Magnetic resonance imaging-based prediction models for differentiating intraspinal schwannomas from meningiomas: classification and regression tree and random forest analysis.

Background: Due to the variations in surgical approaches and prognosis between intraspinal schwannomas and meningiomas, it is crucial to accurately differentiate between the two prior to surgery. Currently, there is limited research exploring the implementation of machine learning (ML) methods for distinguishing between these two types of tumors. This study aimed to establish a classification and regression tree (CART) model and a random forest (RF) model for distinguishing schwannomas from meningiomas. Methods: We retrospectively collected 88 schwannomas (52 males and 36 females) and 51 meningiomas (10 males and 41 females) who underwent magnetic resonance imaging (MRI) examinations prior to the surgery. Simple clinical data and MRI imaging features, including age, sex, tumor location and size, T1-weighted images (T1WI) and T2-weighted images (T2WI) signal characteristics, degree and pattern of enhancement, dural tail sign, ginkgo leaf sign, and intervertebral foramen widening (IFW), were reviewed. Finally, a CART model and RF model were established based on the aforementioned features to evaluate their effectiveness in differentiating between the two types of tumors. Meanwhile, we also compared the performance of the ML models to the radiologists. The receiver operating characteristic (ROC) curve, accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were used to evaluate the models and clinicians' discrimination performance. Results: Our investigation reveals significant variations in ten out of 11 variables in the training group and five out of 11 variables in the test group when comparing schwannomas and meningiomas (P<0.05). Ultimately, the CART model incorporated five variables: enhancement pattern, the presence of IFW, tumor location, maximum diameter, and T2WI signal intensity (SI). The RF model combined all 11 variables. The CART model, RF model, radiologist 1, and radiologist 2 achieved an area under the curve (AUC) of 0.890, 0.956, 0.681, and 0.723 in the training group, and 0.838, 0.922, 0.580, and 0.659 in the test group, respectively. Conclusions: The RF prediction model exhibits more exceptional performance than an experienced radiologist in discriminating intraspinal schwannomas from meningiomas. The RF model seems to be better in discriminating the two tumors than the CART model.

Renal interstitial fibrotic assessment using non-Gaussian diffusion kurtosis imaging in a rat model of hyperuricemia.

BACKGROUND: To investigate the feasibility of Diffusion Kurtosis Imaging (DKI) in assessing renal interstitial fibrosis induced by hyperuricemia. METHODS: A hyperuricemia rat model was established, and the rats were randomly split into the hyperuricemia (HUA), allopurinol (AP), and AP + empagliflozin (AP + EM) groups (n = 19 per group). Also, the normal rats were selected as controls (CON, n = 19). DKI was performed before treatment (baseline) and on days 1, 3, 5, 7, and 9 days after treatment. The DKI indicators, including mean kurtosis (MK), fractional anisotropy (FA), and mean diffusivity (MD) of the cortex (CO), outer stripe of the outer medulla (OS), and inner stripe of the outer medulla (IS) were acquired. Additionally, hematoxylin and eosin (H&E) staining, Masson trichrome staining, and nuclear factor kappa B (NF-κB) immunostaining were used to reveal renal histopathological changes at baseline, 1, 5, and 9 days after treatment. RESULTS: The HUA, AP, and AP + EM group MKOS and MKIS values gradually increased during this study. The HUA group exhibited the highest MK value in outer medulla. Except for the CON group, all the groups showed a decreasing trend in the FA and MD values of outer medulla. The HUA group exhibited the lowest FA and MD values. The MKOS and MKIS values were positively correlated with Masson's trichrome staining results (r = 0.687, P < 0.001 and r = 0.604, P = 0.001, respectively). The MDOS and FAIS were negatively correlated with Masson's trichrome staining (r = -626, P < 0.0014 and r = -0.468, P = 0.01, respectively). CONCLUSION: DKI may be a non-invasive method for monitoring renal interstitial fibrosis induced by hyperuricemia.

Using intravoxel incoherent motion imaging to evaluate uric acid-induced renal injury and efficacy after treatment.

