based radiomics nomogram for predicting osteoporotic vertebral fractures: A longitudinal study

CONTEXT

Fractures are serious consequence of osteoporosis in old adults. However, few longitudinal studies showed the role of computed tomography (CT)-based radiomics in predicting osteoporotic fractures.

OBJECTIVE

We evaluated the performance of CT radiomics-based model for osteoporotic vertebral fractures (OVF) in a longitudinal study.

METHODS

7906 subjects without OVF who were aged over 50 years, and underwent CT scans between 2016 and 2019 were enrolled and followed up until 2021. Seventy-two cases of new OVF were identified. One hundred and forty-four people without OVF during follow-up were selected as control. Radiomics features were extracted from baseline CT images. CT values of trabecular bone, and area and density of erector spinae were determined. Cox regression analysis was used to identify the independent associated factors. The predictive performance of the nomogram was assessed using the receiver operating characteristic (ROC) curve, calibration curve and decision curve.

RESULTS

CT value of vertebra (adjusted hazard ratio (aHR) = 2.04, 95% confidence interval (CI): 1.07, 3.89), radiomics score (aHR = 6.56, 95%CI:3.47, 12.38) and area of erector spinae (aHR = 1.68, 95%CI: 1.02, 2.78) were independently associated with OVF. Radscore was associated with severe OVF (aHR = 6.00, 95% CI:2.78-12.93). The nomogram showed good discrimination with a C-index of 0.82 (95%CI: 0.77, 0.87). The area under the curve of nomogram and radscore were both higher than osteoporosis + muscle area for 3-year and 4-year risk of fractures (p < 0.05). Decision curve also demonstrated that the radiomics nomogram was useful.

CONCLUSIONS

Bone radiomics is associated with OVF and the nomogram based on radiomics signature and muscle provides a tool for the prediction of OVF.

Medical optimization of osteoporosis for adult spinal deformity surgery: a state-of-the-art evidence-based review of current pharmacotherapy

PURPOSE

Osteoporosis is a common, but challenging phenomenon to overcome in adult spinal deformity (ASD) surgery. Several pharmacological agents are at the surgeon's disposal to optimize the osteoporotic patient prior to undergoing extensive reconstruction. Familiarity with these medications will allow the surgeon to make informed decisions on selecting the most appropriate adjuncts for each individual patient.

METHODS

A comprehensive literature review was conducted in PubMed from September 2021 to April 2022. Studies were selected that contained combinations of various terms including osteoporosis, specific medications, spine surgery, fusion, cage subsidence, screw loosening, pull-out, junctional kyphosis/failure.

RESULTS

Bisphosphonates, denosumab, selective estrogen receptor modulators, teriparatide, abaloparatide and romosozumab are all pharmacological agents currently available for adjunctive use. While these medications have been shown to have beneficial effects on improving bone mineral density in the osteoporotic patient, varying evidence is available on their specific effects in the context of extensive spine surgery. There is still a lack of human studies with use of the newer agents.

CONCLUSION

Bisphosphonates are first-line agents due to their low cost and robust evidence behind their utility. However, in the absence of contraindications, optimizing bone quality with anabolic medications should be strongly considered in preparation for spinal deformity surgeries due to their beneficial and favorable effects on fusion and hardware compared to the anti-resorptive medications.

Associations between paraspinal muscles fatty infiltration and lumbar vertebral bone mineral density - An investigation by fast kVp switching dual-energy CT and QCT

Purpose

To investigate the relationship between paraspinal muscles fat content and lumbar bone mineral density (BMD).

Methods

A total of 119 participants were enrolled in our study (60 males, age: 50.88 ± 17.79 years, BMI: 22.80 ± 3.80 kg·m^-2; 59 females, age: 49.41 ± 17.69 years, BMI: 22.22 ± 3.12 kg·m^-2). Fat content of paraspinal muscles (erector spinae (ES), multifidus (MS), and psoas (PS)) were measured at (ES L1/2-L4/5; MS L2/3-L5/S1; PS L2/3-L5/S1) levels using dual-energy computed tomography (DECT). Quantitative computed tomography (QCT) was used to assess BMD of L1 and L2. Linear regression analysis was used to assess the relationship between BMD of the lumbar spine and paraspinal muscles fat content with age, sex, and BMI. The variance inflation factor (VIF) was used to detect the degree of multicollinearity among the variables. P < .05 was considered to indicate a statistically significant difference.

Results

The paraspinal muscles fat content had a fairly significant inverse association with lumbar BMD after controlling for age, sex, and BMI (adjusted R ² = 0.584-0.630, all P < .05).

Conclusion

Paraspinal muscles fat content was negatively associated with BMD.Paraspinal muscles fatty infiltration may be considered as a potential marker to identify BMD loss.

