Assessment of the sacroiliac joint in patients with axial spondyloarthritis via three-dimensional ultrashort echo time magnetic resonance imaging.

Background: Bone erosion in the sacroiliac joint (SIJ) is highly specific for the diagnosis of axial spondyloarthritis (axSpA) and may indicate early disease progression. The 3D ultrashort echo time (3D-UTE) technique excels in providing clear contrast between the articular cartilage and the bone cortex interface. Additionally, it is emerging as a promising quantitative tool for detecting early cartilage changes. Therefore, this study aimed to evaluate the diagnostic performance of 3D-UTE sequences in identifying bone erosion in the SIJ of patients with axSpA and to clarify the potential of cartilage T2* values as a quantitative biomarker for axSpA. Methods: This prospective study employed convenience and consecutive sampling methods to recruit patients diagnosed with axSpA in Peking University Third Hospital who met the Assessment of Spondyloarthritis International Society (ASAS) criteria and also an equal number of healthy volunteers. After providing informed consent, all participants underwent 3D-UTE sequences and conventional T2* mapping of the SIJs. Two radiologists separately interpreted the bone erosion of each SIJ on 3D-UTE sequences. Erosion detection of SIJs via computed tomography (CT) served as the standard of reference. The T2* values of the cartilage were measured and compared, and the diagnostic efficacy of the T2* value for axSpA diagnosis was evaluated. Results: A total of 32 patients and 32 healthy volunteers were included. The 3D-UTE sequence, as separately assessed by two reviewers in terms of its ability to detect erosions, exhibited a notable level of accuracy. For the two reviewers, the respective diagnostic sensitivities were 94.7% and 92.9%, the specificities were 97.4% and 96.5%, positive predictive values were 96.7% and 95.4%, the negative predictive values were 95.9% and 94.5%, the accuracies were 96.2% and 94.9%, and the areas under the curve (AUCs) were 96.1% and 94.7%. For the detection of erosions, the interreader κ value was 0.949. The T2* values of the SIJ cartilage were significantly higher in patients with axSpA than in healthy volunteers. The intraobserver intraclass correlation coefficients (ICCs) for T2* measurements ranged between 80.5% and 82.2%. Meanwhile, the interobserver ICCs for UTE-T2* and gradient echo T2* measurements were 81.5% and 80.8%, respectively. The AUCs of the UTE-T2* values for discriminating patients with axSpA from the healthy volunteers of the two readers were 73.3% and 71.6%, respectively. Conclusions: 3D-UTE sequences can be used as a reliable morphological imaging technique for detecting bone erosion in the SIJ. Additionally, UTE-T2* values of the cartilage may offer a quantitative method for identifying patients with axSpA.

A matched case-control study of early cervical spondylotic myelopathy based on diffusion magnetic resonance imaging.

BACKGROUND: Early cervical spondylotic myelopathy (CSM) is challenging to diagnose and easily missed. Diffusion MRI (dMRI) has the potential to identify early CSM. METHODS: Using diffusion tensor imaging (DTI), diffusion kurtosis imaging (DKI), and neurite orientation dispersion and density imaging (NODDI), a 1:1 matched case-control study was conducted to evaluate the potential of dMRI in identifying early CSM and assessing uncompressed segments of CSM patients. CSM patients and volunteers were matched by age and spinal location. The differences in dMRI parameters between groups were assessed by the paired t-test, the multicollinearity of the dMRI parameters was evaluated by the variance inflation factor (VIF), and the value of dMRI parameters in distinguishing controls from CSM patients was determined by logistic regression. The univariate t-test was used to analyse differences between CSM patients and volunteers in adjacent uncompressed areas. RESULTS: In total, 56 CSM patients and 56 control volunteers were included. Paired t-tests revealed significant differences in nine dMRI parameters between groups. Multicollinearity calculated through VIF and combined with logistic regression showed that the orientation division index (ODI) was significantly positively correlated (r = 2.12, p = 0.035), and the anisotropic water fraction (AWF) was significantly negatively correlated (r = -0.98, p = 0.015). The fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD), isotropic volume fraction (ISOVF), ODI, and AWF were significantly different in the upper and lower uncompressed areas at all ages. CONCLUSION: dMRI can noninvasively identify early CSM patients and potentially identify the extent of CSM lesions involving the cervical spinal cord. CRITICAL RELEVANCE STATEMENT: Diffusion MRI (dMRI) can identify early cervical spondylotic myelopathy (CSM) and has the potential to help determine the extent of CSM involvement. The application of dMRI can help screen for early CSM and develop clinical surgical and rehabilitation treatment plans. KEY POINTS: • Diffusion MRI can differentiate between normal and early-stage cervical spondylotic myelopathy patients. • Diffusion MRI has the ability to identify the extent of spinal cord involvement in cervical spondylotic myelopathy. • Diffusion MRI enables the early screening of cervical spondylotic myelopathy and helps guide clinical treatment.