OBJECTIVES: To validate the feasibility of intravoxel incoherent motion imaging (IVIM) for monitoring renal injury and uric acid-lowering efficacy in a rat model of hyperuricaemia. METHODS: A total of 92 rats were analysed and categorized into 4 groups: control (CON), hyperuricaemia (HUA), allopurinol intervention (ALL), and combined intervention (COM). Eight rats were randomly selected from each group and underwent IVIM scanning on days 0, 1, 3, 5, 7, and 9. Quantitative magnetic resonance values (D, D*, and f values) measured from the different renal anatomical regions. Quantitative histopathological analysis was performed to assess renal tubular injury using neutrophil gelatinase-associated lipocalin (NGAL), and renal fibrosis using alpha-smooth-muscle-actin (α-SMA). Pearson's correlation analysis was used to determine the correlation between IVIM-derived parameters and the expression of NGAL and α-SMA. RESULTS: The D values of the HUA, ALL, and COM groups generally showed a downward trend over time, and this fluctuation was most significant in the HUA group. The D values showed significant intergroup differences at each point, whereas only a few discrepancies were found in the D* and f values. In addition, the renal D value was negatively correlated with the positive staining rates for NGAL and α-SMA (P < .05), except for the lack of correlation between Dos and α-SMA (P > .05). CONCLUSION: IVIM could be a noninvasive and potential assessment modality for the evaluation of renal injury induced by hyperuricaemia and its prognostic efficacy. ADVANCES IN KNOWLEDGE: IVIM could be a surrogate manner in monitoring renal damage induced by hyperuricaemia and its treatment evaluation.

Association of Muscle Fat Content and Muscle Mass With Impaired Lung Function in Young Adults With Obesity: Evaluation With MRI.

RATIONALE AND OBJECTIVES: Although low muscle mass is associated with decreased lung function, studies exploring the relationship between muscle fat content and lung function impairment are scarce. This study aimed to evaluate the association of muscle mass and fatty infiltration with lung function in young adults with obesity. MATERIALS AND METHODS: We performed a retrospective cross-sectional study of patients aged 18-45 years with obesity who had impaired pulmonary function (case group, n = 66) and those with normal pulmonary function (control group, n = 198) by matching age, sex, body mass index (BMI), and height to assess whether muscle characteristics differed. Muscle mass and muscle fat content were assessed by MRI using a chemical shift-encoded sequence (IDEAL-IQ). RESULTS: A total of 264 patients were enrolled (124 females; mean age 32.0 years). The case group had lower muscle mass than the control group (p = 0.012), and there was an association between low muscle mass and lung function impairment (odds ratio (OR), 3.74; 95% confidence interval (CI), 1.57-8.93). Furthermore, muscle fat content was significantly higher in cases compared to controls (7.4 (2.7) % vs. 6.2 (2.5) %, p = 0.001). Multiple logistic regression analysis showed that muscle fat content was associated with a higher risk of impaired lung function (OR, 2.10; 95% CI, 1.65-2.66), regardless of adiposity and muscle mass. CONCLUSION: Both muscle fat content and muscle mass are associated with impaired lung function in young adults with obesity.

Assessing early tubular protective effects of SGLT2 inhibitor empagliflozin against type 2 diabetes mellitus using functional magnetic resonance imaging.

AIMS: To observe the alterations in functional magnetic resonance imaging parameters in normoalbuminuric type 2 diabetic patients undergoing SGLT2 inhibitor empagliflozin treatment and investigate the early tubular protective effects of the inhibitor. METHODS: This study was performed in normoalbuminuric type 2 diabetes mellitus patients (UACR < 30 mg/g, eGFR ≥ 60 ml/min/1.73 m2). The patients were divided into the intervention group (empagliflozin) and the control group (27 cases each). The intervention group was treated with 10 mg/day empagliflozin tablets orally, while the control group had adjustments to their basic treatment stage. The patients were treated for 6 weeks. RESULTS: The baseline clinical data of the two groups were comparable (P˃0.05). The intervention group exhibited better improvements in blood lipid profiles and more significant reductions in blood uric acid levels compared to the control group (P < 0.05). The two groups had No significant difference in blood pressure changes (P˃0.05). Notably, the intervention group demonstrated a greater reduction in UACR and a more substantial decline in eGFR than the control group (P < 0.05). Regarding functional magnetic resonance imaging parameters, the MD value of the renal medulla region in the intervention group increased after treatment, while the MR2* value of the renal medulla region decreased (P < 0.05). CONCLUSIONS: SGLT2 inhibitor empagliflozin can reduce UACR and eGFR levels in early type 2 diabetic patients with normal proteinuria. Moreover, empagliflozin therapy led to an increase in the MD value and a decrease in the MR2* value of the renal medulla, evidencing the early tubular protective effects of this therapy.