Bone Fracture Detection Using Deep Supervised Learning from Radiological Images: A Paradigm Shift

Bone diseases are common and can result in various musculoskeletal conditions (MC). An estimated 1.71 billion patients suffer from musculoskeletal problems worldwide. Apart from musculoskeletal fractures, femoral neck injuries, knee osteoarthritis, and fractures are very common bone diseases, and the rate is expected to double in the next 30 years. Therefore, proper and timely diagnosis and treatment of a fractured patient are crucial. Contrastingly, missed fractures are a common prognosis failure in accidents and emergencies. This causes complications and delays in patients’ treatment and care. These days, artificial intelligence (AI) and, more specifically, deep learning (DL) are receiving significant attention to assist radiologists in bone fracture detection. DL can be widely used in medical image analysis. Some studies in traumatology and orthopaedics have shown the use and potential of DL in diagnosing fractures and diseases from radiographs. In this systematic review, we provide an overview of the use of DL in bone imaging to help radiologists to detect various abnormalities, particularly fractures. We have also discussed the challenges and problems faced in the DL-based method, and the future of DL in bone imaging.

A Classification Method for Thoracolumbar Vertebral Fractures due to Basketball Sports Injury Based on Deep Learning

Objective

There are more and more basketball competitions, to propose a classification method of thoracolumbar fractures to assist in the diagnosis of basketball injuries, to analyze the feasibility of its clinical application, and to improve the recovery rate.

Methods

From February 2015 to May 2022, 1130 CT images of thoracolumbar fractures admitted to our hospital and affiliated hospital units due to basketball injuries were collected, and the image labeling system uniformly labeled them. All CT images were classified according to the AO spine classification of thoracolumbar injuries. In the ABC-type classification, 935 CT images were used for training and validation to optimize the deep learning system, including 815 training sets and 120 validation sets; the remaining 198 CT images were used as test sets for comparing the deep learning system and clinician's diagnosis. In the classification of subtype A, a total of 523 CT scans can be performed for training and validation to optimize the deep learning system, including 500 training sets and 23 validation sets; the remaining 94 CT images are used as test sets for comparing depth learning systems and clinicians' diagnostic results.

Results

The deep learning system had a correct rate of ABC classification of fractures in 86.4%, with a kappa coefficient of 0.850 (P < 0.001); the correct rate of subtype A was 85.3%, with a kappa coefficient of 0.815 (P < 0.001).

Conclusion

The classification accuracy of thoracolumbar fractures based on deep learning is high. The method can assist in diagnosing CT images of thoracolumbar fractures and improve the current manual and complex diagnosis process.

Prediction of the Acuity of Vertebral Compression Fractures on CT Using Radiologic and Radiomic Features

RATIONALE AND OBJECTIVES

To develop and validate prediction models to differentiate acute and chronic vertebral compression fractures based on radiologic and radiomic features on CT.

MATERIALS AND METHODS

This study included acute and chronic compression fractures in patients who underwent both spine CT and MRI examinations. For each fractured vertebra, three CT findings ([1] cortical disruption, [2] hypoattenuating cleft or sclerotic line, and [3] relative bone marrow attenuation) were assessed by two radiologists. A radiomic score was built from 280 radiomic features extracted from non-contrast-enhanced CT images. Weighted multivariable logistic regression analysis was performed to build a radiologic model based on CT findings and an integrated model combining the radiomic score and CT findings. Model performance was evaluated and compared. Models were externally validated using an independent test cohort.

RESULTS

A total to 238 fractures (159 acute and 79 chronic) in 122 patients and 58 fractures (39 acute and 19 chronic) in 32 patients were included in the training and test cohorts, respectively. The AUC of the radiomic score was 0.95 in the training and 0.93 in the test cohorts. The AUC of the radiologic model was 0.89 in the training and 0.83 in the test cohorts. The discriminatory performance of the integrated model was significantly higher than the radiologic model in both the training (AUC, 0.97; p<0.01) and the test (AUC, 0.95; p=0.01) cohorts.

CONCLUSION

Combining radiomics with radiologic findings significantly improved the performance of CT in determining the acuity of vertebral compression fractures.

Artificial Intelligence in Spinal Imaging: Current Status and Future Directions

Spinal maladies are among the most common causes of pain and disability worldwide. Imaging represents an important diagnostic procedure in spinal care. Imaging investigations can provide information and insights that are not visible through ordinary visual inspection. Multiscale in vivo interrogation has the potential to improve the assessment and monitoring of pathologies thanks to the convergence of imaging, artificial intelligence (AI), and radiomic techniques. AI is revolutionizing computer vision, autonomous driving, natural language processing, and speech recognition. These revolutionary technologies are already impacting radiology, diagnostics, and other fields, where automated solutions can increase precision and reproducibility. In the first section of this narrative review, we provide a brief explanation of the many approaches currently being developed, with a particular emphasis on those employed in spinal imaging studies. The previously documented uses of AI for challenges involving spinal imaging, including imaging appropriateness and protocoling, image acquisition and reconstruction, image presentation, image interpretation, and quantitative image analysis, are then detailed. Finally, the future applications of AI to imaging of the spine are discussed. AI has the potential to significantly affect every step in spinal imaging. AI can make images of the spine more useful to patients and doctors by improving image quality, imaging efficiency, and diagnostic accuracy.