A Deep Learning Model Enhances Clinicians' Diagnostic Accuracy to More Than 96% for Anterior Cruciate Ligament Ruptures on Magnetic Resonance Imaging.

PURPOSE: To develop a deep learning model to accurately detect anterior cruciate ligament (ACL) ruptures on magnetic resonance imaging (MRI) and to evaluate its effect on the diagnostic accuracy and efficiency of clinicians. METHODS: A training dataset was built from MRIs acquired from January 2017 to June 2021, including patients with knee symptoms, irrespective of ACL ruptures. An external validation dataset was built from MRIs acquired from January 2021 to June 2022, including patients who underwent knee arthroscopy or arthroplasty. Patients with fractures or prior knee surgeries were excluded in both datasets. Subsequently, a deep learning model was developed and validated using these datasets. Clinicians of varying expertise levels in sports medicine and radiology were recruited, and their capacities in diagnosing ACL injuries in terms of accuracy and diagnosing time were evaluated both with and without artificial intelligence (AI) assistance. RESULTS: A deep learning model was developed based on the training dataset of 22,767 MRIs from 5 centers and verified with external validation dataset of 4,086 MRIs from 6 centers. The model achieved an area under the receiver operating characteristic curve of 0.987 and a sensitivity and specificity of 95.1%. Thirty-eight clinicians from 25 centers were recruited to diagnose 3,800 MRIs. The AI assistance significantly improved the accuracy of all clinicians, exceeding 96%. Additionally, a notable reduction in diagnostic time was observed. The most significant improvements in accuracy and time efficiency were observed in the trainee groups, suggesting that AI support is particularly beneficial for clinicians with moderately limited diagnostic expertise. CONCLUSIONS: This deep learning model demonstrated expert-level diagnostic performance for ACL ruptures, serving as a valuable tool to assist clinicians of various specialties and experience levels in making accurate and efficient diagnoses. LEVEL OF EVIDENCE: Level III, retrospective comparative case series.

Predictive Value of the Diffusion Magnetic Resonance Imaging Technique for the Postoperative Outcome of Cervical Spondylotic Myelopathy.

BACKGROUND: Diffusion magnetic resonsance imaging (dMRI) can potentially predict the postoperative outcome of cervical spondylotic myelopathy (CSM). PURPOSE: To explore preoperative dMRI parameters to predict the postoperative outcome of CSM through multifactor correlation analysis. STUDY TYPE: Prospective. POPULATION: Post-surgery CSM patients; 102 total, 73 male (52.42 ± 10.60 years old) and 29 female (52.0 ± 11.45 years old). FIELD STRENGTH/SEQUENCE: 3.0 T/Turbo spin echo T1/T2-weighted, T2*-weighted multiecho gradient echo and dMRI. ASSESSMENT: Spinal cord function was evaluated using modified Japanese Orthopedic Association (mJOA) scoring at different time points: preoperative and 3, 6, and 12 months postoperative. Single-factor correlation and t test analyses were conducted based on fractional anisotropy (FA), mean diffusivity, intracellular volume fraction, isotropic volume fraction, orientation division index, increased signal intensity, compression ratio, age, sex, symptom duration and operation method, and multicollinearity was calculated. The linear quantile mixed model (LQMM) and the linear mixed-effects regression model (LMER) were used for multifactor correlation analysis using the combinations of the above variables. STATISTICAL TESTS: Distance correlation, Pearson's correlation, multiscale graph correlation and t tests were used for the single-factor correlation analyses. The variance inflation factor (VIF) was used to calculate multicollinearity. LQMM and LMER were used for multifactor correlation analyses. P < 0.05 was considered statistically significant. RESULTS: The single-factor correlation between all variables and the postoperative mJOA score was weak (all r < 0.3). The linear relationship was stronger than the nonlinear relationship, and there was no significant multicollinearity (VIF = 1.10-1.94). FA values in the LQMM and LMER models had a significant positive correlation with the mJOA score (r = 5.27-6.04), which was stronger than the other variables. DATA CONCLUSION: The FA value based on dMRI significantly positively correlated with CSM patient postoperative outcomes, helping to predict the surgical outcome and formulate a treatment plan before surgery. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 2.

Preliminary exploration of deep learning-assisted recognition of superior labrum anterior and posterior lesions in shoulder MR arthrography.