Correlation Between Functional Magnetic Resonance Imaging and Renal Tubular Injury Markers in Early Assessment Of Renal Tubular Injury in Type 2 Diabetes Mellitus.

Objective: Both functional magnetic resonance imaging and renal tubular injury markers have been proved to be able to detect early renal damage in normoalbuminuric diabetic patients. This study mainly explored the functional magnetic resonance imaging parameters and renal tubular injury markers in the early evaluation of type 2 diabetes. Methods: A case observation study was established, and 62 patients with early-stage low-risk type 2 diabetes mellitus with normoalbuminuric (UACR<30 mg/g, eGFR≥60 ml/min/1.73 m2) were included for analysis. Urine kidney damage was determined by ELISA. Kidney injury molecule 1 (KIM-1) and neutrophil gelatinase-associated lipocalin (NGAL) assessment of renal tubular injury, and use of intravoxel incoherent motion magnetic resonance Imaging (intravoxel incoherent motion, IVIM) and blood oxygen level dependent magnetic resonance imaging (blood oxygen level dependent, BOLD) to evaluate renal cortex, medulla blood perfusion, water molecule diffusion, oxygenation level and other functional information, using linear correlation to analyze the correlation between functional magnetic resonance imaging parameters and markers of renal tubular injury. Results: The correlation analysis between IVIM parameters and renal tubular injury markers showed that KIM-1 was inversely correlated with the MD value of the renal medulla region parameter (r = -0.24, P = .03), and was closely related to the other IVIM cortex and medulla. There was no correlation between qualitative parameters (P > .05), and no correlation between NGAL and all parameters of IVIM (P > .05). The correlation analysis between BOLD parameters and renal tubular injury markers showed that KIM-1 was positively correlated with renal medulla region parameter MR2* value (r = 0.26, P = .04) and MCR value (r = 0.28, P = .03), respectively. There was also a positive correlation between NGAL and renal medulla region parameter MR2* value (r = 0.24, P = .04). Conclusion: In the early low-risk type 2 diabetic patients with normoalbuminuria, the more obvious the renal medullary water molecule diffusion disorder, the higher the renal tubular injury marker KIM-1, and the more severe renal medullary hypoxia, the renal tubular injury. The higher the markers KIM-1 and NGAL are, it is proved that the hypoxia and water diffusion disorder in the early renal medulla are related to renal tubular damage.

Well-controlled versus poorly controlled diabetes in patients with obesity: differences in MRI-evaluated pancreatic fat content.

Background: Patients with obesity and poorly controlled type 2 diabetes (T2D) are at high risk of diabetic complications. This study aimed to determine the associations of visceral adipose tissue (VAT), hepatic proton-density fat fraction (PDFF), and pancreatic PDFF with poor glycemic control in patients with obesity and T2D and to evaluate the metabolic effect of bariatric surgery in patients with obesity and poorly controlled diabetes. Methods: In this retrospective cross-sectional study, from July 2019 to March 2021, 151 consecutive obese patients with new-onset T2D (n=28), well-controlled T2D (n=17), poorly controlled T2D (n=32), prediabetes (n=20), or normal glucose tolerance (NGT; n=54) were included. A total of 18 patients with poorly controlled T2D were evaluated before and 12 months after bariatric surgery, and 18 non-obese healthy individuals served as controls. VAT, hepatic PDFF, and pancreatic PDFF were quantified by magnetic resonance imaging (MRI) using a chemical shift-encoded sequence [iterative decomposition of water and fat with echo asymmetry and least-squares estimation quantitation (IDEAL-IQ)]. Univariate analysis and multivariate regression analysis were performed. Results: There were significant differences in VAT, hepatic PDFF, and all pancreatic PDFF between the new-onset T2D, prediabetes, and NGT groups (all P<0.05). Pancreatic tail PDFF was significantly higher in the poorly controlled T2D group than in the well-controlled T2D group (P=0.001). In the multivariate analysis, only pancreatic tail PDFF was significantly associated with increased odds of poor glycemic control [odds ratio (OR) =2.09; 95% confidence interval (CI): 1.11-3.94; P=0.022]. The glycated hemoglobin (HbA1c), hepatic PDFF, and pancreatic PDFF significantly decreased (all P<0.01) after bariatric surgery, and the values were statistically similar to those observed in the non-obese healthy controls. Conclusions: Increased fat in the pancreatic tail is strongly associated with poor glycemic control in patients with obesity and T2D. Bariatric surgery is an effective therapy for poorly controlled diabetes and obesity, which improves glycemic control and decreases ectopic fat deposits.

