Fully automated radiomic screening pipeline for osteoporosis and abnormal bone density with a deep learning-based segmentation using a short lumbar mDixon sequence

T2-Weighted MRI-Based Vertebral Bone Quality Score is an Independent Risk Factor of Osteoporotic Vertebral Compression Fracture: An Age- and Sex-Matched Study

Study DesignA case-controlled retrospective study.ObjectiveWe aimed to explore the effectiveness of MRI-based VBQ scores derived by different MRI sequences in assessing risk of an osteoporotic vertebral compression fracture (OVCF) in age- and sex-controlled patients.MethodsThis retrospective study included patients hospitalized for OVCF (fracture group) and degenerative lumbar disease (non-fracture group) from July 2022 to July 2024. Patients in both groups were matched for sex and age in a 1:1 ratio. VBQ scores were acquired from non-contrast lumbosacral MRI T1-weighted, T2-weighted, and short tau inversion recovery (STIR)-weighted sequences. A receiver operating characteristic (ROC) curve and area under the ROC (AUC) were plotted to evaluate the diagnostic accuracy.ResultsA total of 168 patients (n = 84 in each group) were included. VBQ-T1 scores were higher in the fracture group (4.4 vs 4.1, P = 0.001), with an AUC of 0.641 to predict OVCF. VBQ-T2 scores were higher in the fracture group (0.60 vs 0.55, P < 0.001), with an AUC of 0.697. Additionally, VBQ-T2-STIR scores were higher in the fracture group (0.99 vs 0.83, P = 0.004), with an AUC of 0.644. Multivariate logistic regression analysis identified VBQ-T2, rather than VBQ-T1 or VBQ-T2-STIR, as an independent risk factor for OVFC.ConclusionThis study evaluated the MRI-based VBQ scores in assessing risk of OVCF based on age- and sex-matched cases. The VBQ-T2 score appears most promising for evaluating the risk of OVCF in clinical practice.

Conventional chest computed tomography-based radiomics for predicting the risk of thoracolumbar osteoporotic vertebral fractures

Our study focused on predicting thoracolumbar osteoporotic vertebral fractures through radiomic analysis of non-fractured thoracic vertebrae using conventional chest CT. Four types of radiomics models were developed and showed acceptable prediction performance. Radiomics models incorporating both cortical-appendicular and trabecular bone may have superior performance compared to those using either feature set individually. The RAD score models based on thoracic vertebral combinations achieved comparable performance with lumbar bone mineral density (BMD) measurements.

PURPOSE

To develop and validate radiomics models based on chest CT for predicting the risk of thoracolumbar osteoporotic vertebral fractures (OVFs).

METHODS

A total of 494 patients (including 198 patients with thoracolumbar OVFs) who underwent conventional chest CT scans were included in this retrospective analysis and were divided into training set 1 (n = 334) and validation set 1 (n = 160). Radiomics features (RFs) were extracted from each thoracic vertebral level on chest CT images. Four types of radiomics models (trabecular RFs, cortical-appendicular RFs, mixed RFs, and RAD score) were constructed and compared. Additionally, RAD score models based on trabecular and cortical-appendicular bone of different vertebral combinations (T1-T6, T7-T12, and top 3 vertebrae) were performed, respectively. A subset of patients with available bone mineral density (BMD) data formed training set 2 (n = 199) and validation set 2 (n = 88). We combined RAD score of different vertebral combinations with lumbar BMD for predicting thoracolumbar OVFs, and further adjusted for age. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC).

RESULTS

Among the radiomics models, the RAD score model based on trabecular and cortical-appendicular bone achieved highest AUC at the most vertebral levels. The RAD score model of top 3 (T5 + T8 + T10) vertebrae achieved higher AUC (0.813) than T7-T12 (AUC = 0.780) with a statistically significant difference (P = 0.02) and T1-T6 (AUC = 0.772) without a statistically significant difference (P = 0.062). Prior to adjusting for age, both RAD score models (AUCs 0.774-0.807) and RAD score + BMD models (AUCs 0.771-0.800) demonstrated slightly superior performance compared to BMD (AUC = 0.736) alone in predicting OVFs, although the differences were not statistically significant (P > 0.05). Following adjustment for age, our RAD score models, which utilized different vertebral combinations (AUCs 0.784-0.804), were found to be comparable to lumbar BMD (AUC = 0.785) in predicting OVFs (P > 0.05).

CONCLUSION

Radiomics analysis based on conventional chest CT can provide valuable information for predicting thoracolumbar OVFs. Radiomics models incorporating both cortical-appendicular and trabecular bone may have superior performance compared to those using either feature set alone. RAD score models based on thoracic vertebral combinations comparable performance compared to lumbar BMD highlights its clinical utility.