PURPOSE: MR arthrography (MRA) is the most accurate method for preoperatively diagnosing superior labrum anterior-posterior (SLAP) lesions, but diagnostic results can vary considerably due to factors such as experience. In this study, deep learning was used to facilitate the preliminary identification of SLAP lesions and compared with radiologists of different seniority. METHODS: MRA data from 636 patients were retrospectively collected, and all patients were classified as having/not having SLAP lesions according to shoulder arthroscopy. The SLAP-Net model was built and tested on 514 patients (dataset 1) and independently tested on data from two other MRI devices (122 patients, dataset 2). Manual diagnosis was performed by three radiologists with different seniority levels and compared with SLAP-Net outputs. Model performance was evaluated by the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), etc. McNemar's test was used to compare performance among models and between radiologists' models. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 was considered statistically significant. RESULTS: SLAP-Net had AUC = 0.98 and accuracy = 0.96 for classification in dataset 1 and AUC = 0.92 and accuracy = 0.85 in dataset 2. In dataset 1, SLAP-Net had diagnostic performance similar to that of senior radiologists (p = 0.055) but higher than that of early- and mid-career radiologists (p = 0.025 and 0.011). In dataset 2, SLAP-Net had similar diagnostic performance to radiologists of all three seniority levels (p = 0.468, 0.289, and 0.495, respectively). CONCLUSIONS: Deep learning can be used to identify SLAP lesions upon initial MR arthrography examination. SLAP-Net performs comparably to senior radiologists.

Feasibility and safety of one-stage sacral laminoplasty with autologous sacral laminar reimplantation fixed by absorbable fixation clamps in direct microsurgical treatment of symptomatic sacral extradural spinal meningeal cysts.

Introduction: Sacral laminoplasty with titanium mesh and titanium screws can reduce symptomatic sacral extradural spinal meningeal cysts (SESMCs) recurrence and operation complications. However, due to a defect or thinning of the sacrum, the screws cannot be securely anchored and there are also problems with permanent metal implantation for titanium mesh and screws. We propose that sacral laminoplasty with absorbable clamps can provide rigid fixation even for a thinned or defected sacrum without leaving permanent metal implants. Methods: In the direct microsurgical treatment of symptomatic SESMCs, we performed one-stage sacral laminoplasty with autologous sacral lamina reimplantation fixed by absorbable fixation clamps. Retrospectively, we analyzed intraoperative handling, planarity of the sacral lamina, and stability of the fixation based on clinical and radiological data. Results: Between November 2021 to October 2022, we performed sacral laminoplasty with the absorbable craniofix system in 28 consecutive patients with SESMCs. The size of the sacral lamina flaps ranged from 756 to 1,052 mm2 (average 906.21 ± 84.04 mm2). We applied a minimum of two (in four cases) and up to four (in four cases) Craniofix clamps in the operation, with three (in 20 cases) being the most common (82.14%, 20/28) and convenient to handle. Excellent sacral canal reconstruction could be confirmed intraoperatively by the surgeons and postoperatively by CT scans. No intraoperative complications occurred. Conclusions: One-stage sacral laminoplasty with absorbable fixation clamps is technically feasible, and applying 3 of these can achieve a stable fixation effect and are easy to operate. Restoring the normal structure of the sacral canal could reduce complications and improve surgical efficacy.

Perioperative cerebral blood flow measured by arterial spin labeling with different postlabeling delay in patients undergoing carotid endarterectomy: a comparison study with CT perfusion.

Background: Arterial spin labeling (ASL) is a non-invasive technique for measuring cerebral perfusion. Its accuracy is affected by the arterial transit time. This study aimed to (1) evaluate the accuracy of ASL in measuring the cerebral perfusion of patients who underwent carotid endarterectomy (CEA) and (2) determine a better postlabeling delay (PLD) for pre- and postoperative perfusion imaging between 1.5 and 2.0 s. Methods: A total of 24 patients scheduled for CEA due to severe carotid stenosis were included in this study. All patients underwent ASL with two PLDs (1.5 and 2.0 s) and computed tomography perfusion (CTP) before and after surgery. Cerebral blood flow (CBF) values were measured on the registered CBF images of ASL and CTP. The correlation in measuring perioperative relative CBF (rCBF) and difference ratio of CBF (DRCBF) between ASL with PLD of 1.5 s (ASL1.5) or 2.0 s (ASL2.0) and CTP were also determined. Results: There were no significant statistical differences in preoperative rCBF measurements between ASL1.5 and CTP (p = 0.17) and between ASL2.0 and CTP (p = 0.42). Similarly, no significant differences were found in rCBF between ASL1.5 and CTP (p = 0.59) and between ASL2.0 and CTP (p = 0.93) after CEA. The DRCBF measured by CTP was found to be marginally lower than that measured by ASL2.0_1.5 (p = 0.06) and significantly lower than that measured by ASL1.5_1.5 (p = 0.01), ASL2.0_2.0 (p = 0.03), and ASL1.5_2.0 (p = 0.007). There was a strong correlation in measuring perioperative rCBF and DRCBF between ASL and CTP (r = 0.67-0.85, p < 0.001). Using CTP as the reference standard, smaller bias can be achieved in measuring rCBF by ASL2.0 (-0.02) than ASL1.5 (-0.07) before CEA. In addition, the same bias (0.03) was obtained by ASL2.0 and ASL1.5 after CEA. The bias of ASL2.0_2.0 (0.31) and ASL2.0_1.5 (0.32) on DRCBF measurement was similar, and both were smaller than that of ASL1.5_1.5 (0.60) and ASL1.5_2.0 (0.60). Conclusion: Strong correlation can be found in assessing perioperative cerebral perfusion between ASL and CTP. During perioperative ASL imaging, the PLD of 2.0 s is better than 1.5 s for preoperative scan, and both 1.5 and 2.0 s are suitable for postoperative scan.