Osteoporosis in 2022: Care gaps to screening and personalised medicine

Osteoporosis care has evolved markedly over the last 50 years, such that there are now an established clinical definition, validated methods of fracture risk assessment, and a range of effective pharmacological agents. However, it is apparent that both in the context of primary and secondary fracture prevention, there is a considerable gap between the population at high fracture risk and those actually receiving appropriate antiosteoporosis treatment. In this narrative review article, we document recent work describing the burden of disease, approaches to management, and service provision across Europe, emerging data on gaps in care, and existing/new ways in which these gaps may be addressed at the level of healthcare systems and policy. We conclude that although the field has come a long way in recent decades, there is still a long way to go, and a concerted, integrated effort is now required from all of us involved in this field to address these urgent issues to ensure the best possible outcomes for our patients.

Whole-volume ADC histogram of the brain as an image biomarker in evaluating disease severity of neonatal hypoxic-ischemic encephalopathy

Purpose

To examine the diagnostic significance of the apparent diffusion coefficient (ADC) histogram in quantifying neonatal hypoxic ischemic encephalopathy (HIE).

Methods

An analysis was conducted on the MRI data of 90 HIE patients, 49 in the moderate-to-severe group, and the other in the mild group. The 3D Slicer software was adopted to delineate the whole brain region as the region of interest, and 22 ADC histogram parameters were obtained. The interobserver consistency of the two radiologists was assessed by the interclass correlation coefficient (ICC). The difference in parameters (ICC > 0.80) between the two groups was compared by performing the independent sample t-test or the Mann–Whitney U test. In addition, an investigation was conducted on the correlation between parameters and the neonatal behavioral neurological assessment (NBNA) score. The ROC curve was adopted to assess the efficacy of the respective significant parameters. Furthermore, the binary logistic regression was employed to screen out the independent risk factors for determining the severity of HIE.

Results

The ADCmean, ADCmin, ADCmax,10th−70th, 90th percentile of ADC values of the moderate-to-severe group were smaller than those of the mild group, while the group's variance, skewness, kurtosis, heterogeneity, and mode-value were higher than those of the mild group (P < 0.05). All the mentioned parameters, the ADCmean, ADCmin, and 10th−70th and 90th percentile of ADC displayed positive correlations with the NBNA score, mode-value and ADCmax displayed no correlations with the NBNA score, the rest showed negative correlations with the NBNA score (P < 0.05). The area under the curve (AUC) of variance was the largest (AUC = 0.977; cut-off 972.5, sensitivity 95.1%; specificity 87.8%). According to the logistic regression analysis, skewness, kurtosis, variance, and heterogeneity were independent risk factors for determining the severity of HIE (OR > 1, P < 0.05).

Conclusions

The ADC histogram contributes to the HIE diagnosis and is capable of indicating the diffusion information of the brain objectively and quantitatively. It refers to a vital method for assessing the severity of HIE.

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.

Development of a Spine X-Ray-Based Fracture Prediction Model Using a Deep Learning Algorithm

BACKGRUOUND

Since image-based fracture prediction models using deep learning are lacking, we aimed to develop an X-ray-based fracture prediction model using deep learning with longitudinal data.

METHODS

This study included 1,595 participants aged 50 to 75 years with at least two lumbosacral radiographs without baseline fractures from 2010 to 2015 at Seoul National University Hospital. Positive and negative cases were defined according to whether vertebral fractures developed during follow-up. The cases were divided into training (n=1,416) and test (n=179) sets. A convolutional neural network (CNN)-based prediction algorithm, DeepSurv, was trained with images and baseline clinical information (age, sex, body mass index, glucocorticoid use, and secondary osteoporosis). The concordance index (C-index) was used to compare performance between DeepSurv and the Fracture Risk Assessment Tool (FRAX) and Cox proportional hazard (CoxPH) models.

RESULTS

Of the total participants, 1,188 (74.4%) were women, and the mean age was 60.5 years. During a mean follow-up period of 40.7 months, vertebral fractures occurred in 7.5% (120/1,595) of participants. In the test set, when DeepSurv learned with images and clinical features, it showed higher performance than FRAX and CoxPH in terms of C-index values (DeepSurv, 0.612; 95% confidence interval [CI], 0.571 to 0.653; FRAX, 0.547; CoxPH, 0.594; 95% CI, 0.552 to 0.555). Notably, the DeepSurv method without clinical features had a higher C-index (0.614; 95% CI, 0.572 to 0.656) than that of FRAX in women.

CONCLUSION

DeepSurv, a CNN-based prediction algorithm using baseline image and clinical information, outperformed the FRAX and CoxPH models in predicting osteoporotic fracture from spine radiographs in a longitudinal cohort.

Novel Radiomics-Clinical Model for the Noninvasive Prediction of New Fractures After Vertebral Augmentation

PURPOSE

To investigate the noninvasive prediction model for new fractures after percutaneous vertebral augmentation (PVA) based on radiomics signature and clinical parameters.

METHODS

Data from patients who were diagnosed with osteoporotic vertebral compression fracture (OVCF) and treated with PVA in our hospital between May 2014 and April 2019 were retrospectively analyzed. Radiomics features were extracted from T1-weighted magnetic resonance imaging (MRI) of the T11-L5 segments taken before PVA. Different radiomics models was developed by using linear discriminant analysis (LDA), multilayer perceptron (MLP), and stochastic gradient descent (SGD) classifiers. A nomogram was constructed by integrating clinical parameters and Radscore that calculated by the best radiomics model. The model performance was quantified in terms of discrimination, calibration and clinical usefulness.

