Deep Learning to Differentiate Benign and Malignant Vertebral Fractures at Multidetector CT.

Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate between benign and malignant vertebral fractures. Materials and Methods CT scans acquired in patients with benign or malignant vertebral fractures from June 2005 to December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic and radiologic information. An internal test set was randomly selected, and an external test set was obtained from an additional hospital. Models used a three-dimensional U-Net encoder-classifier architecture and applied data augmentation during training. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared with that of two residents and one fellowship-trained radiologist using the DeLong test. Results The training set included 381 patients (mean age, 69.9 years ± 11.4 [SD]; 193 male) with 1307 vertebrae (378 benign fractures, 447 malignant fractures, 482 malignant lesions). Internal and external test sets included 86 (mean age, 66.9 years ± 12; 45 male) and 65 (mean age, 68.8 years ± 12.5; 39 female) patients, respectively. The better-performing model of two training approaches achieved AUCs of 0.85 (95% CI: 0.77, 0.92) in the internal and 0.75 (95% CI: 0.64, 0.85) in the external test sets. Including an uncertainty category further improved performance to AUCs of 0.91 (95% CI: 0.83, 0.97) in the internal test set and 0.76 (95% CI: 0.64, 0.88) in the external test set. The AUC values of residents were lower than that of the best-performing model in the internal test set (AUC, 0.69 [95% CI: 0.59, 0.78] and 0.71 [95% CI: 0.61, 0.80]) and external test set (AUC, 0.70 [95% CI: 0.58, 0.80] and 0.71 [95% CI: 0.60, 0.82]), with significant differences only for the internal test set (P < .001). The AUCs of the fellowship-trained radiologist were similar to those of the best-performing model (internal test set, 0.86 [95% CI: 0.78, 0.93; P = .39]; external test set, 0.71 [95% CI: 0.60, 0.82; P = .46]). Conclusion Developed models showed a high discriminatory power to differentiate between benign and malignant vertebral fractures, surpassing or matching the performance of radiology residents and matching that of a fellowship-trained radiologist. © RSNA, 2024 See also the editorial by Booz and D'Angelo in this issue.

Automated assessment of cardiac pathologies on cardiac MRI using T1-mapping and late gadolinium phase sensitive inversion recovery sequences with deep learning.

BACKGROUND: A deep learning (DL) model that automatically detects cardiac pathologies on cardiac MRI may help streamline the diagnostic workflow. To develop a DL model to detect cardiac pathologies on cardiac MRI T1-mapping and late gadolinium phase sensitive inversion recovery (PSIR) sequences were used. METHODS: Subjects in this study were either diagnosed with cardiac pathology (n = 137) including acute and chronic myocardial infarction, myocarditis, dilated cardiomyopathy, and hypertrophic cardiomyopathy or classified as normal (n = 63). Cardiac MR imaging included T1-mapping and PSIR sequences. Subjects were split 65/15/20% for training, validation, and hold-out testing. The DL models were based on an ImageNet pretrained DenseNet-161 and implemented using PyTorch and fastai. Data augmentation with random rotation and mixup was applied. Categorical cross entropy was used as the loss function with a cyclic learning rate (1e-3). DL models for both sequences were developed separately using similar training parameters. The final model was chosen based on its performance on the validation set. Gradient-weighted class activation maps (Grad-CAMs) visualized the decision-making process of the DL model. RESULTS: The DL model achieved a sensitivity, specificity, and accuracy of 100%, 38%, and 88% on PSIR images and 78%, 54%, and 70% on T1-mapping images. Grad-CAMs demonstrated that the DL model focused its attention on myocardium and cardiac pathology when evaluating MR images. CONCLUSIONS: The developed DL models were able to reliably detect cardiac pathologies on cardiac MR images. The diagnostic performance of T1 mapping alone is particularly of note since it does not require a contrast agent and can be acquired quickly.

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.

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 (ß = -0.32; 95% confidence interval (CI): -20.10, 4.35; p < 0.001) compared to manual measurements (ß = -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 Evaluation of MR-Based Radiogenomic Models to Differentiate Atypical Lipomatous Tumors from Lipomas.