MRI feature-based radiomics models to predict treatment outcome after stereotactic body radiotherapy for spinal metastases.

OBJECTIVE: This study aimed to extract radiomics features from MRI using machine learning (ML) algorithms and integrate them with clinical features to build response prediction models for patients with spinal metastases undergoing stereotactic body radiotherapy (SBRT). METHODS: Patients with spinal metastases who were treated using SBRT at our hospital between July 2018 and April 2023 were recruited. We assessed their response to treatment using the revised Response Evaluation Criteria in Solid Tumors (version 1.1). The lesions were categorized into progressive disease (PD) and non-PD groups. Radiomics features were extracted from T1-weighted image (T1WI), T2-weighted image (T2WI), and fat-suppression T2WI sequences. Feature selection involved intraclass correlation coefficients, minimal-redundancy-maximal-relevance, and least absolute shrinkage and selection operator methods. Thirteen ML algorithms were employed to construct the radiomics prediction models. Clinical, conventional imaging, and radiomics features were integrated to develop combined models. Model performance was evaluated using receiver operating characteristic (ROC) curve analysis, and the clinical value was assessed using decision curve analysis. RESULTS: We included 194 patients with 142 (73.2%) lesions in the non-PD group and 52 (26.8%) in the PD group. Each region of interest generated 2264 features. The clinical model exhibited a moderate predictive value (area under the ROC curve, AUC = 0.733), while the radiomics models demonstrated better performance (AUC = 0.745-0.825). The combined model achieved the best performance (AUC = 0.828). CONCLUSION: The MRI-based radiomics models exhibited valuable predictive capability for treatment outcomes in patients with spinal metastases undergoing SBRT. CRITICAL RELEVANCE STATEMENT: Radiomics prediction models have the potential to contribute to clinical decision-making and improve the prognosis of patients with spinal metastases undergoing SBRT. KEY POINTS: • Stereotactic body radiotherapy effectively delivers high doses of radiation to treat spinal metastases. • Accurate prediction of treatment outcomes has crucial clinical significance. • MRI-based radiomics models demonstrated good performance to predict treatment outcomes.

Glenoid segmentation from computed tomography scans based on a 2-stage deep learning model for glenoid bone loss evaluation.

BACKGROUND: The best-fitting circle drawn by computed tomography (CT) reconstruction of the en face view of the glenoid bone to measure the bone defect is widely used in clinical application. However, there are still some limitations in practical application, which can prevent the achievement of accurate measurements. This study aimed to accurately and automatically segment the glenoid from CT scans based on a 2-stage deep learning model and to quantitatively measure the glenoid bone defect. MATERIALS AND METHODS: Patients who were referred to our institution between June 2018 and February 2022 were retrospectively reviewed. The dislocation group consisted of 237 patients with a history of ≥2 unilateral shoulder dislocations within 2 years. The control group consisted of 248 individuals with no history of shoulder dislocation, shoulder developmental deformity, or other disease that may lead to abnormal morphology of the glenoid. All patients underwent CT examination with a 1-mm slice thickness and a 1-mm increment, including complete imaging of the bilateral glenoid. A residual neural network (ResNet) location model and a U-Net bone segmentation model were constructed to develop an automated segmentation model for the glenoid from CT scans. The data set was randomly divided into training (201 of 248) and test (47 of 248) data sets of control-group data and training (190 of 237) and test (47 of 237) data sets of dislocation-group data. The accuracy of the stage 1 (glenoid location) model, the mean intersection-over-union value of the stage 2 (glenoid segmentation) model, and the glenoid volume error were used to assess the performance of the model. The R2 value and Lin concordance correlation coefficient were used to assess the correlation between the prediction and the gold standard. RESULTS: A total of 73,805 images were obtained after the labeling process, and each image was composed of CT images of the glenoid and its corresponding mask. The average overall accuracy of stage 1 was 99.28%; the average mean intersection-over-union value of stage 2 was 0.96. The average glenoid volume error between the predicted and true values was 9.33%. The R2 values of the predicted and true values of glenoid volume and glenoid bone loss (GBL) were 0.87 and 0.91, respectively. The Lin concordance correlation coefficient value of the predicted and true values of glenoid volume and GBL were 0.93 and 0.95, respectively. CONCLUSION: The 2-stage model in this study showed a good performance in glenoid bone segmentation from CT scans and could quantitatively measure GBL, providing a data reference for subsequent clinical treatment.

The value of enhanced multiparameteric MRI diagnostic model for preoperatively predicting surgical methods of inferior vena cava in patients with renal tumors and inferior vena cava tumor thrombus.