The Quality and Accuracy of Radiomics Model in Diagnosing Osteoporosis: A Systematic Review and Meta-analysis

RATIONALE AND OBJECTIVES

The purpose of this study is to conduct a meta-analysis to evaluate the diagnostic performance of current radiomics models for diagnosing osteoporosis, as well as to assess the methodology and reporting quality of these radiomics studies.

METHODS

According to PRISMA guidelines, four databases including MEDLINE, Web of Science, Embase and the Cochrane Library were searched systematically to select relevant studies published before July 18, 2024. The articles that used radiomics models for diagnosing osteoporosis were considered eligible. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and radiomics quality score (RQS) were used to assess the quality of included studies. The pooled diagnostic odds ratio (DOR), sensitivity, specificity, area under the summary receiver operator characteristic curve (AUC) were calculated to estimated diagnostic efficiency of pooled model.

RESULTS

A total of 25 studies were included, of which 24 provided usable data that were utilized for the meta-analysis, including 1553 patients with osteoporosis and 2200 patients without osteoporosis. The mean RQS score of included studies was 11.48 ± 4.92, with an adherence rate of 31.89%. The pooled DOR, sensitivity and specificity for model to diagnose osteoporosis were 81.72 (95% CI: 51.08 - 130.73), 0.90 (95% CI: 0.87-0.93) and 0.90 (95% CI: 0.87-0.93), respectively. The AUC was 0.96, indicating a high diagnostic capability. Subgroup analysis revealed that the use of different imaging modalities to construct radiomics models might be one source of heterogeneity. Radiomics models built using CT images and deep learning algorithms demonstrated higher diagnostic accuracy for osteoporosis.

CONCLUSION

Radiomics models for the diagnosis of osteoporosis have high diagnostic efficacy. In the future, radiomics models for diagnosing osteoporosis will be an efficient instrument to assist clinical doctors in screening osteoporosis patients. However, relevant guidelines should be followed strictly to improve the quality of radiomics studies.

Quantification of infrapatellar fat pad fibrosis using magnetic resonance imaging-derived proton density fat fraction: a pathology-controlled study

Background

Knee osteoarthritis (KOA) is a degenerative joint disease leading to disability in the elderly. Fibrosis of the infrapatellar fat pad (IPFP) impacts knee joint function and disease progression. Accurate assessment of IPFP fibrosis aids early intervention and treatment. The aim of this study was to evaluate the diagnostic efficacy of proton density fat fraction (PDFF) and T2* measurements using mDixon-Quant technology in assessing IPFP fibrosis in KOA.

Methods

A total of 47 patients were included in this study (23 patients without fibrosis, 17 with mild fibrosis, and 7 with severe fibrosis). Knee magnetic resonance (MR) scans were performed on a 3.0 T MR system. MR sequences included 3.0 T, sagittal T2-weighted images, proton density-weighted spectral adiabatic inversion recovery (PDW-SPAIR), and three-dimensional (3D) six-echo gradient recalled echo sequence (mDixon-Quant). Two radiologists performed PDFF, T2* measurements, and the hypointense signal grade of the IPFP. Measurements were compared among the three subgroups, and correlations of the three parameters with pathology-derived IPFP fibrosis degree and diagnostic efficacy were evaluated. Intraclass correlation coefficient (ICC), one-way analysis of variance (ANOVA), and Spearman correlation analysis were used. The diagnostic performance was assessed using the area under the receiver operating characteristic (ROC) curve (AUC) and linear regression with leave-one-out cross validation. Statistical significance was set at P<0.05.

Results

MR measurements demonstrated good inter-observer reproducibility (ICC for PDFF =0.901, ICC for T2* =0.902). The PDFF and T2* values in the normal and mild fibrosis groups were higher than those in the severe fibrosis group. PDFF and T2* measurements were strongly correlated with IPFP fibrosis (ρ=-0.7083, -0.6028, respectively). PDFF and T2* showed good diagnostic performance for IPFP fibrosis (AUC =0.9529, 0.8098, respectively). Adjusted R2 indicated similar results (PDFF 0.6682, T2* 0.538, hypointense 0.1437). Using PDFF and T2* together showed good diagnostic performance for IPFP fibrosis (AUC =0.9601) and had the best R2 of 0.6995.

Conclusions

PDFF and T2* measurements based on mDixon technology provide a non-invasive and quantitative assessment of IPFP fibrosis, especially PDFF.

Effect of adipose tissue deposition on insulin resistance in middle-aged and elderly women: Based on QCT and MRI mDIXON-Quant

OBJECTIVE

To explore the relationship between adipose tissue deposition and triglyceride-glucose (TyG) index, an indicator clinically used to assess insulin resistance (IR), in middle-aged and elderly women using quantitative computed tomography (QCT) and MRI mDIXON-Quant sequence.