BACKGROUND: The aim of this study was to develop and validate radiogenomic models to predict the MDM2 gene amplification status and differentiate between ALTs and lipomas on preoperative MR images. METHODS: MR images were obtained in 257 patients diagnosed with ALTs (n = 65) or lipomas (n = 192) using histology and the MDM2 gene analysis as a reference standard. The protocols included T2-, T1-, and fat-suppressed contrast-enhanced T1-weighted sequences. Additionally, 50 patients were obtained from a different hospital for external testing. Radiomic features were selected using mRMR. Using repeated nested cross-validation, the machine-learning models were trained on radiomic features and demographic information. For comparison, the external test set was evaluated by three radiology residents and one attending radiologist. RESULTS: A LASSO classifier trained on radiomic features from all sequences performed best, with an AUC of 0.88, 70% sensitivity, 81% specificity, and 76% accuracy. In comparison, the radiology residents achieved 60-70% accuracy, 55-80% sensitivity, and 63-77% specificity, while the attending radiologist achieved 90% accuracy, 96% sensitivity, and 87% specificity. CONCLUSION: A radiogenomic model combining features from multiple MR sequences showed the best performance in predicting the MDM2 gene amplification status. The model showed a higher accuracy compared to the radiology residents, though lower compared to the attending radiologist.

Diagnostic value of water-fat-separated images and CT-like susceptibility-weighted images extracted from a single ultrashort echo time sequence for the evaluation of vertebral fractures and degenerative changes of the spine.

OBJECTIVES: To evaluate the performance of single-echo Dixon water-fat imaging and computed tomography (CT)-like imaging based on a single ultrashort echo time (sUTE) MR sequence for imaging of vertebral fractures as well as degenerative bone changes of the spine in comparison to conventional CT and MR sequences. METHODS: Thirty patients with suspected acute vertebral fractures were examined using a 3-T MRI, including an sUTE sequence as well as short-tau inversion recovery (STIR) and T1-weighted sequences. During postprocessing, water-fat separation was performed by solving the smoothness-constrained inverse water-fat problem based on a single-complex UTE image. By removing the unwanted low-frequency phase terms, additional MR-based susceptibility-weighted-like (SW-like) images with CT-like contrast were created. Two radiologists evaluated semi-quantitative and quantitative features of fractures and degenerative changes independently and separately on CT and MR images. RESULTS: In total, all 58 fractures were accurately detected of whom 24 were correctly classified as acute fractures with an edema detected on the water-fat-separated UTE images, using STIR and T1w sequences as standard of reference. For the morphological assessment of fractures and degenerative changes, the overall agreement between SW-like images and CT was substantial to excellent (e.g., Genant: κ 0.90 (95% confidence interval 0.54-1.00); AO/Magerl: κ 0.75 (95% confidence interval 0.43-1.00)). Overall inter-reader agreement for water-fat-separated UTE images and SW-like images was substantial to almost perfect. CONCLUSION: Detection and assessment of vertebral fractures and degenerative bone changes of the spine were feasible and accurate using water-fat-separated images as well as SW-like images, both derived from the same sUTE-Dixon sequence. KEY POINTS: • The detection of acute vertebral fractures was feasible using water-fat-separated images and CT-like images reconstructed from one sUTE sequence. • Assessment of the vertebral fractures using SW-like images with CT-like contrast was found to be comparable to conventional CT. • sUTE imaging of the spine can help reduce examination times and radiation exposure.

Deep learning-based acceleration of Compressed Sense MR imaging of the ankle.

OBJECTIVES: To evaluate a compressed sensing artificial intelligence framework (CSAI) to accelerate MRI acquisition of the ankle. METHODS: Thirty patients were scanned at 3T. Axial T2-w, coronal T1-w, and coronal/sagittal intermediate-w scans with fat saturation were acquired using compressed sensing only (12:44 min, CS), CSAI with an acceleration factor of 4.6-5.3 (6:45 min, CSAI2x), and CSAI with an acceleration factor of 6.9-7.7 (4:46 min, CSAI3x). Moreover, a high-resolution axial T2-w scan was obtained using CSAI with a similar scan duration compared to CS. Depiction and presence of abnormalities were graded. Signal-to-noise and contrast-to-noise were calculated. Wilcoxon signed-rank test and Cohen's kappa were used to compare CSAI with CS sequences. RESULTS: The correlation was perfect between CS and CSAI2x (κ = 1.0) and excellent for CS and CSAI3x (κ = 0.86-1.0). No significant differences were found for the depiction of structures between CS and CSAI2x and the same abnormalities were detected in both protocols. For CSAI3x the depiction was graded lower (p ≤ 0.001), though most abnormalities were also detected. For CSAI2x contrast-to-noise fluid/muscle was higher compared to CS (p ≤ 0.05), while no differences were found for other tissues. Signal-to-noise and contrast-to-noise were higher for CSAI3x compared to CS (p ≤ 0.05). The high - resolution axial T2-w sequence specifically improved the depiction of tendons and the tibial nerve (p ≤ 0.005). CONCLUSIONS: Acquisition times can be reduced by 47% using CSAI compared to CS without decreasing diagnostic image quality. Reducing acquisition times by 63% is feasible but should be reserved for specific patients. The depiction of specific structures is improved using a high-resolution axial T2-w CSAI scan. KEY POINTS: • Prospective study showed that CSAI enables reduction in acquisition times by 47% without decreasing diagnostic image quality. • Reducing acquisition times by 63% still produces images with an acceptable diagnostic accuracy but should be reserved for specific patients. • CSAI may be implemented to scan at a higher resolution compared to standard CS images without increasing acquisition times.

