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.

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.

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.

Deep Learning Approach for MRI in the Classification of Anterior Talofibular Ligament Injuries.

BACKGROUND: Diagnosing anterior talofibular ligament (ATFL) injuries differs among radiologists. Further assessment of ATFL tears is valuable for clinical decision-making. PURPOSE: To establish a deep learning method for classifying ATFL injuries based on magnetic resonance imaging (MRI). STUDY TYPE: Retrospective. POPULATION: One thousand seventy-three patients from a single center with ankle MRI within 1 month of reference standard arthroscopy (in-group dataset), were divided into training, validation, and test sets in a ratio of 8:1:1. Additionally, 167 patients from another center were used as an independent out-group dataset. FIELD STRENGTH/SEQUENCE: Fat-saturation proton density-weighted fast spin-echo sequence at 1.5/3.0 T. ASSESSMENT: Patients were divided into normal, strain and degeneration, partial tear and complete tear groups (groups 0-3). The complete tear group was divided into five sub-groups by location and the potential avulsion fracture (groups 3.1-3.5). All images were input into AlexNet, VGG11, Small-Sample-Attention Net (SSA-Net), and SSA-Net + Weight Loss for classification. The results were compared with four radiologists with 5-30 years of experience. STATISTICAL TESTS: Model performance was evaluated by the receiver operating characteristic (ROC) curve, the area under the ROC curve (AUC), and so on. McNemar's test was used to compare performance among the different models, and between the radiologists and models. The intraclass correlation coefficient (ICC) was used to assess the reliability of the radiologists. P < 0.05 was considered statistically significant. RESULTS: The average AUC of AlexNet, VGG11, SAA-Net, and SSA-Net + Weight Loss was 0.95, 0.99, 0.99, 0.99 in groups 0-3 and 0.96, 0.99, 0.99, 0.99 in groups 3.1-3.5. The effect of SSA-Net + Weight Loss was similar to SSA-Net but better than AlexNet and VGG11. In the out-group test set, the AUC of SSA-Net + Weight Loss ranged from 0.89 to 0.99. The ICC of radiologists was 0.97-1.00. The effect of SSA-Net + Weight Loss was better than each radiologist in the in-group and out-group test sets. DATA CONCLUSION: Deep learning has potential to be used for classifying ATFL injuries. SSA-Net + Weight Loss has a better diagnostic effect than radiologists with different experience levels. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

Investigating the Association of Carotid Atherosclerotic Plaque MRI Features and Silent Stroke After Carotid Endarterectomy.