RESULT

Four clinical parameters and 16 selected radiomics features were used for model development. The clinical model showed poor discrimination capability with area under the curves (AUCs) yielding of 0.522 in the training dataset and 0.517 in the validation dataset. The LDA, MLP and SGD classifier-based radiomics model had achieved AUCs of 0.793, 0.810, and 0.797 in the training dataset, and 0.719, 0.704, and 0.725 in the validation dataset, respectively. The nomogram showed the best performance with AUCs achieving 0.810 and 0.754 in the training and validation datasets, respectively. The decision curve analysis demonstrated the net benefit of the nomogram was higher than that of other models.

CONCLUSION

Our findings indicate that combining clinical features with radiomics features from pre-augmentation T1-weighted MRI can be used to develop a nomogram that can predict new fractures in patients after PVA.

Imaging of the Osteoporotic Spine - Quantitative Approaches in Diagnostics and for the Prediction of the Individual Fracture Risk

Osteoporosis is a highly prevalent systemic skeletal disease that is characterized by low bone mass and microarchitectural bone deterioration. It predisposes to fragility fractures that can occur at various sites of the skeleton, but vertebral fractures (VFs) have been shown to be particularly common. Prevention strategies and timely intervention depend on reliable diagnosis and prediction of the individual fracture risk, and dual-energy X-ray absorptiometry (DXA) has been the reference standard for decades. Yet, DXA has its inherent limitations, and other techniques have shown potential as viable add-on or even stand-alone options. Specifically, three-dimensional (3 D) imaging modalities, such as computed tomography (CT) and magnetic resonance imaging (MRI), are playing an increasing role. For CT, recent advances in medical image analysis now allow automatic vertebral segmentation and value extraction from single vertebral bodies using a deep-learning-based architecture that can be implemented in clinical practice. Regarding MRI, a variety of methods have been developed over recent years, including magnetic resonance spectroscopy (MRS) and chemical shift encoding-based water-fat MRI (CSE-MRI) that enable the extraction of a vertebral body's proton density fat fraction (PDFF) as a promising surrogate biomarker of bone health. Yet, imaging data from CT or MRI may be more efficiently used when combined with advanced analysis techniques such as texture analysis (TA; to provide spatially resolved assessments of vertebral body composition) or finite element analysis (FEA; to provide estimates of bone strength) to further improve fracture prediction. However, distinct and experimentally validated diagnostic criteria for osteoporosis based on CT- and MRI-derived measures have not yet been achieved, limiting broad transfer to clinical practice for these novel approaches. KEY POINTS::   · DXA is the reference standard for diagnosis and fracture prediction in osteoporosis, but it has important limitations.. · CT- and MRI-based methods are increasingly used as (opportunistic) approaches.. · For CT, particularly deep-learning-based automatic vertebral segmentation and value extraction seem promising.. · For MRI, multiple techniques including spectroscopy and chemical shift imaging are available to extract fat fractions.. · Texture and finite element analyses can provide additional measures for vertebral body composition and bone strength.. CITATION FORMAT: · Sollmann N, Kirschke JS, Kronthaler S et al. Imaging of the Osteoporotic Spine - Quantitative Approaches in Diagnostics and for the Prediction of the Individual Fracture Risk. Fortschr Röntgenstr 2022; DOI: 10.1055/a-1770-4626.

Automated segmentation of the fractured vertebrae on CT and its applicability in a radiomics model to predict fracture malignancy

Although CT radiomics has shown promising results in the evaluation of vertebral fractures, the need for manual segmentation of fractured vertebrae limited the routine clinical implementation of radiomics. Therefore, automated segmentation of fractured vertebrae is needed for successful clinical use of radiomics. In this study, we aimed to develop and validate an automated algorithm for segmentation of fractured vertebral bodies on CT, and to evaluate the applicability of the algorithm in a radiomics prediction model to differentiate benign and malignant fractures. A convolutional neural network was trained to perform automated segmentation of fractured vertebral bodies using 341 vertebrae with benign or malignant fractures from 158 patients, and was validated on independent test sets (internal test, 86 vertebrae [59 patients]; external test, 102 vertebrae [59 patients]). Then, a radiomics model predicting fracture malignancy on CT was constructed, and the prediction performance was compared between automated and human expert segmentations. The algorithm achieved good agreement with human expert segmentation at testing (Dice similarity coefficient, 0.93-0.94; cross-sectional area error, 2.66-2.97%; average surface distance, 0.40-0.54 mm). The radiomics model demonstrated good performance in the training set (AUC, 0.93). In the test sets, automated and human expert segmentations showed comparable prediction performances (AUC, internal test, 0.80 vs 0.87, p = 0.044; external test, 0.83 vs 0.80, p = 0.37). In summary, we developed and validated an automated segmentation algorithm that showed comparable performance to human expert segmentation in a CT radiomics model to predict fracture malignancy, which may enable more practical clinical utilization of radiomics.