Development and evaluation of machine learning models based on X-ray radiomics for the classification and differentiation of malignant and benign bone tumors.

OBJECTIVES: To develop and validate machine learning models to distinguish between benign and malignant bone lesions and compare the performance to radiologists. METHODS: In 880 patients (age 33.1 ± 19.4 years, 395 women) diagnosed with malignant (n = 213, 24.2%) or benign (n = 667, 75.8%) primary bone tumors, preoperative radiographs were obtained, and the diagnosis was established using histopathology. Data was split 70%/15%/15% for training, validation, and internal testing. Additionally, 96 patients from another institution were obtained for external testing. Machine learning models were developed and validated using radiomic features and demographic information. The performance of each model was evaluated on the test sets for accuracy, area under the curve (AUC) from receiver operating characteristics, sensitivity, and specificity. For comparison, the external test set was evaluated by two radiology residents and two radiologists who specialized in musculoskeletal tumor imaging. RESULTS: The best machine learning model was based on an artificial neural network (ANN) combining both radiomic and demographic information achieving 80% and 75% accuracy at 75% and 90% sensitivity with 0.79 and 0.90 AUC on the internal and external test set, respectively. In comparison, the radiology residents achieved 71% and 65% accuracy at 61% and 35% sensitivity while the radiologists specialized in musculoskeletal tumor imaging achieved an 84% and 83% accuracy at 90% and 81% sensitivity, respectively. CONCLUSIONS: An ANN combining radiomic features and demographic information showed the best performance in distinguishing between benign and malignant bone lesions. The model showed lower accuracy compared to specialized radiologists, while accuracy was higher or similar compared to residents. KEY POINTS: • The developed machine learning model could differentiate benign from malignant bone tumors using radiography with an AUC of 0.90 on the external test set. • Machine learning models that used radiomic features or demographic information alone performed worse than those that used both radiomic features and demographic information as input, highlighting the importance of building comprehensive machine learning models. • An artificial neural network that combined both radiomic and demographic information achieved the best performance and its performance was compared to radiology readers on an external test set.

Multitask Deep Learning for Segmentation and Classification of Primary Bone Tumors on Radiographs.

Background An artificial intelligence model that assesses primary bone tumors on radiographs may assist in the diagnostic workflow. Purpose To develop a multitask deep learning (DL) model for simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. Materials and Methods This retrospective study analyzed bone tumors on radiographs acquired prior to treatment and obtained from patient data from January 2000 to June 2020. Benign or malignant bone tumors were diagnosed in all patients by using the histopathologic findings as the reference standard. By using split-sample validation, 70% of the patients were assigned to the training set, 15% were assigned to the validation set, and 15% were assigned to the test set. The final performance was evaluated on an external test set by using geographic validation, with accuracy, sensitivity, specificity, and 95% CIs being used for classification, the intersection over union (IoU) being used for bounding box placements, and the Dice score being used for segmentations. Results Radiographs from 934 patients (mean age, 33 years ± 19 [standard deviation]; 419 women) were evaluated in the internal data set, which included 667 benign bone tumors and 267 malignant bone tumors. Six hundred fifty-four patients were in the training set, 140 were in the validation set, and 140 were in the test set. One hundred eleven patients were in the external test set. The multitask DL model achieved 80.2% (89 of 111; 95% CI: 72.8, 87.6) accuracy, 62.9% (22 of 35; 95% CI: 47, 79) sensitivity, and 88.2% (67 of 76; CI: 81, 96) specificity in the classification of bone tumors as malignant or benign. The model achieved an IoU of 0.52 ± 0.34 for bounding box placements and a mean Dice score of 0.60 ± 0.37 for segmentations. The model accuracy was higher than that of two radiologic residents (71.2% and 64.9%; P = .002 and P < .001, respectively) and was comparable with that of two musculoskeletal fellowship-trained radiologists (83.8% and 82.9%; P = .13 and P = .25, respectively) in classifying a tumor as malignant or benign. Conclusion The developed multitask deep learning model allowed for accurate and simultaneous bounding box placement, segmentation, and classification of primary bone tumors on radiographs. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Carrino in this issue.