METHODS

All participants underwent quantitative computed tomography (QCT) and MRI mDIXON-Quant examination and calculated the TyG index based on the fasting blood glucose and triacylglycerol. Bounded by the median TyG index, all participants were divided into low TyG group and high TyG group. Visceral fat mass (VFM) and subcutaneous fat mass (SFM) were measured on QCT images. Hepatic proton density fat fraction (H-PDFF), pancreatic proton density fat fraction (P-PDFF), and lumbar bone marrow fat fraction (L-BMFF) were measured on MRI mDIXON-Quant images.

RESULTS

Adjusting for age and body mass index (BMI), TyG was moderately positively correlated with H-PDFF, and r/P was 0.416/<0.001, TyG index was weakly positively correlated with VFM and P-PDFF, and r/P were 0.385/<0.001 and 0.221/0.030. There was a difference of VFM, H-PDFF, and P-PDFF between low TyG group and high TyG group (P < 0.05). Adjusting for age and BMI, VFM, and H-PDFF were the risk factors of high TyG, and H-PDFF was the independent risk factor of high TyG.

CONCLUSIONS

VFM and H-PDFF were the risk factors of IR, and H-PDFF was the independent risk factor. Early identification and active treatment of adipose tissue deposition, especially hepatic fat deposition, may reserve and delay the progression of IR and even metabolic syndrome.

Radiomics models based on thoracic and upper lumbar spine in chest LDCT to predict low bone mineral density

This study aims to develop and validate different radiomics models based on thoracic and upper lumbar spine in chest low-dose computed tomography (LDCT) to predict low bone mineral density (BMD) using quantitative computed tomography (QCT) as standard of reference. A total of 905 participants underwent chest LDCT and paired QCT BMD examination were retrospectively included from August 2018 and June 2019. The patients with low BMD (n = 388) and the normal (n = 517) were randomly divided into a training set (n = 622) and a validation set (n = 283). Radiomics features (RFs) were extracted from the single and consecutive vertebrae in chest LDCT images to construct the single vertebra RFs models, mixed RFs models and Radscore models, respectively. The performance of these models was evaluated by the area under the curve (AUC) of receiver operator characteristic curve, using QCT as standard of reference. The Radscore models, mixed RFs models, and single vertebra RFs models yielded the AUC values ranging from 0.809 to 0.906, 0.792 to 0.883, and 0.731 to 0.884 for predicting low BMD in the validation set, respectively. For predicting low BMD, the Radscore model of L1-L2 vertebrae yielded the highest AUC of 0.906, and of T1-T3 yielded the lowest AUC of 0.809 (P < 0.05), respectively. However, there was no significant difference among the AUC values of three Radscore models constructed on the vertebrae of T4-T6 (AUC = 0.855), T7-T9 (AUC = 0.845), and T10-T12 (AUC = 0.871) for predicting low BMD in the validation set (P > 0.1). The Radscore model of L1-L2 have potential to serve as an important tool for predicting and screening low BMD from normal in chest LDCT images.

Enhancing the Opportunistic Bone Status Assessment Using Radiomics Based on Dual-Energy Spectral CT Material Decomposition Images

The dual-energy spectral CT (DEsCT) employs material decomposition (MD) technology, opening up novel avenues for the opportunistic assessment of bone status. Radiomics, a powerful tool for elucidating the structural and textural characteristics of bone, aids in the detection of mineral loss. Therefore, this study aims to compare the efficacy of bone status assessment using both bone density measurements and radiomics models derived from MD images and to further explore the clinical value of radiomics models.

METHODS

Retrospective data were collected from 307 patients who underwent both quantitative computed tomography (QCT) and full-abdomen DEsCT scans at our institution. Based on QCT measurements, patients were divided into three categories: normal bone mineral density (BMD), osteopenia, and osteoporosis. Using the abdominal DEsCT data, six types of MD images were reconstructed, including HAP (Water), HAP (Fat), Ca (Water), Ca (Fat), Fat (Ca), and Fat (HAP). Patients were randomly divided into a training cohort (n = 214) and a validation cohort (n = 93) at a ratio of 7:3. Focusing on the L1 to L3 vertebrae, density values from the six MD images were measured. Six density value models and six radiomics models were constructed using a random forest (RF) classifier. The performance of these models in assessing bone status was evaluated using the receiver operating characteristic (ROC) curves, and the DeLong test was employed to compare performance differences between the models.

RESULTS

The macro-area under the curve (AUC) values for the density value models based on HAP (Water), HAP (Fat), Ca (Water), and Ca (Fat) MD images were 0.870, 0.870, 0.847, and 0.765, respectively, which outperformed those of Fat (Ca) (AUC = 0.623) and Fat (HAP) (AUC = 0.618) density value models. In the comparison of radiomics models, the trends of model performance were consistent with the density value models across the six MD images. However, the models based on HAP (Water), Ca (Water), HAP (Fat), Ca (Fat), Fat (Ca), and Fat (HAP) images exhibited superior performance than those of the density value models with the corresponding MD images, with values of 0.946, 0.941, 0.934, 0.926, 0.831, and 0.824, respectively.