Detecting Multiple Myeloma Infiltration of the Bone Marrow on CT Scans in Patients with Osteopenia: Feasibility of Radiomics Analysis

It is difficult to detect multiple myeloma (MM) infiltration of the bone marrow on computed tomography (CT) scans of patients with osteopenia. Our aim is to determine the feasibility of using radiomics analysis to detect MM infiltration of the bone marrow on CT scans of patients with osteopenia. The contrast-enhanced thoracic CT scans of 104 patients with MM and 104 age- and sex-matched controls were retrospectively evaluated. All individuals had decreased bone density on radiography. The study group was divided into development (n = 160) and temporal validation sets (n = 48). The radiomics model was developed using 805 texture features extracted from the bone marrow for a development set, using a Random Forest algorithm. The developed models were applied to evaluate a temporal validation set. For comparison, three radiologists evaluated the CTs for the possibility of MM infiltration in the bone marrow. The diagnostic performances were assessed and compared using an area under the receiver operating characteristic curve (AUC) analysis. The AUC of the radiomics model was not significantly different from those of the radiologists (p = 0.056–0.821). The radiomics analysis results showed potential for detecting MM infiltration in the bone marrow on CT scans of patients with osteopenia.

Bone radiomics reproducibility: a three-centered study on the impacts of image contrast, edge enhancement, and latitude variations

This study aims to measure the reproducibility of radiomics features in ankle bone radiography over changes in post-processing parameters including contrast, edge enhancement and latitude. Lateral ankle bone radiographies for sixty patients were obtained from three digital radiology centers. All images were acquired by same image acquisition settings. A two-dimensional region of interest was drawn in any image and 93 features from 6 feature sets including first and second order were extracted. The coefficient of variation (COV) and intraclass correlation coefficient (ICC) were calculated to assess feature reproducibility for each center and among all centers in three scenarios: Adams (Nat Rev Endocrinol 9(1):28, 2013) ten different contrast Brown et al. (J Med Imaging 5(1):011017, 2018) ten different edge enhancement and Hirvasniemi et al. (Osteoarthr Cartilage 27(6):906-914, 2019)  ten different image latitude parameters. Based on ICC analysis, it is observed that 46-100-44% of Histogram, 54-72-42% of GLCM, 43-76-36% of GLDM, 60-90-17% of GLRLM, 33-19-21% of GLSZM and 13-20-0% of NGTDM radiomics features had 90% < ICC < 100% over changes in contrast-edge enhancement-latitude changes respectively. Based on COV, GLRLM was only feature set that 100% of their features had COV ≤ 5% over changes in contrast and edge enhancement. The results presented here, indicating that radiomics features extracted are vulnerable over changes in contrast, edge enhancement and latitude. The most reproducible features that introduced in this study could be used for further clinical decision making.

Machine Learning Applications of Surgical Imaging for the Diagnosis and Treatment of Spine Disorders: Current State of the Art

Recent developments in machine learning (ML) methods demonstrate unparalleled potential for application in the spine. The ability for ML to provide diagnostic faculty, produce novel insights from existing capabilities, and augment or accelerate elements of surgical planning and decision making at levels equivalent or superior to humans will tremendously benefit spine surgeons and patients alike. In this review, we aim to provide a clinically relevant outline of ML-based technology in the contexts of spinal deformity, degeneration, and trauma, as well as an overview of commercial-level and precommercial-level surgical assist systems and decisional support tools. Furthermore, we briefly discuss potential applications of generative networks before highlighting some of the limitations of ML applications. We conclude that ML in spine imaging represents a significant addition to the neurosurgeon's armamentarium-it has the capacity to directly address and manifest clinical needs and improve diagnostic and procedural quality and safety-but is yet subject to challenges that must be addressed before widespread implementation.

Risk Factors for Failure in Conservatively Treated Osteoporotic Vertebral Fractures: A Systematic Review

STUDY DESIGN

Systematic review.

OBJECTIVES

Osteoporosis is one of the most common diseases of the elderly, whereby vertebral body fractures are in many cases the first manifestation. Even today, the consequences for patients are underestimated. Therefore, early identification of therapy failures is essential. In this context, the aim of the present systematic review was to evaluate the current literature with respect to clinical and radiographic findings that might predict treatment failure.

METHODS

We conducted a comprehensive, systematic review of the literature according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) checklist and algorithm.

RESULTS

After the literature search, 724 potentially eligible investigations were identified. In total, 24 studies with 3044 participants and a mean follow-up of 11 months (range 6-27.5 months) were included. Patient-specific risk factors were age >73 years, bone mineral density with a t-score <-2.95, BMI >23 and a modified frailty index >2.5. The following radiological and fracture-specific risk factors could be identified: involvement of the posterior wall, initial height loss, midportion type fracture, development of an intravertebral cleft, fracture at the thoracolumbar junction, fracture involvement of both endplates, different morphological types of fractures, and specific MRI findings. Further, a correlation between sagittal spinal imbalance and treatment failure could be demonstrated.

CONCLUSION

In conclusion, this systematic review identified various factors that predict treatment failure in conservatively treated osteoporotic fractures. In these cases, additional treatment options and surgical treatment strategies should be considered in addition to follow-up examinations.

A hierarchical opportunistic screening model for osteoporosis using machine learning applied to clinical data and CT images

Background

Osteoporosis is a common metabolic skeletal disease and usually lacks obvious symptoms. Many individuals are not diagnosed until osteoporotic fractures occur. Bone mineral density (BMD) measured by dual-energy X-ray absorptiometry (DXA) is the gold standard for osteoporosis detection. However, only a limited percentage of people with osteoporosis risks undergo the DXA test. As a result, it is vital to develop methods to identify individuals at-risk based on methods other than DXA.