BACKGROUND: Inferior vena cava tumor thrombus (IVCTT) invading the IVC wall majorly affects the surgical method choice and prognosis in renal tumors. Enhanced multiparameteric MRI plays an important role in preoperative evaluation. In this work, an MRI-based diagnostic model for IVCTT was established so as to guide the preoperative decisions. METHODS: Preoperative MR images of 165 cases of renal tumors with IVCTT were retrospectively analyzed, and imaging indicators were analyzed, including IVCTT morphology and Mayo grade, IVCTT diameter measurements, bland thrombosis, primary MRI-based diagnosis of renal tumor, and involvement of contralateral renal vein. The indicators were analyzed based on intraoperative performance and resection scope of the IVC wall. Multivariate logistic regression analysis was used to establish the diagnostic model. RESULTS: The morphological classification of the IVCTT, primary MRI-based diagnosis of renal tumors, maximum transverse diameter of IVCTT, and length of the bland thrombus were the main indexes predicting IVC wall invasion. The MRI-based diagnostic model established according to these indexes had good diagnostic efficiency. The prediction probability of 0.61 was set as the cutoff value. The area under the curve of the test set was 0.88, sensitivity was 0.79, specificity was 0.85, and prediction accuracy was 0.79 under the optimal cutoff value. CONCLUSION: The preoperative MRI-based diagnostic model could reliably predict IVC wall invasion, which is helpful for better prediction of IVC-associated surgical operations.

Refining the radiation and contrast medium dose in weight-grouped scanning protocols for coronary CT angiography.

PURPOSE: To refine the currently used, weight-grouped protocol for coronary computed tomography angiography (CCTA), in terms of the radiation and contrast medium dose, through clinical evaluation. METHODS: Following the current routine setting that varies between three weight groups (group A: 55-65 kg, group B: 66-75 kg, group C: 76-85 kg), three additional reduction protocols were proposed to each group, with different combinations of lowered tube voltage (70-100 kVp), tube current (100-220 mAs), and iodine delivery rate (0.8-1.5 gI/s). A total of 321 patients scheduled for CCTA due to suspected coronary artery disease were enrolled, who were randomly assigned to one of the four subgroups of settings under the corresponding weight group. The resulting objective image quality was compared by measuring the contrast-to-noise ratio and signal-to-noise ratio. Subjective image quality was graded by two radiologists using a 4-point Likert scale, on a total of 3848 segments. The optimal protocol for each weight group was determined with respect to the image quality and the applied radiation dose. RESULTS: For all three groups, no significant difference was noticed in objective images quality between subgroups of dose settings (all p > 0.05). The average score on subjective image quality was ≥3 for every subgroup, while the percentage of score 4 showed greater dependence on the setting, ranging from 83.2% to 91.5%, and was chosen to be the determining factor. The optimal dose settings were found to be 80 kVp, 150 mAs, and 1.0 gI/s for patients of 55-75 kg in weight, and 100 kVp, 170 mAs, and 1.5 gI/s for those of 76-85 kg. CONCLUSION: It is feasible to refine the currently used, weight-grouped protocol for CCTA in terms of radiation and contrast medium dose, by use of an optimization strategy where the balance between dose and image quality can be improved in a routine clinical setting.

Predicting the Risk of Thymic Tumors Using Texture Analysis of Contrast-Enhanced Chest Computed Tomography.

OBJECTIVE: This study aimed to explore the value of contrast-enhanced computed tomography texture features for predicting the risk of malignant thymic epithelial tumor. METHODS: Data of 97 patients with pathologically confirmed thymic epithelial tumors treated at in our hospital from March 2015 to October 2021 were retrospectively analyzed. Based on the World Health Organization classification of thymic epithelial tumors, patients were divided into a high-risk group (types B2, B3, and C; n = 45) and a low-risk group (types A, AB, and B1; n = 52). Texture analysis was performed using a first-order, gray-level histogram method. Six features were evaluated: mean, variance, skewness, kurtosis, energy, and entropy. The association between contrast-enhanced computed tomography texture features and the risk of malignancy in thymic epithelial tumors was analyzed. The predictive thresholds of predictive texture features were determined by receiver operating characteristics analysis. RESULTS: The mean, skewness, and entropy were significantly greater in the high-risk group than in the low-risk group ( P < 0.05); however, variance, kurtosis, and energy were comparable in the two groups ( P > 0.05). The area under curve of mean, skewness, and entropy was 0.670, 0.760, and 0.880, respectively. The optimal cutoff value of entropy for predicting risk of malignancy was 7.74, with sensitivity, specificity, and accuracy of 80.0%, 80.0%, and 75%, respectively. CONCLUSIONS: Contrast-enhanced computed tomography texture features, especially entropy, may be a useful tool to predict the risk of malignancy in thymic epithelial tumors.

Predictive model based on DCE-MRI and clinical features for the evaluation of pain response after stereotactic body radiotherapy in patients with spinal metastases.