CONCLUSIONS

Bone status assessment can be accurately conducted using density values from HAP (Water), HAP (Fat), Ca (Water), and Ca (Fat) MD images. However, radiomics models derived from MD images surpass traditional density measurement methods in evaluating bone status, highlighting their superior diagnostic potential.

Deep-Learning-Based Radiomics to Predict Surgical Risk Factors for Lumbar Disc Herniation in Young Patients: A Multicenter Study

Objective

The aim of this study is to develop and validate a deep-learning radiomics model for predicting surgical risk factors for lumbar disc herniation (LDH) in young patients to assist clinicians in identifying surgical candidates, alleviating symptoms, and improving prognosis.

Methods

A retrospective analysis of patients from two medical centers was conducted. From sagittal and axial MR images, the regions of interest were handcrafted to extract radiomics features. Various machine-learning algorithms were employed and combined with clinical features, resulting in the development of a deep-learning radiomics nomogram (DLRN) to predict surgical risk factors for LDH in young adults. The efficacy of the different models and the clinical benefits of the model were compared.

Results

We derived six sets of features, including clinical features, radiomics features (Rad_SAG and Rad_AXI) and deep learning features (DL_SAG and DL_AXI) from sagittal and axial MR images, as well as fused deep-learning radiomics (DLR) features. The support vector machine(SVM) algorithm exhibited the best performance. The area under the curve (AUC) of DLR in the training and testing cohorts of 0.991 and 0.939, respectively, were significantly better than those of the models developed with radiomics(Rad_SAG=0.914 and 0.863, Rad_AXI=0.927 and 0.85) and deep-learning features(DL_SAG=0.959 and 0.818, DL_AXI=0.960 and 0.811). The AUC of DLRN coupled with clinical features(ODI, Pfirrmann grade, SLRT, MMFI, and MSU classification) were 0.994 and 0.941 in the training and testing cohorts, respectively. Analysis of the calibration and decision curves demonstrated good agreement between the predicted and observed outcomes, and the use of the DLRN to predict the need for surgical treatment of LDH demonstrated significant clinical benefits.

Conclusion

The DLRN established based on clinical and DLR features effectively predicts surgical risk factors for LDH in young adults, offering valuable insights for diagnosis and treatment.

A novel deep learning method for large-scale analysis of bone marrow adiposity using UK Biobank Dixon MRI data

Background

Bone marrow adipose tissue (BMAT) represents > 10% fat mass in healthy humans and can be measured by magnetic resonance imaging (MRI) as the bone marrow fat fraction (BMFF). Human MRI studies have identified several diseases associated with BMFF but have been relatively small scale. Population-scale studies therefore have huge potential to reveal BMAT's true clinical relevance. The UK Biobank (UKBB) is undertaking MRI of 100,000 participants, providing the ideal opportunity for such advances.

Objective

To establish deep learning for high-throughput multi-site BMFF analysis from UKBB MRI data.

Materials and methods

We studied males and females aged 60-69. Bone marrow (BM) segmentation was automated using a new lightweight attention-based 3D U-Net convolutional neural network that improved segmentation of small structures from large volumetric data. Using manual segmentations from 61-64 subjects, the models were trained to segment four BM regions of interest: the spine (thoracic and lumbar vertebrae), femoral head, total hip and femoral diaphysis. Models were tested using a further 10-12 datasets per region and validated using datasets from 729 UKBB participants. BMFF was then quantified and pathophysiological characteristics assessed, including site- and sex-dependent differences and the relationships with age, BMI, bone mineral density, peripheral adiposity, and osteoporosis.

Results

Model accuracy matched or exceeded that for conventional U-Nets, yielding Dice scores of 91.2% (spine), 94.5% (femoral head), 91.2% (total hip) and 86.6% (femoral diaphysis). One case of severe scoliosis prevented segmentation of the spine, while one case of Non-Hodgkin Lymphoma prevented segmentation of the spine, femoral head and total hip because of T2 signal depletion; however, successful segmentation was not disrupted by any other pathophysiological variables. The resulting BMFF measurements confirmed expected relationships between BMFF and age, sex and bone density, and identified new site- and sex-specific characteristics.

Conclusions

We have established a new deep learning method for accurate segmentation of small structures from large volumetric data, allowing high-throughput multi-site BMFF measurement in the UKBB. Our findings reveal new pathophysiological insights, highlighting the potential of BMFF as a novel clinical biomarker. Applying our method across the full UKBB cohort will help to reveal the impact of BMAT on human health and disease.