Results

We proposed a hierarchical model with three layers to detect osteoporosis using clinical data (including demographic characteristics and routine laboratory tests data) and CT images covering lumbar vertebral bodies rather than DXA data via machine learning. 2210 individuals over age 40 were collected retrospectively, among which 246 individuals’ clinical data and CT images are both available. Irrelevant and redundant features were removed via statistical analysis. Consequently, 28 features, including 16 clinical data and 12 texture features demonstrated statistically significant differences (p < 0.05) between osteoporosis and normal groups. Six machine learning algorithms including logistic regression (LR), support vector machine with radial-basis function kernel, artificial neural network, random forests, eXtreme Gradient Boosting and Stacking that combined the above five classifiers were employed as classifiers to assess the performances of the model. Furthermore, to diminish the influence of data partitioning, the dataset was randomly split into training and test set with stratified sampling repeated five times. The results demonstrated that the hierarchical model based on LR showed better performances with an area under the receiver operating characteristic curve of 0.818, 0.838, and 0.962 for three layers, respectively in distinguishing individuals with osteoporosis and normal BMD.

Conclusions

The proposed model showed great potential in opportunistic screening for osteoporosis without additional expense. It is hoped that this model could serve to detect osteoporosis as early as possible and thereby prevent serious complications of osteoporosis, such as osteoporosis fractures.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04596-z.

AI MSK clinical applications: spine imaging

Recent investigations have focused on the clinical application of artificial intelligence (AI) for tasks specifically addressing the musculoskeletal imaging routine. Several AI applications have been dedicated to optimizing the radiology value chain in spine imaging, independent from modality or specific application. This review aims to summarize the status quo and future perspective regarding utilization of AI for spine imaging. First, the basics of AI concepts are clarified. Second, the different tasks and use cases for AI applications in spine imaging are discussed and illustrated by examples. Finally, the authors of this review present their personal perception of AI in daily imaging and discuss future chances and challenges that come along with AI-based solutions.

Use of machine learning to select texture features in investigating the effects of axial loading on T2-maps from magnetic resonance imaging of the lumbar discs

BACKGROUND

Recent advances in texture analysis and machine learning offer new opportunities to improve the application of imaging to intervertebral disc biomechanics. This study employed texture analysis and machine learning on MRIs to investigate the lumbar disc's response to loading.

METHODS

Thirty-five volunteers (30 (SD 11) yrs.) with and without chronic back pain spent 20 min lying in a relaxed unloaded supine position, followed by 20 min loaded in compression, and then 20 min with traction applied. T₂-weighted MR images were acquired during the last 5 min of each loading condition. Custom image analysis software was used to segment discs from adjacent tissues semi-automatically and segment each disc into the nucleus, anterior and posterior annulus automatically. A grey-level, co-occurrence matrix with one to four pixels offset in four directions (0°, 45°, 90° and 135°) was then constructed (320 feature/tissue). The Random Forest Algorithm was used to select the most promising classifiers. Linear mixed-effect models and Cohen's d compared loading conditions.

FINDINGS

All statistically significant differences (p < 0.001) were observed in the nucleus and posterior annulus in the 135° offset direction at the L4-5 level between lumbar compression and traction. Correlation (P_2-Offset, P_4-Offset) and information measure of correlation 1 (P_3-Offset, P_4-Offset) detected significant changes in the nucleus. Statistically significant changes were also observed for homogeneity (P_2-Offset, P_3-Offset), contrast (P_2-Offset), and difference variance (P_4-Offset) of the posterior annulus.

INTERPRETATION

MRI textural features may have the potential of identifying the disc's response to loading, particularly in the nucleus and posterior annulus, which appear most sensitive to loading.

LEVEL OF EVIDENCE

Diagnostic: individual cross-sectional studies with consistently applied reference standard and blinding.

Applications of Machine Learning in Bone and Mineral Research

In this unprecedented era of the overwhelming volume of medical data, machine learning can be a promising tool that may shed light on an individualized approach and a better understanding of the disease in the field of osteoporosis research, similar to that in other research fields. This review aimed to provide an overview of the latest studies using machine learning to address issues, mainly focusing on osteoporosis and fractures. Machine learning models for diagnosing and classifying osteoporosis and detecting fractures from images have shown promising performance. Fracture risk prediction is another promising field of research, and studies are being conducted using various data sources. However, these approaches may be biased due to the nature of the techniques or the quality of the data. Therefore, more studies based on the proposed guidelines are needed to improve the technical feasibility and generalizability of artificial intelligence algorithms.

Prediction of incident vertebral fractures in routine MDCT: Comparison of global texture features, 3D finite element parameters and volumetric BMD

PURPOSE

In this case-control study, we evaluated different quantitative parameters derived from routine multi-detector computed tomography (MDCT) scans with respect to their ability to predict incident osteoporotic vertebral fractures of the thoracolumbar spine.