Association of body composition with postoperative complications after laparoscopic sleeve gastrectomy and Roux-en-Y gastric bypass.

OBJECTIVE: To evaluate predictive values of body composition parameters measured from preoperative CT/MRIs for postoperative complications after laparoscopic sleeve gastrectomy (LSG) and Roux-en-Y gastric bypass (LRYGB) in patients with obesity. METHODS: In this retrospective case-control study, patients performing abdominal CT/MRIs within one month before and developing 30-day complications after bariatric procedures were matched for age, sex, and type of surgery with patients without complications (1/3 ratio, respectively). Complications were determined by documentation in the medical record. Two readers blindly segmented the total abdominal muscle area (TAMA) and visceral fat area (VFA) using predetermined thresholds for the Hounsfield unit (HU) on unenhanced CT and the signal intensity (SI) on T1-weighted MRI at the L3 vertebral level. Visceral obesity (VO) was defined as VFA > 136 cm2 in males and > 95 cm2 in females. These measures, along with perioperative variables, were compared. Multivariate logistic regression analyses were performed. RESULTS: Of 145 included patients, 36 had postoperative complications. No significant differences between LSG and LRYGB were present regarding complications and VO. Hypertension (p = 0.022), impaired lung function (p = 0.018), American Society of Anesthesiologists (ASA) grade (p = 0.046), VO (p = 0.021), and VFA/TAMA ratio (p < 0.0001) were associated with postoperative complications in the univariate logistic analysis; the VFA/TAMA ratio was the only independent predictor in multivariate analyses (OR 2.01, 95% CI 1.37-2.93, p < 0.001). CONCLUSION: The VFA/TAMA ratio provides important perioperative information in predicting patients who are likely to develop postoperative complications undergoing bariatric surgery.

Relationship of liver fat content with systemic metabolism and chronic complications in patients with type 2 diabetes mellitus.

OBJECTIVE: This study investigated the correlation of liver fat content (LFC) with metabolic characteristics and its association with chronic complications in type 2 diabetes mellitus (T2DM) patients. METHODS: Eighty-one prospectively enrolled T2DM patients were divided into non-alcoholic fatty liver disease (NAFLD) group and the non-NAFLD group according to the presence of NAFL complications. LFC was determined by MRI IDEAL-IQ Sequence, and patients were divided into 4 groups according to LFC by quartile method. Basic information, metabolic indexes, and occurrence of chronic complications in different groups were analyzed and compared. RESULTS: BMI, SBP, DBP, TG, ALT, AST, GGT, UA, HbA1c, FCP, 2 h CP, HOMA-IR, and HOMA-IS in the NAFLD group were significantly higher than the non-NAFLD group (P < 0.05). The incidences of chronic complications in the NAFLD group were higher than in the non-NAFLD group but not statistically significant (P > 0.05). BMI, SBP, DBP, TC, TG, ALT, AST, FCP, 2 h CP, HOMA-IR, and HOMA-IS showed significant differences between the patients with different LFC, and these indexes were significantly higher in patients with higher LFC than those with lower LFC (P < 0.05). Moreover, diabetes duration, TC, HOMA-IR, and LFC were the risk factors for ASCVD complications, while diabetes duration, TG, and LDL-C were risk factors for DN complications. Also, diabetes duration and SBP were risk factors for both DR and DPN complications in T2DM patients (P < 0.05). CONCLUSION: LFC is positively correlated with the severity of the systemic metabolic disorder and chronic complications in T2DM patients.

Risk Factors for Lymphovascular Invasion in Invasive Ductal Carcinoma Based on Clinical and Preoperative Breast MRI Features: a Retrospective Study.