Prognostic Assessment in High-Grade Soft-Tissue Sarcoma Patients: A Comparison of Semantic Image Analysis and Radiomics.

BACKGROUND: In patients with soft-tissue sarcomas of the extremities, the treatment decision is currently regularly based on tumor grading and size. The imaging-based analysis may pose an alternative way to stratify patients' risk. In this work, we compared the value of MRI-based radiomics with expert-derived semantic imaging features for the prediction of overall survival (OS). METHODS: Fat-saturated T2-weighted sequences (T2FS) and contrast-enhanced T1-weighted fat-saturated (T1FSGd) sequences were collected from two independent retrospective cohorts (training: 108 patients; testing: 71 patients). After preprocessing, 105 radiomic features were extracted. Semantic imaging features were determined by three independent radiologists. Three machine learning techniques (elastic net regression (ENR), least absolute shrinkage and selection operator, and random survival forest) were compared to predict OS. RESULTS: ENR models achieved the best predictive performance. Histologies and clinical staging differed significantly between both cohorts. The semantic prognostic model achieved a predictive performance with a C-index of 0.58 within the test set. This was worse compared to a clinical staging system (C-index: 0.61) and the radiomic models (C-indices: T1FSGd: 0.64, T2FS: 0.63). Both radiomic models achieved significant patient stratification. CONCLUSIONS: T2FS and T1FSGd-based radiomic models outperformed semantic imaging features for prognostic assessment.

Patients with Type 2 Diabetes Exhibit a More Mineralized Deep Cartilage Layer Compared with Nondiabetic Controls: A Pilot Study.

OBJECTIVE: To assess differences in biochemical composition of the deep cartilage layer in subjects with type 2 diabetes mellitus (T2DM) and nondiabetic controls using UTE (ultra-short echo time) T2* mapping and to investigate the association of vascular health and UTE T2* measurements. DESIGN: Ten subjects with T2DM matched for age, sex, and body mass index with 10 nondiabetic controls. A 3D UTE sequence with 6 echo times was acquired using 3T magnetic resonance imaging of the knee. For UTE T2* analysis, the deep cartilage layer was segmented and analyzed in 5 compartments (patella, medial, and lateral femur and tibia). The ankle brachial index (ABI) was obtained in all subjects. Linear regression analyses were used to assess associations of T2DM and UTE T2* relaxation times and the associations of ABI measurements and UTE measurements. RESULTS: Compared with nondiabetic controls, T2DM subjects had significantly lower mean T2*-UTE in the patella (mean difference 4.87 ms; 95% confidence interval [CI] 1.09-8.65; P = 0.015), the lateral tibia (mean difference 2.26 ms; 95% CI 0.06-4.45; P = 0.045), and the lateral femur (mean difference 4.96 ms; 95% CI 0.19-9.73; P = 0.043). Independent of diabetic status, subjects with higher ABI values, indicating better vascular health, had higher T2*-UTE of the patella (coefficient 15.2; 95% CI 3.3-21.4; P = 0.017), the medial tibia (coefficient 9.8; 95% CI 1.0-18.6; P = 0.031), and the lateral femur (coefficient 18.8; 95% CI 3.3-34.3; P = 0.021). CONCLUSIONS: T2*-UTE measurements of the deep cartilage layer were consistently lower in subjects with T2DM and in subjects with impaired vascular health, likely indicating increased mineralization of this layer.

Meniscal Root Tears and Extrusion Are Significantly Associated with the Development of Accelerated Knee Osteoarthritis: Data from the Osteoarthritis Initiative.