METHODS

16 patients who received baseline and follow-up contrast-enhanced MDCT and were diagnosed with an incident osteoporotic vertebral fracture at follow-up, and 16 age-, sex-, and follow-up-time-matched controls were included in the study. Vertebrae were labelled and segmented using a fully automated pipeline. Volumetric bone mineral density (vBMD), finite element analysis (FEA)-based failure load (FL) and failure displacement (FD), as well as 24 texture features were extracted from L1 - L3 and averaged. Odds ratios (OR) with 95% confidence intervals (CI), expressed per standard deviation decrease, receiver operating characteristic (ROC) area under the curve (AUC), as well as logistic regression models, including all analyzed parameters as independent variables, were used to assess the prediction of incident vertebral fractures.

RESULTS

The texture feature Correlation (AUC = 0.754, p = 0.014; OR = 2.76, CI = 1.16-6.58) and vBMD (AUC = 0.750, p = 0.016; OR = 2.67, CI = 1.12-6.37) classified incident vertebral fractures best, while the best FEA-based parameter FL showed an AUC = 0.719 (p = 0.035). Correlation was the only significant predictor of incident fractures in the logistic regression analysis of all parameters (p = 0.022).

CONCLUSION

MDCT-derived FEA parameters and texture features, averaged from L1 - L3, showed only a moderate, but no statistically significant improvement of incident vertebral fracture prediction beyond BMD, supporting the hypothesis that vertebral-specific parameters may be superior for fracture risk assessment.

Texture analysis of muscle MRI: machine learning-based classifications in idiopathic inflammatory myopathies

To develop a machine learning (ML) model that predicts disease groups or autoantibodies in patients with idiopathic inflammatory myopathies (IIMs) using muscle MRI radiomics features. Twenty-two patients with dermatomyositis (DM), 14 with amyopathic dermatomyositis (ADM), 19 with polymyositis (PM) and 19 with non-IIM were enrolled. Using 2D manual segmentation, 93 original features as well as 93 local binary pattern (LBP) features were extracted from MRI (short-tau inversion recovery [STIR] imaging) of proximal limb muscles. To construct and compare ML models that predict disease groups using each set of features, dimensional reductions were performed using a reproducibility analysis by inter-reader and intra-reader correlation coefficients, collinearity analysis, and the sequential feature selection (SFS) algorithm. Models were created using the linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machine (SVM), k-nearest neighbors (k-NN), random forest (RF) and multi-layer perceptron (MLP) classifiers, and validated using tenfold cross-validation repeated 100 times. We also investigated whether it was possible to construct models predicting autoantibody status. Our ML-based MRI radiomics models showed the potential to distinguish between PM, DM, and ADM. Models using LBP features provided better results, with macro-average AUC values of 0.767 and 0.714, accuracy of 61.2 and 61.4%, and macro-average recall of 61.9 and 59.8%, in the LDA and k-NN classifiers, respectively. In contrast, the accuracies of radiomics models distinguishing between non-IIM and IIM disease groups were low. A subgroup analysis showed that classification models for anti-Jo-1 and anti-ARS antibodies provided AUC values of 0.646–0.853 and 0.692–0.792, with accuracy of 71.5–81.0 and 65.8–78.3%, respectively. ML-based TA of muscle MRI may be used to predict disease groups or the autoantibody status in patients with IIM and is useful in non-invasive assessments of disease mechanisms.

Machine Learning Solutions for Osteoporosis-A Review

Osteoporosis and its clinical consequence, bone fracture, is a multifactorial disease that has been the object of extensive research. Recent advances in machine learning (ML) have enabled the field of artificial intelligence (AI) to make impressive breakthroughs in complex data environments where human capacity to identify high-dimensional relationships is limited. The field of osteoporosis is one such domain, notwithstanding technical and clinical concerns regarding the application of ML methods. This qualitative review is intended to outline some of these concerns and to inform stakeholders interested in applying AI for improved management of osteoporosis. A systemic search in PubMed and Web of Science resulted in 89 studies for inclusion in the review. These covered one or more of four main areas in osteoporosis management: bone properties assessment (n = 13), osteoporosis classification (n = 34), fracture detection (n = 32), and risk prediction (n = 14). Reporting and methodological quality was determined by means of a 12-point checklist. In general, the studies were of moderate quality with a wide range (mode score 6, range 2 to 11). Major limitations were identified in a significant number of studies. Incomplete reporting, especially over model selection, inadequate splitting of data, and the low proportion of studies with external validation were among the most frequent problems. However, the use of images for opportunistic osteoporosis diagnosis or fracture detection emerged as a promising approach and one of the main contributions that ML could bring to the osteoporosis field. Efforts to develop ML-based models for identifying novel fracture risk factors and improving fracture prediction are additional promising lines of research. Some studies also offered insights into the potential for model-based decision-making. Finally, to avoid some of the common pitfalls, the use of standardized checklists in developing and sharing the results of ML models should be encouraged. © 2021 American Society for Bone and Mineral Research (ASBMR).

Integration of a vertebral fracture identification service into a fracture liaison service: a quality improvement project

Integration of a vertebral fracture identification service into a Fracture Liaison Service is possible. Almost one-fifth of computerised tomography scans performed identified an individual with a fracture. This increase in workload needs to be considered by any FLS that wants to utilise such a service.