BACKGROUND: The predictive value of carotid plaque characteristics for silent stroke (SS) after carotid endarterectomy (CEA) is unclear. OBJECTIVE: To investigate the associations between carotid plaque characteristics and postoperative SS in patients undergoing CEA. STUDY TYPE: Prospective. POPULATION: One hundred fifty-three patients (mean age: 65.4 ± 7.9 years; 126 males) with unilateral moderate-to-severe carotid stenosis (evaluated by CT angiography) referred for CEA. FIELD STRENGTH/SEQUENCE: 3 T, brain-MRI:T2-PROPELLER, T1-/T2-FLAIR, diffusion weighted imaging (DWI) and T2*, carotid-MRI:black-blood T1-/T2W, 3D TOF, Simultaneous Non-contrast Angiography intraplaque hemorrhage. ASSESSMENT: Patients underwent carotid-MRI within 1-week before CEA, and brain-MRI within 48-hours pre-/post-CEA. The presence and size (volume, maximum-area-percentage) of carotid lipid-rich necrotic core (LRNC), intraplaque hemorrhage (Type-I/Type-II IPH) and calcification were evaluated on carotid-MR images. Postoperative SS was assessed from pre-/post-CEA brain DWI. Patients were divided into moderate-carotid-stenosis (50%-69%) and severe-carotid-stenosis (70%-99%) groups and the associations between carotid plaque characteristics and SS were analyzed. STATISTICAL TESTS: Independent t test, Mann-Whitney U-test, chi-square test and logistic regressions (OR: odds ratio, CI: confidence interval). P value <0.05 was considered statistically significant. RESULTS: SS was found in 8 (16.3%) of the 49 patients with moderate-carotid-stenosis and 21 (20.2%) of the 104 patients with severe-carotid-stenosis. In patients with severe-carotid-stenosis, those with SS had significantly higher IPH (66.7% vs. 39.8%) and Type-I IPH (66.7% vs. 38.6%) than those without. The presence of IPH (OR 3.030, 95% CI 1.106-8.305) and Type-I IPH (OR 3.187, 95% CI 1.162-8.745) was significantly associated with SS. After adjustment, the associations of SS with presence of IPH (OR 3.294, 95% CI 1.122-9.669) and Type-I IPH (OR 3.633, 95% CI 1.216-10.859) remained significant. Moreover, the volume of Type-II IPH (OR 1.014, 95% CI 1.001-1.028), and maximum-area-percentage of Type-II IPH (OR 1.070, 95% CI 1.002-1.142) and LRNC (OR 1.030, 95% CI 1.000-1.061) were significantly associated with SS after adjustment. No significant (P range: 0.203-0.980) associations were found between carotid plaque characteristics and SS in patients with moderate-carotid-stenosis. DATA CONCLUSIONS: In patients with unilateral severe-carotid-stenosis, carotid vulnerable plaque MR features, particularly presence and size of IPH, might be effective predictors for SS after CEA. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

MRI-based automated multitask deep learning system to evaluate supraspinatus tendon injuries.

OBJECTIVE: To establish an automated, multitask, MRI-based deep learning system for the detailed evaluation of supraspinatus tendon (SST) injuries. METHODS: According to arthroscopy findings, 3087 patients were divided into normal, degenerative, and tear groups (groups 0-2). Group 2 was further divided into bursal-side, articular-side, intratendinous, and full-thickness tear groups (groups 2.1-2.4), and external validation was performed with 573 patients. Visual geometry group network 16 (VGG16) was used for preliminary image screening. Then, the rotator cuff multitask learning (RC-MTL) model performed multitask classification (classifiers 1-4). A multistage decision model produced the final output. Model performance was evaluated by receiver operating characteristic (ROC) curve analysis and calculation of related parameters. McNemar's test was used to compare the differences in the diagnostic effects between radiologists and the model. The intraclass correlation coefficient (ICC) was used to assess the radiologists' reliability. p < 0.05 indicated statistical significance. RESULTS: In the in-group dataset, the area under the ROC curve (AUC) of VGG16 was 0.92, and the average AUCs of RC-MTL classifiers 1-4 were 0.99, 0.98, 0.97, and 0.97, respectively. The average AUC of the automated multitask deep learning system for groups 0-2.4 was 0.98 and 0.97 in the in-group and out-group datasets, respectively. The ICCs of the radiologists were 0.97-0.99. The automated multitask deep learning system outperformed the radiologists in classifying groups 0-2.4 in both the in-group and out-group datasets (p < 0.001). CONCLUSION: The MRI-based automated multitask deep learning system performed well in diagnosing SST injuries and is comparable to experienced radiologists. CLINICAL RELEVANCE STATEMENT: Our study established an automated multitask deep learning system to evaluate supraspinatus tendon (SST) injuries and further determine the location of SST tears. The model can potentially improve radiologists' diagnostic efficiency, reduce diagnostic variability, and accurately assess SST injuries. KEY POINTS: • A detailed classification of supraspinatus tendon tears can help clinical decision-making. • Deep learning enables the detailed classification of supraspinatus tendon injuries. • The proposed automated multitask deep learning system is comparable to radiologists.

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.

Feasibility of AI-assisted compressed sensing protocols in knee MR imaging: a prospective multi-reader study.