OBJECTIVE: To identify joint structural risk factors, measured using quantitative compositional and semiquantitative magnetic resonance imaging (MRI) scoring, associated with the development of accelerated knee osteoarthritis (AKOA) compared with a more normal rate of knee osteoarthritis (OA) development. DESIGN: From the Osteoarthritis Initiative we selected knees with no radiographic OA (Kellgren-Lawrence grade [KL] 0/1) that developed advanced-stage OA (KL 3/4; AKOA) within a 4-year timeframe and a comparison group with a more normal rate of OA development (KL 0/1 to KL 2 in 4 years). MRIs at the beginning of the 4-year timeframe were assessed for cartilage T2 values and structural abnormalities using a modified Whole-Organ Magnetic Resonance Imaging Score (WORMS). Associations of MRI findings with AKOA versus normal OA were assessed using multivariable logistic regression models. RESULTS: A total of 106 AKOA and 168 subjects with normal OA development were included. Mean cartilage T2 values were not significantly associated with AKOA (odds ratio [OR] 1.06; 95% confidence interval [CI] 0.82-1.36). Risk factors for AKOA development included higher meniscus maximum scores (OR 1.37; 95% CI 1.11-1.68), presence of meniscal extrusion (OR 6.30; 95% CI 2.57-15.49), presence of root tears (OR 4.64; 95% CI 1.61-13.34), and higher medial tibia cartilage lesion scores (OR 1.96; 95% CI 1.19-3.24). CONCLUSIONS: We identified meniscal damage, especially meniscal extrusion and meniscal root tears as risk factors for AKOA development. These findings contribute to identifying subjects at risk of AKOA at an early stage when preventative measures targeting modifiable risk factors such as meniscal repair surgery could still be effective.

Determining a Threshold of Medial Meniscal Extrusion for Prediction of Knee Pain and Cartilage Damage Progression Over 4 Years: Data From the Osteoarthritis Initiative.

BACKGROUND. The extent of medial meniscal extrusion (MME) that is associated with structural and symptomatic progression of knee osteoarthritis has not been defined yet. OBJECTIVE. The purpose of our study was to investigate MRI-based thresholds of MME that are associated with structural progression of knee degenerative disease and symptoms over a period of 4 years. METHODS. We studied 328 knees of 235 participants that were randomly selected from the Osteoarthritis Initiative cohort. MME was quantified on coronal sections of intermediate-weighted MRI sequences obtained at 3 T. Knee pain and cartilage abnormalities were measured using the Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) pain scale and the cartilage whole-organ MRI score (WORMS). General estimating equations with logistic regression models were used to correlate baseline MME and changes in pain (WOMAC) and cartilage damage (WORMS). ROC analyses were performed to determine the area under the ROC curve (AUROC). Individual thresholds were determined by maximizing the product of sensitivity and specificity. RESULTS. The AUROC for predicting progression of knee pain, medial compartment cartilage damage, and medial tibial cartilage damage were 0.71, 0.70, and 0.72, respectively, and the individual thresholds for MME were 2.5, 2.7, and 2.8 mm. A single threshold of 2.5 mm was determined by maximizing the mean of the product of sensitivity and specificity of the three outcome variables (knee pain progression, medial compartmental cartilage damage progression, and medial tibial cartilage damage progression). CONCLUSION. MME was associated with knee pain and cartilage damage progression over 4 years. A single threshold of 2.5 mm was found to be the most useful threshold for predicting knee pain, medial compartment cartilage damage progression, and tibial cartilage damage progression over 4 years. CLINICAL IMPACT. This threshold could be used to standardize the diagnostic criterion of extrusion and to better characterize the risk for subsequent structural and symptomatic progression of knee osteoarthritis.

Investigating the Association of Metabolic Biomarkers With Knee Cartilage Composition and Structural Abnormalities Using MRI: A Pilot Study.

OBJECTIVE: The goal of this study was to explore the metabolic syndrome-associated phenotype of osteoarthritis by investigating the cross-sectional associations of glycemic markers and serum lipids with knee cartilage composition and structural abnormalities in middle-aged adults. DESIGN: Twenty participants between 40 to 70 years of age with Kellgren-Lawrence score 0-1 in at least one knee were recruited at a single center. Knee cartilage composition was assessed using 3.0 T cartilage T2 and T1ρ mapping. Evaluation of structural knee abnormalities was performed using the modified Whole-Organ Magnetic Resonance Imaging Score (WORMS). Linear regression was used to assess the associations of standardized fasting glucose (FG), hemoglobin A1c (HbA1c), insulin, total cholesterol, high-density lipoprotein (HDL), low-density lipoprotein (LDL), non-HDL cholesterol, and triglycerides with cartilage T2 and T1ρ as well as WORMS subscores, adjusting for body mass index. RESULTS: Higher FG and higher HbA1c were associated with higher WORMS meniscus sum (beta coefficient 1.31 [95% confidence interval (CI): 0.57, 2.05], P = 0.002 per standard deviation [SD] increase in FG; beta coefficient 0.90 [95% CI: 0.07, 1.73], P = 0.035 per SD increase in HbA1c). Also, higher total cholesterol and higher non-HDL cholesterol were associated with higher WORMS cartilage sum (beta coefficient 0.94 [95% CI: 0.01, 1.86], P = 0.048 per SD increase in total cholesterol; beta coefficient 1.05 [95% CI: 0.14, 1.96], P = 0.03 per SD increase in non-HDL cholesterol). CONCLUSIONS: Higher FG and HbA1c were associated with increased meniscal degeneration while higher total and non-HDL cholesterol were associated with increased cartilage degeneration.