Estimating lumbar bone mineral density from conventional MRI and radiographs with deep learning in spine patients

PURPOSE

This study aimed to develop machine learning methods to estimate bone mineral density and detect osteopenia/osteoporosis from conventional lumbar MRI (T1-weighted and T2-weighted images) and planar radiography in combination with clinical data and imaging parameters of the acquisition protocol.

METHODS

A database of 429 patients subjected to lumbar MRI, radiographs and dual-energy x-ray absorptiometry within 6 months was created from an institutional database. Several machine learning models were trained and tested (373 patients for training, 86 for testing) with the following objectives: (1) direct estimation of the vertebral bone mineral density; (2) classification of T-score lower than - 1 or (3) lower than - 2.5. The models took as inputs either the images or radiomics features derived from them, alone or in combination with metadata (age, sex, body size, vertebral level, parameters of the imaging protocol).

RESULTS

The best-performing models achieved mean absolute errors of 0.15-0.16 g/cm2 for the direct estimation of bone mineral density, and areas under the receiver operating characteristic curve of 0.82 (MRIs) - 0.80 (radiographs) for the classification of T-scores lower than - 1, and 0.80 (MRIs) - 0.65 (radiographs) for T-scores lower than - 2.5.

CONCLUSIONS

The models showed good discriminative performances in detecting cases of low bone mineral density, and more limited capabilities for the direct estimation of its value. Being based on routine imaging and readily available data, such models are promising tools to retrospectively analyse existing datasets as well as for the opportunistic investigation of bone disorders.

Development and reporting of artificial intelligence in osteoporosis management

An abundance of medical data and enhanced computational power have led to a surge in artificial intelligence (AI) applications. Published studies involving AI in bone and osteoporosis research have increased exponentially, raising the need for transparent model development and reporting strategies. This review offers a comprehensive overview and systematic quality assessment of AI articles in osteoporosis while highlighting recent advancements. A systematic search in the PubMed database, from December 17, 2020 to February 1, 2023 was conducted to identify AI articles that relate to osteoporosis. The quality assessment of the studies relied on the systematic evaluation of 12 quality items derived from the minimum information about clinical artificial intelligence modeling checklist. The systematic search yielded 97 articles that fell into 5 areas; bone properties assessment (11 articles), osteoporosis classification (26 articles), fracture detection/classification (25 articles), risk prediction (24 articles), and bone segmentation (11 articles). The average quality score for each study area was 8.9 (range: 7-11) for bone properties assessment, 7.8 (range: 5-11) for osteoporosis classification, 8.4 (range: 7-11) for fracture detection, 7.6 (range: 4-11) for risk prediction, and 9.0 (range: 6-11) for bone segmentation. A sixth area, AI-driven clinical decision support, identified the studies from the 5 preceding areas that aimed to improve clinician efficiency, diagnostic accuracy, and patient outcomes through AI-driven models and opportunistic screening by automating or assisting with specific clinical tasks in complex scenarios. The current work highlights disparities in study quality and a lack of standardized reporting practices. Despite these limitations, a wide range of models and examination strategies have shown promising outcomes to aid in the earlier diagnosis and improve clinical decision-making. Through careful consideration of sources of bias in model performance assessment, the field can build confidence in AI-based approaches, ultimately leading to improved clinical workflows and patient outcomes.

Automated graded prognostic assessment for patients with hepatocellular carcinoma using machine learning

BACKGROUND

Accurate mortality risk quantification is crucial for the management of hepatocellular carcinoma (HCC); however, most scoring systems are subjective.

PURPOSE

To develop and independently validate a machine learning mortality risk quantification method for HCC patients using standard-of-care clinical data and liver radiomics on baseline magnetic resonance imaging (MRI).

METHODS

This retrospective study included all patients with multiphasic contrast-enhanced MRI at the time of diagnosis treated at our institution. Patients were censored at their last date of follow-up, end-of-observation, or liver transplantation date. The data were randomly sampled into independent cohorts, with 85% for development and 15% for independent validation. An automated liver segmentation framework was adopted for radiomic feature extraction. A random survival forest combined clinical and radiomic variables to predict overall survival (OS), and performance was evaluated using Harrell's C-index.

RESULTS

A total of 555 treatment-naïve HCC patients (mean age, 63.8 years ± 8.9 [standard deviation]; 118 females) with MRI at the time of diagnosis were included, of which 287 (51.7%) died after a median time of 14.40 (interquartile range, 22.23) months, and had median followed up of 32.47 (interquartile range, 61.5) months. The developed risk prediction framework required 1.11 min on average and yielded C-indices of 0.8503 and 0.8234 in the development and independent validation cohorts, respectively, outperforming conventional clinical staging systems. Predicted risk scores were significantly associated with OS (p < .00001 in both cohorts).

CONCLUSIONS

Machine learning reliably, rapidly, and reproducibly predicts mortality risk in patients with hepatocellular carcinoma from data routinely acquired in clinical practice.