RATIONALE AND OBJECTIVES: Lymphovascular invasion (LVI) plays an important role in the prediction of metastasis and prognosis in breast cancer (BC) patients. The present study assessed correlations between preoperative breast MRI, clinical features, and LVI in patients with invasive ductal carcinoma (IDC) and identified risk factors based on these correlation factors. MATERIALS AND METHODS: Patients confirmed with IDC between 01/2012 and 12/2021 were retrospectively reviewed at our hospital. A total of 5 clinical and 14 MRI features to characterize tumours were extracted. LVI evaluated in hematoxylin and eosin sections. T-test and chi-square tests were used to compare the differences in clinical and MRI features between the LVI positive and negative groups. The associations between individual features and LVI were analysed by univariable logistic regression analysis, and risk factors for LVI were identified by multivariable logistic regression analysis based on these correlation factors. RESULTS: This study included 353 patients with IDC, including 130 with positive LVI. Age, CEA, CA-153, amount of fibroglandular tissue (FGT), background parenchymal enhancement, tumour size, shape, skin thickening, nipple retraction, adjacent vessel sign, and axillary lymph node (ALN) size in the LVI positive group were significantly different from the LVI negative group (all p<0.05). Multivariate logistic regression analysis revealed that age (odds ratio OR = 1.030), CA-153 (OR = 1.018), heterogeneous FGT (OR = 2.484), shape (OR = 2.157), and ALN size (OR = 1.051) were risk factors for LVI (all p<0.05). CONCLUSION: Preoperative breast MRI and clinical features correlated with LVI, age, CA-153, heterogeneous FGT, shape, and ALN size are risk factors for LVI in patients with IDC.

Preliminary Feasibility Study on Diffusion Kurtosis Imaging to Monitor the Early Functional Alterations of Kidneys in Streptozocin-Induced Diabetic Rats.

RATIONALE AND OBJECTIVES: The aim of this study was to investigate the potential of diffusion kurtosis imaging (DKI) to assess the early renal functional undulation of diabetic mellitus (DM). MATERIALS AND METHODS: Fifty-seven Sprague-Dawley (SD) rats were randomly divided into two groups and eventually 48 rats were included in this study: the normal control (CON) group and diabetic mellitus (DM) group. Weeks 0, 4, 8, and 12 after the diabetes model was successfully established, all the rats were scanned on the 3.0T MRI. The DKI derived parameters of renal parenchyma, including fractional anisotropy (FAco, FAme), mean diffusivity (MDco, MDme), and mean kurtosis (MKco, MKme) were measured. Their alteration over time was analyzed and then correlated with urine volume (UV), blood urea nitrogen (BUN), and serum creatinine (Scr) using Pearson correlation analysis. Finally, hematoxylin and eosin (H&E) staining was performed on the kidneys of the two groups. RESULT: There was a decreasing trend in FA, MK, and MD values over time in diabetic rats. Also, the gradually worsening histological damage of kidneys was noted over time in diabetic rats. The cortical FA and MK values and medullary FA, MK and MD values of diabetic rats were significantly lower than those of controls at most time points after DM induction. In addition, negative correlations were revealed between the BUN and FAco (r = -0.43, p = 0.03) or FAme value (r = -0.49, p = 0.01). The cortical MK value was moderately correlated with UV (r = -0.46, p = 0.03) and BUN (r = -0.55, p = 0.01). CONCLUSION: The preliminary findings suggest that DKI might be an effective and sensitive tool to assess the early changes of renal function impairment in diabetic rats. The FA values of the cortex and medulla and the MK value of the cortex are sensitive markers in detecting renal injury in diabetic rats.

CuS NP-based nanocomposite with photothermal and augmented-photodynamic activity for magnetic resonance imaging-guided tumor synergistic therapy.

Although many treatments have been developed for oncotherapy, the lack of effective imaging guidance in the therapeutic process is still an urgent problem to be solved. In this study, magnetic resonance contrast agent (Gd) chelated on CuS nanoparticles and glucose oxidase (GOx) were coloaded into mesoporous silica nanoparticles (MSNs) to form GOx-Gd-CuS@MSNs, in which the Gd provided magnetic resonance imaging (MRI) for therapeutic process monitor while GOx could catalyze the generation of H2O2 to enhance the photodynamic therapy (PDT). The in vitro results show that under near-infrared (NIR) laser irradiation (2 W·cm-2, 5 min), temperature rapidly increased by approximately 30 °C for the accumulation of heat. At the same time, GOx on GOx-Gd-CuS@MSNs effectively consumed glucose to produce a large amount of H2O2, which was used to augment PDT through producing highly toxic hydroxyl radicals (·OH) and singlet oxygen (1O2). The photothermal and augmented-photodynamic could induce apoptosis and death of tumor cells. More importantly, the study found that GOx-Gd-CuS@MSNs had MRI performance, which provided imaging guidance during the treatment process, and it can monitor the diffusion of water molecules in the tumor tissue during the treatment and microcirculation perfusion of capillary network. These results indicate that the nanomaterial produced significant synergistic therapeutic effects through photothermal and photodynamic forces, meanwhile showed excellent spatial resolution and deep tissue penetration in imaging.