Development and Validation of a Multitask Deep Learning Model for Severity Grading of Hip Osteoarthritis Features on Radiographs.

Background A multitask deep learning model might be useful in large epidemiologic studies wherein detailed structural assessment of osteoarthritis still relies on expert radiologists' readings. The potential of such a model in clinical routine should be investigated. Purpose To develop a multitask deep learning model for grading radiographic hip osteoarthritis features on radiographs and compare its performance to that of attending-level radiologists. Materials and Methods This retrospective study analyzed hip joints seen on weight-bearing anterior-posterior pelvic radiographs from participants in the Osteoarthritis Initiative (OAI). Participants were recruited from February 2004 to May 2006 for baseline measurements, and follow-up was performed 48 months later. Femoral osteophytes (FOs), acetabular osteophytes (AOs), and joint-space narrowing (JSN) were graded as absent, mild, moderate, or severe according to the Osteoarthritis Research Society International atlas. Subchondral sclerosis and subchondral cysts were graded as present or absent. The participants were split at 80% (n = 3494), 10% (n = 437), and 10% (n = 437) by using split-sample validation into training, validation, and testing sets, respectively. The multitask neural network was based on DenseNet-161, a shared convolutional features extractor trained with multitask loss function. Model performance was evaluated in the internal test set from the OAI and in an external test set by using temporal and geographic validation consisting of routine clinical radiographs. Results A total of 4368 participants (mean age, 61.0 years ± 9.2 [standard deviation]; 2538 women) were evaluated (15 364 hip joints on 7738 weight-bearing anterior-posterior pelvic radiographs). The accuracy of the model for assessing these five features was 86.7% (1333 of 1538) for FOs, 69.9% (1075 of 1538) for AOs, 81.7% (1257 of 1538) for JSN, 95.8% (1473 of 1538) for subchondral sclerosis, and 97.6% (1501 of 1538) for subchondral cysts in the internal test set, and 82.7% (86 of 104) for FOS, 65.4% (68 of 104) for AOs, 80.8% (84 of 104) for JSN, 88.5% (92 of 104) for subchondral sclerosis, and 91.3% (95 of 104) for subchondral cysts in the external test set. Conclusion A multitask deep learning model is a feasible approach to reliably assess radiographic features of hip osteoarthritis. © RSNA, 2020 Online supplemental material is available for this article.

Diagnostic Performance of CT-Guided Bone Biopsies in Patients with Suspected Osteomyelitis of the Appendicular and Axial Skeleton with a Focus on Clinical and Technical Factors Associated with Positive Microbiology Culture Results.

PURPOSE: To assess diagnostic performance of CT-guided percutaneous needle bone biopsy (CTNBB) in patients with suspected osteomyelitis and analyze whether certain clinical or technical factors were associated with positive microbiology results. MATERIALS AND METHODS: All CTNBBs performed in a single center for suspected osteomyelitis of the appendicular and axial skeleton during 2003-2018 were retrospectively reviewed. Specific inclusion criteria were clinical and radiologic suspicion of osteomyelitis. Standard of reference was defined using outcome of surgical histopathology and microbiology culture and clinical and imaging follow-up. Technical and clinical data (needle size, comorbidities, clinical factors, laboratory values, blood cultures) were collected. Logistic regression was performed to assess associations between technical and clinical data and microbiology biopsy outcome. RESULTS: A total of 142 CTNBBs were included (46.5% female patients; age ± SD 46.10 y ± 22.8), 72 (50.7%) from the appendicular skeleton and 70 (49.3%) from the axial skeleton. CTNBB showed a sensitivity of 42.5% (95% confidence interval [CI], 32.0%-53.6%) in isolating the causative pathogen. A higher rate of positive microbiology results was found in patients with intravenous drug use (odds ratio [OR] = 5.15; 95% CI, 1.2-21.0; P = .022) and elevated white blood cell count ≥ 10 × 109/L (OR = 3.9; 95% CI, 1.62-9.53; P = .002). Fever (≥ 38°C) was another clinical factor associated with positive microbiology results (OR = 3.6; 95% CI, 1.3-9.6; P = .011). CONCLUSIONS: CTNBB had a low sensitivity of 42.5% for isolating the causative pathogen. Rate of positive microbiology samples was significantly higher in patients with IV drug use, elevated white blood cell count, and fever.