OBJECTIVE: To investigate the correlation of conventional MRI, DCE-MRI and clinical features with pain response after stereotactic body radiotherapy (SBRT) in patients with spinal metastases and establish a pain response prediction model. METHODS: Patients with spinal metastases who received SBRT in our hospital from July 2018 to April 2022 consecutively were enrolled. All patients underwent conventional MRI and DCE-MRI before treatment. Pain was assessed before treatment and in the third month after treatment, and the patients were divided into pain-response and no-pain-response groups. A multivariate logistic regression model was constructed to obtain the odds ratio and 95% confidence interval (CI) for each variable. C-index was used to evaluate the model's discrimination performance. RESULTS: Overall, 112 independent spinal lesions in 89 patients were included. There were 73 (65.2%) and 39 (34.8%) lesions in the pain-response and no-pain-response groups, respectively. Multivariate analysis showed that the number of treated lesions, pretreatment pain score, Karnofsky performance status score, Bilsky grade, and the DCE-MRI quantitative parameter Ktrans were independent predictors of post-SBRT pain response in patients with spinal metastases. The discrimination performance of the prediction model was good; the C index was 0.806 (95% CI: 0.721-0.891), and the corrected C-index was 0.754. CONCLUSION: Some imaging and clinical features correlated with post-SBRT pain response in patients with spinal metastases. The model based on these characteristics has a good predictive value and can provide valuable information for clinical decision-making. KEY POINTS: • SBRT can accurately irradiate spinal metastases with ablative doses. • Predicting the post-SBRT pain response has important clinical implications. • The prediction models established based on clinical and MRI features have good performance.

Deep learning-assisted classification of calcaneofibular ligament injuries in the ankle joint.

Background: The classification of calcaneofibular ligament (CFL) injuries on magnetic resonance imaging (MRI) is time-consuming and subject to substantial interreader variability. This study explores the feasibility of classifying CFL injuries using deep learning methods by comparing them with the classifications of musculoskeletal (MSK) radiologists and further examines image cropping screening and calibration methods. Methods: The imaging data of 1,074 patients who underwent ankle arthroscopy and MRI examinations in our hospital were retrospectively analyzed. According to the arthroscopic findings, patients were divided into normal (class 0, n=475); degeneration, strain, and partial tear (class 1, n=217); and complete tear (class 2, n=382) groups. All patients were divided into training, validation, and test sets at a ratio of 8:1:1. After preprocessing, the images were cropped using Mask region-based convolutional neural network (R-CNN), followed by the application of an attention algorithm for image screening and calibration and the implementation of LeNet-5 for CFL injury classification. The diagnostic effects of the axial, coronal, and combined models were compared, and the best method was selected for outgroup validation. The diagnostic results of the models in the intragroup and outgroup test sets were compared with those results of 4 MSK radiologists of different seniorities. Results: The mean average precision (mAP) of the Mask R-CNN using the attention algorithm for the left and right image cropping of axial and coronal sequences was 0.90-0.96. The accuracy of LeNet-5 for classifying classes 0-2 was 0.92, 0.93, and 0.92, respectively, for the axial sequences and 0.89, 0.92, and 0.90, respectively, for the coronal sequences. After sequence combination, the classification accuracy for classes 0-2 was 0.95, 0.97, and 0.96, respectively. The mean accuracies of the 4 MSK radiologists in classifying the intragroup test set as classes 0-2 were 0.94, 0.91, 0.86, and 0.85, all of which were significantly different from the model. The mean accuracies of the MSK radiologists in classifying the outgroup test set as classes 0-2 were 0.92, 0.91, 0.87, and 0.85, with the 2 senior MSK radiologists demonstrating similar diagnostic performance to the model and the junior MSK radiologists demonstrating worse accuracy. Conclusions: Deep learning can be used to classify CFL injuries at similar levels to those of MSK radiologists. Adding an attention algorithm after cropping is helpful for accurately cropping CFL images.

Comparison of the diagnostic value of measurements of transverse syndesmotic interval and 'lambda sign' in distinguishing latent syndesmotic diastasis in chronic lateral ankle instability: a cross-sectional study of 188 cases.