Multiparametric MRI analysis for the evaluation of renal function in patients with hyperuricemia: a preliminary study.

BACKGROUND: To investigate the renal dysfunction in patients with hyperuricemia by employing a multiparametric MRI protocol, consisting of quantitative water molecule diffusion, microstructure, microscopic perfusion, and oxygenation measurements in kidneys. MATERIALS AND METHODS: A total of 48 patients with hyperuricemia (HU) and 22 age-matched healthy control subjects (HC) were enrolled in the study. For each participant, three different functional magnetic resonance imaging (fMRI) sequences were acquired and analyzed, including intravoxel incoherent motion imaging (IVIM), diffusion tensor imaging (DTI), and blood-oxygen-level-dependent MRI (BOLD). Thereafter, an independent two-sample t-test was applied to discover the significant differences of MRI indices between the hyperuricemia (HU) and HC groups, and the specific potential biomarkers between two subgroups of HU group (asymptomatic hyperuricemia group (AH) and gouty arthritis group (GA)). Further, multivariate logistic regression analyses were performed to classify the AH from the GA group using the MRI indices with significant between-group differences. The receiver operating characteristic (ROC) curve was plotted, and the area under the ROC curve (AUC) was calculated to assess the performance of each MR index for differentiation between the AH and GA groups. RESULTS: Ten parametric values of the HU group were significantly lower than those of the HC group among the 14 fMRI parameters (P < 0.05). The cortical D, D*, and f values and medullary D and R2*values had significant differences between the AH and GA groups (P < 0.05). Combining the cortical D and f values and medullary R2* value gave the best diagnostic efficacy, yielding an AUC, sensitivity, and specificity of 0.967 ± 0.022, 91.67%, and 95.83%, respectively. CONCLUSIONS: A multiparametric MR analysis plays an important role in the evaluation of renal dysfunction in hyperuricemia from multiple perspectives. It could be a promising method for noninvasive detection and identification of the early-stage renal damage induced by hyperuricemia.

Non-invasive investigation of early kidney damage in streptozotocin-induced diabetic rats by intravoxel incoherent motion diffusion-weighted (IVIM) MRI.

BACKGROUND: The current study investigated the performance of intravoxel incoherent motion diffusion (IVIM) technology in monitoring early renal injury in streptozotocin rats. METHODS: Forty-eight Sprague-Dawley (SD) rats were divided into a control group and a diabetic mellitus (DM) group. Six rats in each group were randomly selected for MR scans at four different time points (0, 4, 8, and 12 weeks). The IVIM-derived parameters (D, D*, f and ADC values) of the renal cortex (CO), outer and inner stripe of the outer medulla (OS, IS), and internal medulla (IM) were acquired. Changes in each IVIM-derived parameter over time were analyzed, and differences between the two groups at each point were assessed. The associations between the IVIM parameters and IV collagen expression, urine volume (UV), blood urea nitrogen (BUN), and serum creatinine (Scr) were investigated. RESULTS: The D and D* values of CO and the ADC values of CO, OS, IS and IM displayed significantly different trends between the two groups over time (P<0.05). In addition, significant correlations were discovered between the D* value of CO and UV and BUN (r=0.527, P=0.033; r=0.617, P=0.005), between the ADC value of IM and BUN (r=0.557, P=0.019) and between the f value of IM and BUN (r=0.527, P=0.033). No correlation was found between IVIM parameters and IV collagen expression and Scr. CONCLUSIONS: IVIM is a potential sensitive and noninvasive technology for the simultaneous assessment of early renal cortical and medullary injuries induced by diabetes.

Development and Validation of a Machine Learning Approach for Automated Severity Assessment of COVID-19 Based on Clinical and Imaging Data: Retrospective Study.

BACKGROUND: COVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated. OBJECTIVE: This study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data. METHODS: Clinical data-including demographics, signs, symptoms, comorbidities, and blood test results-and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework. RESULTS: Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929). CONCLUSIONS: Clinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease.

Combined application of DTI and BOLD-MRI in the assessment of renal injury with hyperuricemia.