CLINICAL RELEVANCE STATEMENT

Precision mortality risk prediction using routinely available standard-of-care clinical data and automated MRI radiomic features could enable personalized follow-up strategies, guide management decisions, and improve clinical workflow efficiency in tumor boards.

KEY POINTS

• Machine learning enables hepatocellular carcinoma mortality risk prediction using standard-of-care clinical data and automated radiomic features from multiphasic contrast-enhanced MRI. • Automated mortality risk prediction achieved state-of-the-art performances for mortality risk quantification and outperformed conventional clinical staging systems. • Patients were stratified into low, intermediate, and high-risk groups with significantly different survival times, generalizable to an independent evaluation cohort.

Predicting osteoporosis from kidney-ureter-bladder radiographs utilizing deep convolutional neural networks

Osteoporosis is a common condition that can lead to fractures, mobility issues, and death. Although dual-energy X-ray absorptiometry (DXA) is the gold standard for osteoporosis, it is expensive and not widely available. In contrast, kidney-ureter-bladder (KUB) radiographs are inexpensive and frequently ordered in clinical practice. Thus, it is a potential screening tool for osteoporosis. In this study, we explored the possibility of predicting the bone mineral density (BMD) and classifying high-risk patient groups using KUB radiographs. We proposed DeepDXA-KUB, a deep learning model that predicts the BMD values of the left hip and lumbar vertebrae from an input KUB image. The datasets were obtained from Taiwanese medical centers between 2006 and 2019, using 8913 pairs of KUB radiographs and DXA examinations performed within 6 months. The images were randomly divided into training and validation sets in a 4:1 ratio. To evaluate the model's performance, we computed a confusion matrix and evaluated the sensitivity, specificity, accuracy, precision, positive predictive value, negative predictive value, F1 score, and area under the receiver operating curve (AUROC). Moderate correlations were observed between the predicted and DXA-measured BMD values, with a correlation coefficient of 0.858 for the lumbar vertebrae and 0.87 for the left hip. The model demonstrated an osteoporosis detection accuracy, sensitivity, and specificity of 84.7 %, 81.6 %, and 86.6 % for the lumbar vertebrae and 84.2 %, 91.2 %, and 81 % for the left hip, respectively. The AUROC was 0.939 for the lumbar vertebrae and 0.947 for the left hip, indicating a satisfactory performance in osteoporosis screening. The present study is the first to develop a deep learning model based on KUB radiographs to predict lumbar spine and femoral BMD. Our model demonstrated a promising correlation between the predicted and DXA-measured BMD in both the lumbar vertebrae and hip, showing great potential for the opportunistic screening of osteoporosis.

Application of Artificial Intelligence Methods on Osteoporosis Classification with Radiographs-A Systematic Review

Osteoporosis is a complex endocrine disease characterized by a decline in bone mass and microstructural integrity. It constitutes a major global health problem. Recent progress in the field of artificial intelligence (AI) has opened new avenues for the effective diagnosis of osteoporosis via radiographs. This review investigates the application of AI classification of osteoporosis in radiographs. A comprehensive exploration of electronic repositories (ClinicalTrials.gov, Web of Science, PubMed, MEDLINE) was carried out in adherence to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2020 statement (PRISMA). A collection of 31 articles was extracted from these repositories and their significant outcomes were consolidated and outlined. This encompassed insights into anatomical regions, the specific machine learning methods employed, the effectiveness in predicting BMD, and categorizing osteoporosis. Through analyzing the respective studies, we evaluated the effectiveness and limitations of AI osteoporosis classification in radiographs. The pooled reported accuracy, sensitivity, and specificity of osteoporosis classification ranges from 66.1% to 97.9%, 67.4% to 100.0%, and 60.0% to 97.5% respectively. This review underscores the potential of AI osteoporosis classification and offers valuable insights for future research endeavors, which should focus on addressing the challenges in technical and clinical integration to facilitate practical implementation of this technology.

Deep learning in the radiologic diagnosis of osteoporosis: a literature review

OBJECTIVE

Osteoporosis is a systemic bone disease characterized by low bone mass, damaged bone microstructure, increased bone fragility, and susceptibility to fractures. With the rapid development of artificial intelligence, a series of studies have reported deep learning applications in the screening and diagnosis of osteoporosis. The aim of this review was to summary the application of deep learning methods in the radiologic diagnosis of osteoporosis.

METHODS

We conducted a two-step literature search using the PubMed and Web of Science databases. In this review, we focused on routine radiologic methods, such as X-ray, computed tomography, and magnetic resonance imaging, used to opportunistically screen for osteoporosis.

RESULTS

A total of 40 studies were included in this review. These studies were divided into three categories: osteoporosis screening (n = 20), bone mineral density prediction (n = 13), and osteoporotic fracture risk prediction and detection (n = 7).