INTRODUCTION: Chronic lateral ankle instability (CLAI) could accompany with latent syndesmotic diastasis (LSD), which is difficult to distinguish before surgery. Tibiofibular interval width and extravasation of joint fluid ('lambda sign') on MRI are widely used in the diagnosis of syndesmotic injury, but the reliability of these methods in distinguishing the associated LSD in CLAI was rarely studied. Our objective was to compare the diagnostic value of the measurement of the transverse tibiofibular interval and 'lambda sign' on MRI in distinguishing LSD in CLAI and to investigate the radiological predictor that best matched the intraoperatively measured syndesmotic width. METHODS: 138 CLAI patients undergoing arthroscopy in our institute from March 2017 to June 2020 were enrolled (CLAI group). Anterior space width (ASW) and posterior space width (PSW) at 10 mm layer above tibial articular and fluid height above tibial articular surface (FH) were measured on preoperative MRI. The same parameters were measured on MRI of 50 healthy volunteers as control group. At arthroscopy, syndesmotic width was measured and the patients were divided into arthroscopic widening (AW) and arthroscopic normal (AN) subgroup taking 2 mm as critical value. The CLAI group was compared with the control group to explore the interval changes related to CLAI. The AW and AN subgroups were compared to explore the potential diagnostic indicators and reference values for the LSD. RESULTS: All parameters showed significant difference between CLAI group and control group (p < 0.05), but only PSW (p = 0.004) showed significant difference between AW and AN subgroups other than FH (p = 0.461). Only PSW was involved in formula of multiple-factor analysis (p = 0.005; OR, 1.819; 95%CI, 1.196-2.767). ROC analysis showed critical value of PSW was 3.8 mm (sensitivity, 66%; specificity, 66%; accuracy, 66.7%), while accuracy of lambda sign was 41.3%. CONCLUSIONS: Transverse tibiofibular interval measurements were more reliable than the 'lambda sign' in distinguishing associated LSD in CLAI patients. The PSW ≥ 3.8 mm could be a predictor of syndesmotic diastasis.

Comparison of MRI and CT-based radiomics for preoperative prediction of lymph node metastasis in pancreatic ductal adenocarcinoma.

BACKGROUND: The preoperative prediction of lymph node metastasis (LNM) in pancreatic ductal adenocarcinoma (PDAC) is essential in prognosis and treatment strategy formulation. PURPOSE: To compare the performance of computed tomography (CT) and magnetic resonance imaging (MRI) radiomics models for the preoperative prediction of LNM in PDAC. MATERIAL AND METHODS: In total, 160 consecutive patients with PDAC were retrospectively included, who were divided into the training and validation sets (ratio of 8:2). Two radiologists evaluated LNM basing on morphological abnormalities. Radiomics features were extracted from T2-weighted imaging, T1-weighted imaging, and multiphase contrast enhanced MRI and multiphase CT, respectively. Overall, 1184 radiomics features were extracted from each volume of interest drawn. Only features with an intraclass correlation coefficient ≥0.75 were included. Three sequential feature selection steps-variance threshold, variance thresholding and least absolute shrinkage selection operator-were repeated 20 times with fivefold cross-validation in the training set. Two radiomics models based on multiphase CT and multiparametric MRI were built with the five most frequent features. Model performance was evaluated using the area under the curve (AUC) values. RESULTS: Multiparametric MRI radiomics model achieved improved AUCs (0.791 and 0.786 in the training and validation sets, respectively) than that of the CT radiomics model (0.672 and 0.655 in the training and validation sets, respectively) and of the radiologists' assessment (0.600-0.613 and 0.560-0.587 in the training and validation sets, respectively). CONCLUSION: Multiparametric MRI radiomics model may serve as a potential tool for preoperatively evaluating LNM in PDAC and had superior predictive performance to multiphase CT-based model and radiologists' assessment.

The narrow subspine space and relatively large labrum are radiographic features of subspine impingement: a case-control study.

BACKGROUND: Subspine impingement is considered a source of residual hip symptoms after primary hip arthroscopy, and the role of the subspine space and soft tissue is not clear. The purpose of this study was to analyze the relationship between the subspine space and labrum size in subspine impingement patients. METHODS: We performed a retrospective study of patients with femoroacetabular impingement between July 2016 and July 2020. Sixteen patients without hip symptom relief after primary hip arthroscopic treatment of femoroacetabular impingement and undergoing revision surgery for anterior inferior iliac spine compression were included as the study group. Forty-eight matched patients who underwent only primary surgery and whose hip discomfort was relieved without a diagnosis of subspine impingement were included as the control group. The patients' preoperative computerized tomography data were reviewed, and the anterior inferior iliac spine dimensions and the size of the subspine space were measured. The size of the labrum at the 11:30, 1:30, and 3 o'clock positions was measured with the use of magnetic resonance imaging. The ratio of the subspine space to the labrum was also calculated. RESULTS: There was no significant difference in anterior inferior iliac spine dimensions between these two groups (p > 0.05). A relatively narrow subspine space was found in the study group, especially in the direction of the anterior inferior iliac spine. Compared with the control group, subspine impingement patients were identified with larger labrums at 11:30 (8.20 ± 1.95 mm vs. 6.81 ± 0.50 mm, p = 0.016), 1:30 (7.83 ± 1.61 mm and 6.25 ± 0.78 mm, p = 0.001) and 3:00 (9.50 ± 1.73 mm vs. 7.48 ± 0.99 mm, p = 0.001). A relative mismatch between the subspine space and the labrum was also identified in the study group. The ratios of the labrum width to the subspine area were significantly larger in the study group than in the control group. CONCLUSION: This study reported potential additional criteria for subspine impingement-a large labrum and a relatively narrow subspine space-instead of abnormal anterior inferior iliac spine dimensions. For those with a large labrum and narrow subspine space, the diagnosis of subspine impingement should be carefully made, and arthroscopic anterior inferior iliac spine decompression may be important.