Cartilage degeneration post-meniscectomy performed for degenerative disease versus trauma: data from the Osteoarthritis Initiative.

OBJECTIVE: To compare the extent of cartilage deterioration in knees with prior meniscal resection related to trauma versus knees with resection related to degenerative disease, and to compare cartilage deterioration in knees with meniscal surgery to knees without meniscal surgery, controlling for prior knee trauma. MATERIALS AND METHODS: In this cross-sectional study, we assessed cartilage deterioration in right knees of Osteoarthritis Initiative participants: (i) with meniscal surgery due to injury (n = 79); (ii) matched control knees with a prior injury but without meniscal surgery (n = 79); (iii) with meniscal surgery but without preceding injury (n = 36); and (iv) matched control knees without meniscal surgery or prior knee injury (n = 36). Cartilage composition was measured using T2 measurements derived using semi-automatic cartilage segmentation of the right. Linear regression analysis was used to compare compartmental values of T2 between groups. RESULTS: Comparing the mean T2 values in surgical cases with and without injury our results did not show significant differences (group i vs. iii, p > 0.05). However, knees with previous meniscal surgery showed significantly (p < 0.001) higher mean T2 values across all compartments (i.e., global T2) when compared to those without meniscal surgery for both knees with a history of trauma (group i vs. ii) and knees without prior trauma (group iii vs. iv). Similar results were obtained when analyzing the compartments separately. CONCLUSIONS: Cartilage deterioration, assessed by T2, is similar in knees undergoing meniscal surgery after trauma and for degenerative conditions. Both groups demonstrated greater cartilage deterioration than nonsurgical knees, controlling for prior knee injury.

Postoperative MRI Findings and Associated Pain Changes After Arthroscopic Surgery for Femoroacetabular Impingement.

OBJECTIVE. The purpose of this study is to describe postoperative MRI findings after femoroacetabular impingement surgery in correlation with pain changes and surgical findings. SUBJECTS AND METHODS. We prospectively enrolled 42 patients (43 hips) who were scheduled for FAI surgery. Pre- and postoperative MR images were obtained using a 3-T MRI system. Changes in pain scores were assessed using the hip dysfunction and osteoarthritis outcome score. MR images were evaluated for the presence of acetabuloplasty or femoroplasty, presence of chondral and labral repair surgery, bone marrow edema, subchondral cysts, chondral defects, labral tears, capsular defects, and effusion. The optimal orientation to detect these changes was noted. Imaging findings were compared with pain score changes using linear regression analysis. Sensitivity and specificity were assessed using surgical correlation as the reference standard. RESULTS. Increased acetabular bony débridement length was associated with decreased improvement in pain scores (coefficient, -2.07; 95% CI, -3.53 to -0.62; p = 0.008), whereas other imaging findings were not significantly different. Femoroplasty and capsular alterations were best detected on oblique axial sequences; acetabuloplasty and cartilage and labral repair were best seen on sagittal sequences. MRI showed excellent sensitivity (100%) and specificity (100%) for detecting labral repair and excellent sensitivity for detecting femoroplasty (98%). Sensitivity and specificity were lower for detecting acetabuloplasty (83% and 80%, respectively) and chondral repair (75% and 54%, respectively). CONCLUSION. Arthroscopic acetabuloplasty showed a greater association with postoperative pain than did other aspects of surgical correction for femoroacetabular impingement. Femoroplasty and labral repair were reliably diagnosed on 3-T MRI; however, limitations were found in the evaluation of acetabular chondral repair.

Factors associated with bone microstructural alterations assessed by HR-pQCT in long-term HIV-infected individuals.