CONCLUSIONS

Deep learning has demonstrated a remarkable capacity for osteoporosis screening. However, clinical commercialization of a diagnostic model for osteoporosis remains a challenge.

Assessment of Osteoporosis at the Lumbar Spine Using Ultrashort Echo Time Magnetization Transfer (UTE-MT) MRI

BACKGROUND

Bone collagen-matrix contributes to the mechanical properties of bone by imparting tensile strength and elasticity, which can be indirectly quantified by ultrashort echo time magnetization transfer ratio (UTE-MTR) to assess osteoporosis.

PURPOSE

To evaluate osteoporosis at the human lumbar spine using UTE-MTR.

STUDY TYPE

Prospective.

POPULATION

One hundred forty-eight-volunteers (age-range, 50-85; females, N = 90), including 81-normal bone density, 35-osteopenic, and 32-osteoporotic subjects. Ten additional healthy volunteers were recruited to study the intrasession reproducibility of the UTE-MT.

FIELD STRENGTH/SEQUENCE

3T/UTE-MT, short repetition-time adiabatic inversion recovery prepared UTE (STAIR-UTE), and iterative decomposition of water-and-fat with echo-asymmetry and least-squares estimation (IDEAL-IQ).

ASSESSMENT

Fracture risk was calculated using Fracture-Risk-Assessment-Tool (FRAX). Region-of-interests (ROIs) were delineated on the trabecular area in the maps of bone-mineral-density, UTE-MTR, collagen-bound water proton-fraction (CBWPF), and bone-marrow fat fraction (BMFF).

STATISTICAL TESTS

Linear-regression and Bland-Altman analysis were performed to assess the reproducibility of UTE-MTR measurements in the different scans. UTE-MTR and BMFF were correlated with bone-mineral-density using Pearson's regression and with FRAX scores using nonlinear regression. The abilities of UTE-MTR, CBWPF, and BMFF to discriminate between the three patient subgroups were evaluated using receiver-operator-characteristic (ROC) analysis and area-under-the-curve (AUC). Decision-curve-analysis (DCA) and clinical-impact curves were used to evaluate the value of UTE-MTR in clinical diagnosis. The DeLong test was used to compare the ROC curves. P-value <0.05 was considered statistically significant.

RESULTS

Excellent reproducibility was obtained for the UTE-MT measurements. UTE-MTR strongly correlated with bone-mineral-density (r = 0.76) and FRAX scores (r = -0.77). UTE-MTR exhibited higher AUCs (≥0.723) than BMFF, indicating its superior ability to distinguish between the three patient subgroups. The DCA and clinical-impact curves confirmed the diagnostic value of UTE-MTR. UTE-MTR and CBWPF showed similar performance in correlation with bone-mineral-density and cohort classification.

DATA CONCLUSION

UTE-MTR strongly correlates with bone-mineral-density and FRAX and shows great potential in distinguishing between normal, osteopenic, and osteoporotic subjects.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

Development and Validation of a Feature-Based Broad-Learning System for Opportunistic Osteoporosis Screening Using Lumbar Spine Radiographs

RATIONALE AND OBJECTIVES

Osteoporosis is primarily diagnosed using dual-energy X-ray absorptiometry (DXA); yet, DXA is significantly underutilized, causing osteoporosis, an underdiagnosed condition. We aimed to provide an opportunistic approach to screen for osteoporosis using artificial intelligence based on lumbar spine X-ray radiographs.

MATERIALS AND METHODS

In this institutional review board-approved retrospective study, female patients aged ≥50 years who received both X-ray scans and DXA of the lumbar vertebrae, in three centers, were included. A total of 1180 cases were used for training and 145 cases were used for testing. We proposed a novel broad-learning system (BLS) and then compared the performance of BLS models using radiomic features and deep features as a source of input. The deep features were extracted using ResNet18 and VGG11, respectively. The diagnostic performances of these BLS models were evaluated with the area under the curve (AUC), sensitivity, and specificity.

RESULTS

The incidence rate of osteoporosis in the training and test sets was 35.9% and 37.9%, respectively. The radiomic feature-based BLS model achieved higher testing AUC (0.802 vs. 0.654 vs. 0.632, both P = .002), sensitivity (78.2% vs. 56.4% vs. 50.9%), and specificity (82.2% vs. 74,4% vs. 75.6%) than the two deep feature-based BLS models.

CONCLUSION

Our proposed radiomic feature-based BLS model has the potential to expand osteoporosis screening to a broader population by identifying osteoporosis on lumbar spine X-ray radiographs.

Machine Learning and Radiomics of Bone Scintigraphy: Their Role in Predicting Recurrence of Localized or Locally Advanced Prostate Cancer

BACKGROUND

Machine-learning (ML) and radiomics features have been utilized for survival outcome analysis in various cancers. This study aims to investigate the application of ML based on patients' clinical features and radiomics features derived from bone scintigraphy (BS) and to evaluate recurrence-free survival in local or locally advanced prostate cancer (PCa) patients after the initial treatment.