BgNet: Classification of benign and malignant tumors with MRI multi-plane attention learning.

Objectives: To propose a deep learning-based classification framework, which can carry out patient-level benign and malignant tumors classification according to the patient's multi-plane images and clinical information. Methods: A total of 430 cases of spinal tumor, including axial and sagittal plane images by MRI, of which 297 cases for training (14072 images), and 133 cases for testing (6161 images) were included. Based on the bipartite graph and attention learning, this study proposed a multi-plane attention learning framework, BgNet, for benign and malignant tumor diagnosis. In a bipartite graph structure, the tumor area in each plane is used as the vertex of the graph, and the matching between different planes is used as the edge of the graph. The tumor areas from different plane images are spliced at the input layer. And based on the convolutional neural network ResNet and visual attention learning model Swin-Transformer, this study proposed a feature fusion model named ResNetST for combining both global and local information to extract the correlation features of multiple planes. The proposed BgNet consists of five modules including a multi-plane fusion module based on the bipartite graph, input layer fusion module, feature layer fusion module, decision layer fusion module, and output module. These modules are respectively used for multi-level fusion of patient multi-plane image data to realize the comprehensive diagnosis of benign and malignant tumors at the patient level. Results: The accuracy (ACC: 79.7%) of the proposed BgNet with multi-plane was higher than that with a single plane, and higher than or equal to the four doctors' ACC (D1: 70.7%, p=0.219; D2: 54.1%, p<0.005; D3: 79.7%, p=0.006; D4: 72.9%, p=0.178). Moreover, the diagnostic accuracy and speed of doctors can be further improved with the aid of BgNet, the ACC of D1, D2, D3, and D4 improved by 4.5%, 21.8%, 0.8%, and 3.8%, respectively. Conclusions: The proposed deep learning framework BgNet can classify benign and malignant tumors effectively, and can help doctors improve their diagnostic efficiency and accuracy. The code is available at https://github.com/research-med/BgNet.

Prognostic Value and Quantitative CT Analysis in RANKL Expression of Spinal GCTB in the Denosumab Era: A Machine Learning Approach.

The receptor activator of the nuclear factor kappa B ligand (RANKL) is the therapeutic target of denosumab. In this study, we evaluated whether radiomics signature and machine learning analysis can predict RANKL status in spinal giant cell tumors of bone (GCTB). This retrospective study consisted of 107 patients, including a training set (n = 82) and a validation set (n = 25). Kaplan-Meier survival analysis was used to validate the prognostic value of RANKL status. Radiomic feature extraction of three heterogeneous regions (VOIentire, VOIedge, and VOIcore) from pretreatment CT were performed. Followed by feature selection using Selected K Best and least absolute shrinkage and selection operator (LASSO) analysis, three classifiers (random forest (RF), support vector machine, and logistic regression) were used to build models. The area under the curve (AUC), accuracy, F1 score, recall, precision, sensitivity, and specificity were used to evaluate the models' performance. Classification of 75 patients with eligible follow-up based on RANKL status resulted in a significant difference in progression-free survival (p = 0.035). VOIcore-based RF classifier performs best. Using this model, the AUCs for the training and validation cohorts were 0.880 and 0.766, respectively. In conclusion, a machine learning approach based on CT radiomic features could discriminate prognostically significant RANKL status in spinal GCTB, which may ultimately aid clinical decision-making.

Intravoxel incoherent motion to differentiate spinal metastasis: A pilot study.

Background: To investigate the value of intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) to discriminate spinal metastasis from tuberculous spondylitis. Methods: This study included 50 patients with spinal metastasis (32 lung cancer, 7 breast cancer, 11 renal cancer), and 20 with tuberculous spondylitis. The IVIM parameters, including the single-index model (apparent diffusion coefficient (ADC)-stand), double exponential model (ADCslow, ADCfast, and f), and the stretched-exponential model parameters (distributed diffusion coefficient (DDC) and α), were acquired. Receiver operating characteristic (ROC) and the area under the ROC curve (AUC) analysis was used to evaluate the diagnostic performance. Each parameter was substituted into a logistic regression model to determine the meaningful parameters, and the combined diagnostic performance was evaluated. Results: The ADCfast and f showed significant differences between spinal metastasis and tuberculous spondylitis (all p < 0.05). The logistic regression model results showed that ADCfast and f were independent factors affecting the outcome (P < 0.05). The AUC values of ADCfast and f were 0.823 (95% confidence interval (CI): 0.719 to 0.927) and 0.876 (95%CI: 0.782 to 0.969), respectively. ADCfast combined with f showed the highest AUC value of 0.925 (95% CI: 0.858 to 0.992). Conclusions: IVIM MR imaging might be helpful to differentiate spinal metastasis from tuberculous spondylitis, and provide guidance for clinical treatment.