INTRODUCTION

This service improvement project aimed to improve detection of incidental vertebral fractures on routine imaging. It embedded a vertebral fracture identification service (Optasia Medical, OM) on routine computerised tomography (CT) scans performed in this hospital as part of its Fracture Liaison Service (FLS).

METHODS

The service was integrated into the hospital's CT workstream. Scans of patients aged ≥ 50 years for 3 months were prospectively retrieved, alongside their clinical history and the CT report. Fractures were identified via OM's machine learning algorithm and cross-checked by the OM radiologist. Fractures identified were then added as an addendum to the original CT report and the hospital FLS informed. The FLS made recommendations based on an agreed algorithm.

RESULTS

In total, 4461 patients with CT scans were retrieved over the 3-month period of which 850 patients had vertebra fractures identified (19.1%). Only 49% had the fractures described on hospital radiology report. On average, 61 patients were identified each week with a median of two fractures. Thirty-six percent were identified by the FLS for further action and recommendations were made to either primary care or the community osteoporosis team within 3 months of fracture detection. Of the 64% not identified for further action, almost half was because the CT was part of cancer assessment or treatment. The remaining were due to a combination of only ≤ 2 mild fractures; already known to a bone health specialist; in the terminal stages of any chronic illness; significant dependency for activities of daily living; or a life expectancy of less than 12 months CONCLUSION: It was feasible to integrate a commercial vertebral fracture identification service into the daily working of a FLS. There was a significant increase in workload which needs to be considered by any future FLS planning to incorporate such a service into their clinical practice.

CT Cervical Spine Fracture Detection Using a Convolutional Neural Network

BACKGROUND AND PURPOSE

Multidetector CT has emerged as the standard of care imaging technique to evaluate cervical spine trauma. Our aim was to evaluate the performance of a convolutional neural network in the detection of cervical spine fractures on CT.

MATERIALS AND METHODS

We evaluated C-spine, an FDA-approved convolutional neural network developed by Aidoc to detect cervical spine fractures on CT. A total of 665 examinations were included in our analysis. Ground truth was established by retrospective visualization of a fracture on CT by using all available CT, MR imaging, and convolutional neural network output information. The ĸ coefficients, sensitivity, specificity, and positive and negative predictive values were calculated with 95% CIs comparing diagnostic accuracy and agreement of the convolutional neural network and radiologist ratings, respectively, compared with ground truth.

RESULTS

Convolutional neural network accuracy in cervical spine fracture detection was 92% (95% CI, 90%-94%), with 76% (95% CI, 68%-83%) sensitivity and 97% (95% CI, 95%-98%) specificity. The radiologist accuracy was 95% (95% CI, 94%-97%), with 93% (95% CI, 88%-97%) sensitivity and 96% (95% CI, 94%-98%) specificity. Fractures missed by the convolutional neural network and by radiologists were similar by level and location and included fractured anterior osteophytes, transverse processes, and spinous processes, as well as lower cervical spine fractures that are often obscured by CT beam attenuation.

CONCLUSIONS

The convolutional neural network holds promise at both worklist prioritization and assisting radiologists in cervical spine fracture detection on CT. Understanding the strengths and weaknesses of the convolutional neural network is essential before its successful incorporation into clinical practice. Further refinements in sensitivity will improve convolutional neural network diagnostic utility.

A diagnostic model for differentiating tuberculous spondylitis from pyogenic spondylitis on computed tomography images

OBJECTIVES

To develop and evaluate a logistics regression diagnostic model based on computer tomography (CT) features to differentiate tuberculous spondylitis (TS) from pyogenic spondylitis (PS).

METHODS

Demographic and clinical features were collected from the Electronic Medical Record System. Data of bony changes seen on CT images were compared between the PS (n = 61) and TS (n = 51) groups using the chi-squared test or t test. Based on features that were identified to be significant, a diagnostic model was developed from a derivation set (two thirds) and evaluated in a validation set (one third). The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated.

RESULTS

The width of bone formation around the vertebra and sequestrum was greater in the TS group. There were significant differences between the two groups in the horizontal and longitudinal location of erosion and the morphology of axial bone destruction and sagittal residual vertebra. Kyphotic deformity and overlapping vertebrae were more common in the TS group. A diagnostic model that included eight predictors was developed and simplified to include the following six predictors: width of the bone formation surrounding the vertebra, longitudinal location, axial-specific erosive morphology, specific morphology of the residual vertebra, kyphotic deformity, and overlapping vertebrae. The simplified model showed good sensitivity, specificity, and total accuracy (85.59%, 87.80%, and 86.50%, respectively); the AUC was 0.95, indicating good clinical predictive ability.

CONCLUSIONS

A diagnostic model based on bone destruction and formation seen on CT images can facilitate clinical differentiation of TS from PS.

KEY POINTS

• We have developed and validated a simple diagnostic model based on bone destruction and formation observed on CT images that can differentiate tuberculous spondylitis from pyogenic spondylitis. • The model includes six predictors: width of the bone formation surrounding the vertebra, longitudinal location, axial-specific erosive morphology, specific morphology of the residual vertebra, kyphotic deformity, and overlapping vertebrae. • The simplified model has good sensitivity, specificity, and total accuracy with a high AUC, indicating excellent predictive ability.