OBJECTIVE: To explore the value of combined diffusion tensor imaging (DTI) and blood oxygenation level-dependent magnetic resonance imaging (BOLD-MRI) in detecting early renal alterations in patients with hyperuricemia. MATERIALS AND METHODS: Seventy-one individuals were enrolled in this study and divided into three groups according to their serum uric acid (SUA) level and clinical symptoms: healthy controls (HC, n = 23), asymptomatic hyperuricemia (AH, n = 22) and gouty arthritis (GA, n = 26). All patients underwent both DTI and BOLD-MRI examination. Renal cortical and medullary ADC, FA and R2* values were calculated, respectively, and compared among the three groups. Correlations between ADC, FA and R2* with estimated glomerular filtration rate (eGFR) and SUA in hyperuricemia were evaluated, respectively. RESULT: In the renal cortex, the ADC, FA and R2* values of the AH and GA groups were significantly lower than those of the HC groups (p < 0.05). In the renal medulla, the ADC and FA values in AH and GA patients were significantly lower than those in healthy controls (p < 0.05). The R2* value of the GA group significantly decreased, compared to that of the AH and HC groups (p < 0.05). SUA was negatively correlated with cortical ADC, FA and R2* values (p < 0.05) as well as with medullary ADC and FA values. No significant correlation was discovered between the eGFR and ADC, FA and R2* values. CONCLUSION: The combined evaluation of DTI and BOLD might provide a sensitive and non-invasive approach for detection of renal microstructural alterations and oxygen metabolism abnormality in hyperuricemia.

Epithelioid hemangioendothelioma of spine: A case report with review of literatures.

Primary epithelioid hemangioendothelioma of the spine is the extremely rare malignant vascular neoplasm with an unpredictable outcome. A case of epithelioid hemangioendothelioma with multiple lytic lesions of thoracolumbar spine and other bones in a 29-year-old male patient is reported. A review of the published data regarding this rare neoplasm is also presented. The features of epithelioid hemangioendothelioma include the occurrence in the young male patient, multiple osteolytic lesions with thin sclerotic rim and hypermetabolic activities. However, its imaging features are not specific. Positron emission tomography/computed tomography is essential for identification of the lesions and subsequent follow-up for treatment.

Intravoxel incoherent motion imaging of the kidney: The application in patients with hyperuricemia.

BACKGROUND: Hyperuricemia is an independent risk factor for onset and progression of kidney disease. However, there remains a lack of a reliable and noninvasive biomarker to identify and monitor the changes of renal function in patients with hyperuricemia. PURPOSE: To assess the utility of intravoxel incoherent motion (IVIM) parameters in identifying the early changes of renal function in patients with hyperuricemia. STUDY TYPE: Retrospective case-control study. POPULATION: Eighty-four male participants, including asymptomatic hyperuricemia (AH, 27 cases), gouty arthritis (GA, 31 cases), and 26 age-matched healthy controls. FIELD STRENGTH/SEQUENCE: 3.0T; intravoxel incoherent motion (IVIM). ASSESSMENT: Differences in the IVIM parameters among the three groups were assessed. Pure molecular diffusion (D value); perfusion-related diffusion (D* value); pseudodiffusion fraction (f value); apparent diffusion coefficient (ADC value); estimated glomerular filtration rate (eGFR). Also, they were correlated with eGFR. STATISTICAL TESTS: Bonferroni test, Tamhane's T2 method, and Pearson correlation analysis. RESULTS: The D values in renal cortex and medulla significantly decreased from the control, AH to GA groups (P < 0.05). The GA patients had a significantly lower cortical f value than the controls and AH patients (P < 0.05). The medullary f values in the AH and GA patients were significantly lower than that in the controls (P < 0.05). Also, the cortical and medullary ADC values had similar results across the three groups (P < 0.05), except for the comparison between the AH and GA groups (P = 0.668, P = 0.111, respectively). No significant correlation was found between any IVIM parameters with eGFR. DATA CONCLUSION: IVIM imaging may be helpful for detecting the early changes of renal function induced by hyperuricemia. The D value could be the most sensitive IVIM-derived parameter in the assessment of renal function in patients with hyperuricemia in this study. LEVEL OF EVIDENCE: 3 Technical Efficacy Stage: 3 J. Magn. Reson. Imaging 2020;51:833-840.

Diffusional kurtosis imaging of kidneys in patients with hyperuricemia: initial study.