METHODS

A total of 354 patients who met the eligibility criteria were analyzed and used to train the model. Clinical information and radiomics features of BS were obtained. Survival-related clinical features and radiomics features were included in the ML model training. Using the pyradiomics software, 128 radiomics features from each BS image's region of interest, validated by experts, were extracted. Four textural matrices were also calculated: GLCM, NGLDM, GLRLM, and GLSZM. Five training models (Logistic Regression, Naive Bayes, Random Forest, Support Vector Classification, and XGBoost) were applied using K-fold cross-validation. Recurrence was defined as either a rise in PSA levels, radiographic progression, or death. To assess the classifier's effectiveness, the ROC curve area and confusion matrix were employed.

RESULTS

Of the 354 patients, 101 patients were categorized into the recurrence group with more advanced disease status compared to the non-recurrence group. Key clinical features including tumor stage, radical prostatectomy, initial PSA, Gleason Score primary pattern, and radiotherapy were used for model training. Random Forest (RF) was the best-performing model, with a sensitivity of 0.81, specificity of 0.87, and accuracy of 0.85. The ROC curve analysis showed that predictions from RF outperformed predictions from other ML models with a final AUC of 0.94 and a p-value of <0.001. The other models had accuracy ranges from 0.52 to 0.78 and AUC ranges from 0.67 to 0.84.

CONCLUSIONS

The study showed that ML based on clinical features and radiomics features of BS improves the prediction of PCa recurrence after initial treatment. These findings highlight the added value of ML techniques for risk classification in PCa based on clinical features and radiomics features of BS.

The role of genetic and epigenetic factors in determining the risk of spinal fragility fractures: new insights in the management of spinal osteoporosis

Osteoporosis predisposes patients to spinal fragility fractures. Imaging plays a key role in the diagnosis and prognostication of these osteoporotic vertebral fractures (OVF). However, the current imaging knowledge base for OVF is lacking sufficient standardisation to enable effective risk prognostication. OVF have been shown to be more prevalent in Caucasian patient cohorts in comparison to the Eastern Asian population. These population-based differences in risk for developing OVF suggest that there could be genetic and epigenetic factors that drive the pathogenesis of osteoporosis, low bone mineral density (BMD) and OVF. Several genetic loci have been associated with a higher vertebral fracture risk, although at varying degrees of significance. The present challenge is clarifying whether these associations are specific to vertebral fractures or osteoporosis more generally. Furthermore, these factors could be exploited for diagnostic interpretation as biomarkers [including novel long non-coding (lnc)RNAs, micro (mi)RNAs and circular (circ)RNAs]. The extent of methylation of genes, alongside post-translational histone modifications, have shown to affect several interlinked pathways that converge on the regulation of bone deposition and resorption, partially through their influence on osteoblast and osteoclast differentiation. Lastly, in addition to biomarkers, several exciting new imaging modalities could add to the established dual-energy X-ray absorptiometry (DXA) method used for BMD assessment. New technologies, and novel sequences within existing imaging modalities, may be able to quantify the quality of bone in addition to the BMD and bone structure; these are making progress through various stages of development from the pre-clinical sphere through to deployment in the clinical setting. In this mini review, we explore the literature to clarify the genetic and epigenetic factors associated with spinal fragility fractures and delineate the causal genes, pathways and interactions which could drive different risk profiles. We also outline the cutting-edge imaging modalities which could transform diagnostic protocols for OVF.

New Horizons: Artificial Intelligence Tools for Managing Osteoporosis

Osteoporosis is a disease characterized by low bone mass and microarchitectural deterioration leading to increased bone fragility and fracture risk. Typically, osteoporotic fractures occur at the spine, hip, distal forearm, and proximal humerus, but other skeletal sites may be affected as well. One of the major challenges in the management of osteoporosis lies in the fact that although the operational diagnosis is based on bone mineral density (BMD) as measured by dual x-ray absorptiometry, the majority of fractures occur at nonosteoporotic BMD values. Furthermore, osteoporosis often remains undiagnosed regardless of the low severity of the underlying trauma. Also, there is only weak consensus among the major guidelines worldwide, when to treat, whom to treat, and which drug to use. Against this background, increasing efforts have been undertaken in the past few years by artificial intelligence (AI) developers to support and improve the management of this disease. The performance of many of these newly developed AI algorithms have been shown to be at least comparable to that of physician experts, or even superior. However, even if study results appear promising at a first glance, they should always be interpreted with caution. Use of inadequate reference standards or selection of variables that are of little or no value in clinical practice are limitations not infrequently found. Consequently, there is a clear need for high-quality clinical research in this field of AI. This could, eg, be achieved by establishing an internationally consented "best practice framework" that considers all relevant stakeholders.