OBJECTIVES: To evaluate the image quality and diagnostic performance of AI-assisted compressed sensing (ACS) accelerated two-dimensional fast spin-echo MRI compared with standard parallel imaging (PI) in clinical 3.0T rapid knee scans. METHODS: This prospective study enrolled 130 consecutive participants between March and September 2022. The MRI scan procedure included one 8.0-min PI protocol and two ACS protocols (3.5 min and 2.0 min). Quantitative image quality assessments were performed by evaluating edge rise distance (ERD) and signal-to-noise ratio (SNR). Shapiro-Wilk tests were performed and investigated by the Friedman test and post hoc analyses. Three radiologists independently evaluated structural disorders for each participant. Fleiss κ analysis was used to compare inter-reader and inter-protocol agreements. The diagnostic performance of each protocol was investigated and compared by DeLong's test. The threshold for statistical significance was set at p  < 0.05. RESULTS: A total of 150 knee MRI examinations constituted the study cohort. For the quantitative assessment of four conventional sequences with ACS protocols, SNR improved significantly (p < 0.001), and ERD was significantly reduced or equivalent to the PI protocol. For the abnormality evaluated, the intraclass correlation coefficient ranged from moderate to substantial between readers (κ = 0.75-0.98) and between protocols (κ = 0.73-0.98). For meniscal tears, cruciate ligament tears, and cartilage defects, the diagnostic performance of ACS protocols was considered equivalent to PI protocol (Delong test, p > 0.05). CONCLUSIONS: Compared with the conventional PI acquisition, the novel ACS protocol demonstrated superior image quality and was feasible for achieving equivalent detection of structural abnormalities while reducing acquisition time by half. CLINICAL RELEVANCE STATEMENT: Artificial intelligence-assisted compressed sensing (ACS) providing excellent quality and a 75% reduction in scanning time presents significant clinical advantages in improving the efficiency and accessibility of knee MRI for more patients. KEY POINTS: • The prospective multi-reader study showed no difference in diagnostic performance between parallel imaging and AI-assisted compression sensing (ACS) was found. • Reduced scan time, sharper delineation, and less noise with ACS reconstruction. • Improved efficiency of the clinical knee MRI examination by the ACS acceleration.

Application research of AI-assisted compressed sensing technology in MRI scanning of the knee joint: 3D-MRI perspective.

OBJECTIVE: To investigate the potential applicability of AI-assisted compressed sensing (ACS) in knee MRI to enhance and optimize the scanning process. METHODS: Volunteers and patients with sports-related injuries underwent prospective MRI scans with a range of acceleration techniques. The volunteers were subjected to varied ACS acceleration levels to ascertain the most effective level. Patients underwent scans at the determined optimal 3D-ACS acceleration level, and 3D compressed sensing (CS) and 2D parallel acquisition technology (PAT) scans were performed. The resultant 3D-ACS images underwent 3.5 mm/2.0 mm multiplanar reconstruction (MPR). Experienced radiologists evaluated and compared the quality of images obtained by 3D-ACS-MRI and 3D-CS-MRI, 3.5 mm/2.0 mm MPR and 2D-PAT-MRI, diagnosed diseases, and compared the results with the arthroscopic findings. The diagnostic agreement was evaluated using Cohen's kappa correlation coefficient, and both absolute and relative evaluation methods were utilized for objective assessment. RESULTS: The study involved 15 volunteers and 53 patients. An acceleration factor of 10.69 × was identified as optimal. The quality evaluation showed that 3D-ACS provided poorer bone structure visualization, and improved cartilage visualization and less satisfactory axial images with 3.5 mm/2.0 mm MPR than 2D-PAT. In terms of objective evaluation, the relative evaluation yielded satisfactory results across different groups, while the absolute evaluation revealed significant variances in most features. Nevertheless, high levels of diagnostic agreement (κ: 0.81-0.94) and accuracy (0.83-0.98) were observed across all diagnoses. CONCLUSION: ACS technology presents significant potential as a replacement for traditional CS in 3D-MRI knee scans, allowing thinner MPRs and markedly faster scans without sacrificing diagnostic accuracy. CLINICAL RELEVANCE STATEMENT: 3D-ACS-MRI of the knee can be completed in the 160 s with good diagnostic consistency and image quality. 3D-MRI-MPR can replace 2D-MRI and reconstruct images with thinner slices, which helps to optimize the current MRI examination process and shorten scanning time. KEY POINTS: • AI-assisted compressed sensing technology can reduce knee MRI scan time by over 50%. • 3D AI-assisted compressed sensing MRI and related multiplanar reconstruction can replace traditional accelerated MRI and yield thinner 2D multiplanar reconstructions. • Successful application of 3D AI-assisted compressed sensing MRI can help optimize the current knee MRI process.