BACKGROUND: At present, there remains a lack of a reliable indicator for monitoring renal function in patients with hyperuricemia. PURPOSE: This study aimed to evaluate the feasibility of diffusion kurtosis imaging in the assessment of renal function in patients with hyperuricemia. MATERIAL AND METHODS: A total of 75 male participants, including 25 with asymptomatic hyperuricemia, 25 with gouty arthritis, and 25 age-matched male healthy controls, were enrolled in this study. Diffusion kurtosis imaging data were acquired to derive axial (Ka), radial (Kr), and mean kurtosis (MK), fractional anisotropy, axial (Da), radial (Dr), and mean diffusivity (MD) for comparisons among the three groups. They were also correlated with estimated glomerular filtration rate (eGFR). RESULTS: The MK values of the renal cortex and medulla and Kr value of the renal medulla in patients with asymptomatic hyperuricemia and gouty arthritis significantly increased compared with those in the controls (P < 0.05). Patients with gouty arthritis showed significant higher cortical and medullary Ka values compared with the other two groups (P < 0.05). The cortical Kr values of the asymptomatic hyperuricemia and gouty arthritis patients were significantly higher than that of the controls (P < 0.05). The medullary fractional anisotropy value showed a significant difference between the control and gouty arthritis groups (P < 0.05). No correlation was found between any diffusion kurtosis imaging parameters and eGFR value. CONCLUSION: Diffusion kurtosis imaging is feasible in the assessment of the early changes of renal cortex and medulla in patients with hyperuricemia.

Non-invasive assessment of early stage diabetic nephropathy by DTI and BOLD MRI.

OBJECTIVE: Patients with diabetes mellitus, diabetic nephropathy (DN) and healthy donor were analyzed to test whether the early DN patients can be detected using both blood oxygenation level dependent (BOLD) and diffusion tensor imaging. METHODS: This study was approved by the Ethics Committee of our hospital. MR images were acquired on a 3.0-Tesla MR system (Discovery MR750, General Electric, Milwaukee, WI). 30 diabetic patients were divided into NAU (normal to mildly increased albuminuria, N = 15) and MAU (moderately increased albuminuria, N = 15) group based on the absence or presence of microalbuminuria. 15 controls with sex- and age-matched were enrolled in the study. Prior to MRI scan, all participants were instructed to collect their fresh morning urine samples for quantitative measurement of urinary microalbumin and urinary creatinine. Then, the estimations of serum creatinine, serum uric acid, HbAlc and fasting plasma glucose as well as fundus examinations were performed in all subjects. Then, the values of albumin-creatinine ratio (ACR) and estimated glomerular filtration rate were also calculated. All subjects underwent renal diffusion tensor imaging (DTI) and BOLD acquisition after fasting for 4 h. Regions of interest were placed in renal medulla and cortex for evaluating apparent diffusion coefficient (ADC), fractional anisotropy (FA) and R2* values by two experienced radiologists. The consistency between the two observations was estimated using intragroup correlation coefficients. To test differences in ADC, FA and R2* values across the three groups, the data were analyzed using separate one-way ANOVAs. Post-hoc pair wise comparisons were then performed using t-test. To investigate the clinical relevance of imaging parameters in both regions across the three groups, the correlations of values of the ACR/estimated glomerular filtration rate and of the ADC/FA/R2* were calculated. RESULTS: There was a high level of consistency of those ADC, FA and R2* values across the three groups on both renal cortex and medulla measured by the two doctors. The FA value of medulla in MAU group was lower than that in control (p < 0.01). The R2* value of medulla in the NAU group was higher than that in the control (p < 0.01), and the R2* value of medulla in the MAU group was lower than that in the control (p = 0.009) . Moreover, the current study revealed a decreasing trend in FA values of the renal medulla from the control group to NAU and MAU groups. Finally, a weak negatively correlation between medullary R2* and ACR was found in current study. CONCLUSION: Medullary R2* value might be a new more sensitive predictor of early DN. Meanwhile, BOLD imaging detected the medullary hypoxia at the simply diabetic stage, while DTI didn't identify the medullary directional diffusion changes at this stage. Based on our assumption mentioned above, it's presumable that BOLD imaging may be more sensitive for assessment of the early renal function changes than DTI. These imaging techniques are more accurate and practical than conventional tests. ADVANCES IN KNOWLEDGE: Non-invasive MRI was used to detect renal function changes at early DN stage.