PURPOSE: In adults with long-term HIV infection, low bone density and increased fracture risk have emerged as significant comorbidities. Our aim was to assess the association of exercise, nutrition, and medications with bone quality in adults with long-term HIV infection. METHODS: Forty-three adults with HIV infection were enrolled (median BMI 25.7, range 18.2-35.6 kg/m2; median age 57, range 50-69 years). Participants underwent ultradistal radius and tibia high-resolution peripheral quantitative CT (HR-pQCT). Questionnaires included the revised Community Healthy Activities Model Program for Seniors (CHAMPS), the Mini Nutritional Assessment (MNA) as well as medication assessments. Multivariable linear regression models were used to evaluate the association of exercise, nutritional status, tenofovir disoproxil fumarate (TDF) and protease inhibitor (PI) use with bone density and microstructure, adjusting for demographic risk factors. RESULTS: In regression models, higher nutrition scores were associated with higher tibia cortical thickness (R2 = 0.23; ß = 0.03; p = 0.044) and higher radius cortical BMD (R2 = 0.43; ß = 8.4; p = 0.026). Higher weekly frequency of all physical activities was significantly associated with higher radius trabecular BMD (R2 = 0.38; ß = 0.96; p = 0.050), higher radius trabecular number (R2 = 0.31; ß = 0.01; p = 0.026), lower tibia and radius trabecular separation (tibia: R2 = 0.30; ß = -0.003; p = 0.038; radius: R2 = 0.35; ß = -0.003; p = 0.021), and higher radius bone stiffness (R2 = 0.45; ß = 0.38; p = 0.047). Higher frequency of bone loading physical activities was significantly associated with higher tibia trabecular density (R2 = 0.44; ß = 4.06; p = 0.036), higher tibia bone stiffness (R2 = 0.46; ß = 3.06; p = 0.050), and higher tibia estimated failure load (R2 = 0.46; ß = 0.17; p = 0.049). TDF used in combination with a PI was associated with lower radius trabecular BMD (R2 = 0.39; ß = -41.2; p = 0.042), lower radius trabecular number (R2 = 0.34; ß = -0.44; p = 0.009) and greater radius trabecular separation (R2 = 0.42; ß = 0.16; p = 0.002), while TDF use without a PI was not associated with reduced bone quality. CONCLUSIONS: In adults with HIV infection, malnutrition is associated with poor cortical bone quality, while reduced frequency of physical activities and specifically reduced frequency of mechanical loading activities are associated with deficient trabecular bone structure and reduced estimates of bone strength. TDF use in combination with a PI is associated with deleterious effects on trabecular bone structure.

[18 F]-Sodium Fluoride PET/MR Imaging for Bone-Cartilage Interactions in Hip Osteoarthritis: A Feasibility Study.

This study characterized the distribution of [18 F]-sodium fluoride (NaF) uptake and blood flow in the femur and acetabulum in hip osteoarthritis (OA) patients to find associations between bone remodeling and cartilage composition in the presence of morphological abnormalities using simultaneous positron emission tomography and magnetic resonance imaging (PET/MR), quantitative magnetic resonance imaging (MRI) and femur shape modeling. Ten patients underwent a [18 F]-NaF PET/MR dynamic scan of the hip simultaneously with: (i) fast spin-echo CUBE for morphology grading and (ii) T1ρ /T2 magnetization-prepared angle-modulated partitioned k-space spoiled gradient echo snapshots for cartilage, bone segmentation, bone shape modeling, and T1ρ /T2 quantification. The standardized uptake values (SUVs) and Patlak kinetic parameter (Kpat ) were calculated for each patient as PET outcomes, using an automated post-processing pipeline. Shape modeling was performed to extract the variations in bone shapes in the patients. Pearson's correlation coefficients were used to study the associations between bone shapes, PET outcomes, and patient reported pain. Direct associations between quantitative MR and PET evidence of bone remodeling were established in the acetabulum and femur. Associations of shaft thickness with SUV in the femur (p = 0.07) and Kpat in the acetabulum (p = 0.02), cam deformity with acetabular score (p = 0.09), osteophytic growth on the femur head with Kpat (p = 0.01) were observed. Pain had increased correlations with SUV in the acetabulum (p = 0.14) and femur (p = 0.09) when shaft thickness was accounted for. This study demonstrated the ability of [18 F]-NaF PET-MRI, 3D shape modeling, and quantitative MRI to investigate cartilage-bone interactions and bone shape features in hip OA, providing potential investigative tools to diagnose OA. © 2019 The Authors. Journal of Orthopaedic Research® published by Wiley Periodicals, Inc. on behalf of Orthopaedic Research Society J Orthop Res 37:2671-2680, 2019.