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.

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.

Deep learning model for measuring the sagittal Cobb angle on cervical spine computed tomography.

PURPOSES: To develop a deep learning (DL) model to measure the sagittal Cobb angle of the cervical spine on computed tomography (CT). MATERIALS AND METHODS: Two VB-Net-based DL models for cervical vertebra segmentation and key-point detection were developed. Four-points and line-fitting methods were used to calculate the sagittal Cobb angle automatically. The average value of the sagittal Cobb angle was manually measured by two doctors as the reference standard. The percentage of correct key points (PCK), matched samples t test, intraclass correlation coefficient (ICC), Pearson correlation coefficient, mean absolute error (MAE), and Bland‒Altman plots were used to evaluate the performance of the DL model and the robustness and generalization of the model on the external test set. RESULTS: A total of 991 patients were included in the internal data set, and 112 patients were included in the external data set. The PCK of the DL model ranged from 78 to 100% in the test set. The four-points method, line-fitting method, and reference standard measured sagittal Cobb angles were - 1.10 ± 18.29°, 0.30 ± 13.36°, and 0.50 ± 12.83° in the internal test set and 4.55 ± 20.01°, 3.66 ± 18.55°, and 1.83 ± 12.02° in the external test set, respectively. The sagittal Cobb angle calculated by the four-points method and the line-fitting method maintained high consistency with the reference standard (internal test set: ICC = 0.75 and 0.97; r = 0.64 and 0.94; MAE = 5.42° and 3.23°, respectively; external test set: ICC = 0.74 and 0.80, r = 0.66 and 0.974, MAE = 5.25° and 4.68°, respectively). CONCLUSIONS: The DL model can accurately measure the sagittal Cobb angle of the cervical spine on CT. The line-fitting method shows a higher consistency with the doctors and a minor average absolute error.

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.

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.

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.

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.

Application of Magnetic Resonance Imaging in Neoadjuvant Treatment of Pancreatic Ductal Adenocarcinoma.

Pancreatic ductal adenocarcinoma (PDAC) is one of the deadliest malignant tumors of the human digestive system. Due to its insidious onset, many patients have already lost the opportunity for radical resection upon tumor diagnosis. In recent years, neoadjuvant treatment for patients with borderline resectable PDAC has been recommended by multiple guidelines to increase the resection rate of radical surgery and improve the postoperative survival. However, further developments are required to accurately assess the tumor response to neoadjuvant therapy and to select the population suitable for such treatment. Reductions in drug toxicity and the number of neoadjuvant cycles are also critical. At present, the clinical evaluation of neoadjuvant treatment is mainly based on several serological and imaging indicators; however, the unique characteristics of PDAC and the insufficient sensitivity and specificity of the markers render this system ineffective. The imaging evaluation system, magnetic resonance imaging (MRI), has its own unique imaging advantages compared with computed tomography (CT) and other imaging examinations. One key advantage is the ability to reflect the changes more rapidly in tumor tissue components, such as the degree of fibrosis, microvessel density, and tissue hypoxia. It can also perform multiparameter quantitative analysis of tumor tissue and changes, attributing to its increasingly important role in imaging evaluation, and potentially the evaluation of neoadjuvant treatment of pancreatic cancer, as several current articles have studied. At the same time, owing to the complexity of MRI and some of its limitations, its wider application is limited. Compared with CT imaging, few relevant studies have been conducted. In this review article, we will investigate and summarize the advantages, limitations, and future development of MRI in the evaluation of neoadjuvant treatment of PDAC. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

A Deep Learning Approach for MRI in the Diagnosis of Labral Injuries of the Hip Joint.

BACKGROUND: The diagnosis of labral injury on MRI is time-consuming and potential for incorrect diagnoses. PURPOSE: To explore the feasibility of applying deep learning to diagnose and classify labral injuries with MRI. STUDY TYPE: Retrospective. POPULATION: A total of 1016 patients were divided into normal (n = 168, class 0) and abnormal labrum (n = 848) groups. The abnormal group consisted of n = 111 with class 1 (degeneration), n = 437 with class 2 (partial or complete tear), and n = 300 with unclassified injury. Patients were randomly divided into training, validation, and test cohort according to the ratio of 55%:15%:30%. FIELD STRENGTH/SEQUENCE: Fat-saturation proton density-weighted fast spin-echo sequence at 3.0 T. ASSESSMENT: Convolutional neural network-6 (CNN-6) was used to extract, discriminate, and detect oblique coronal (OCOR) and oblique sagittal (OSAG) images. Mask R-CNN was used for segmentation. LeNet-5 was used to diagnose and classify labral injuries. The weighting method combined the models of OCOR and OSAG. The output-input connection was used to correlate the whole diagnosis/classification system. Four radiologists performed subjective diagnoses to obtain the diagnosis results. STATISTICAL TESTS: CNN-6 and LeNet-5 were evaluated by area under the receiver operating characteristic (ROC) curve and related parameters. The mean average precision (MAP) evaluated the Mask R-CNN. McNemar's test was used to compare the radiologists and models. A P value < 0.05 was considered statistically significant. RESULTS: The area under the curve (AUC) of CNN-6 was 0.99 for extraction, discrimination, and detection. MAP values of Mask R-CNN for OCOR and OSAG image segmentation were 0.96 and 0.99. The accuracies of LeNet-5 in the diagnosis and classification were 0.94/0.94 (OCOR) and 0.92/0.91 (OSAG), respectively. The accuracy of the weighted models in the diagnosis and classification were 0.94 and 0.97, respectively. The accuracies of radiologists in the diagnosis and classification of labrum injuries ranged from 0.85 to 0.92 and 0.78 to 0.94, respectively. DATA CONCLUSION: Deep learning can assist radiologists in diagnosing and classifying labrum injuries. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Utility of Advanced DWI in the Detection of Spinal Cord Microstructural Alterations and Assessment of Neurologic Function in Cervical Spondylotic Myelopathy Patients.

BACKGROUND: Diffusion-weighted imaging (DWI) can quantify the microstructural changes in the spinal cord. It might be a substitute for T2 increased signal intensity (ISI) for cervical spondylotic myelopathy (CSM) evaluation and prognosis. PURPOSE: The purpose of the study is to investigate the relationship between DWI metrics and neurologic function of patients with CSM. STUDY TYPE: Retrospective. POPULATION: Forty-eight patients with CSM (18.8% females) and 36 healthy controls (HCs, 25.0% females). FIELD STRENGTH/SEQUENCE: 3 T; spin-echo echo-planar imaging-DWI; turbo spin-echo T1/T2; multi-echo gradient echo T2*. ASSESSMENT: For patients, conventional MRI indicators (presence and grades of T2 ISI), DWI indicators (neurite orientation dispersion and density imaging [NODDI]-derived isotropic volume fraction [ISOVF], intracellular volume fraction, and orientation dispersion index [ODI], diffusion tensor imaging [DTI]-derived fractional anisotropy [FA] and mean diffusivity [MD], and diffusion kurtosis imaging [DKI]-derived FA, MD, and mean kurtosis), clinical conditions, and modified Japanese Orthopaedic Association (mJOA) were recorded before the surgery. Neurologic function improvement was measured by the 3-month follow-up recovery rate (RR). For HCs, DWI, and mJOA were measured as baseline comparison. STATISTICAL TESTS: Continuous (categorical) variables were compared between patients and HCs using Student's t-tests or Mann-Whitney U tests (chi-square or Fisher exact tests). The relationships between DWI metrics/conventional MRI findings, and the pre-operative mJOA/RR were assessed using correlation and multivariate analysis. P < 0.05 was considered statistically significant. RESULTS: Among patients, grades of T2 ISI were not correlated with pre-surgical mJOA/RR (P = 0.717  and 0.175, respectively). NODDI ODI correlated with pre-operative mJOA (r = -0.31). DTI FA, DKI FA, and NODDI ISOVF were correlated with the recovery rate (r = 0.31, 0.41, and -0.34, respectively). In multivariate analysis, NODDI ODI (DTI FA, DKI FA, NODDI ISOVF) significantly contributed to the pre-operative mJOA (RR) after adjusting for age. DATA CONCLUSION: DTI FA, DKI FA, and NODDI ISOVF are predictors for prognosis in patients with CSM. NODDI ODI can be used to evaluate CSM severity. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 5.

Proximal nerve MR neurography with diffusion tensor imaging in differentiating subtypes of Charcot-Marie-Tooth disease.

OBJECTIVES: To evaluate the feasibility of proximal nerve MR neurography with diffusion tensor imaging (DTI) for differentiating Charcot-Marie-Tooth (CMT) 1A, CMT2, and healthy controls. METHODS: The diameters, fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) of L4-L5 nerve roots, femoral nerve (FN), and sciatic nerve (SN) were compared. Receiver operating characteristic (ROC) curve analyses were conducted to evaluate the diagnostic performance. DeLong's tests were applied to compare multiple ROC curves. Intraclass correlation coefficients were calculated for interobserver agreement assessment. RESULTS: The diameters of the L4 nerve root, L5 nerve root, and SN of CMT1A patients were significantly larger than those of CMT2 patients and healthy controls. The FA values of all measured proximal nerves were significantly higher in controls (0.46 ± 0.09, 0.46 ± 0.08, 0.45 ± 0.07, and 0.48 ± 0.08) than in CMT1A patients (0.30 ± 0.09, 0.29 ± 0.06, 0.35 ± 0.08, and 0.29 ± 0.09). The FA values of the L5 nerve root, FN, and SN were significantly higher in controls (0.46 ± 0.08, 0.45 ± 0.07, and 0.48 ± 0.08) than in CMT2 patients (0.36 ± 0.06, 0.34 ± 0.07, and 0.34 ± 0.10). The MD and RD values of the L5 nerve root in CMT1A patients (1.59 ± 0.21 and 1.37 ± 0.21) were higher than those in CMT2 patients (1.31 ± 0.17 and 1.05 ± 0.14). The AUCs of the above parameters ranged from 0.780 to 1.000. For the measurements of nerve diameters, the ICC ranged from 0.91 to 0.97. For the measurements of DTI metrics, the ICC ranged from 0.87 to 0.97. CONCLUSIONS: MR neurography with DTI is able to differentiate CMT1A patients, CMT2 patients, and healthy controls. KEY POINTS: • MR neurography with diffusion tensor imaging of the L4-5 nerve roots, proximal femoral nerve, and proximal sciatic nerve is able to discriminate CMT1A, CMT2, and healthy controls. • This method provides an alternative for the diagnosis and discrimination of CMT1A and CMT2, which is crucial for clinical management.