Abstract Objectives To validate blood oxygen level-dependent MRI (BOLD-MRI) for non-invasive discrimination of diabetic nephropathy (DN) vs non-diabetic renal disease (NDRD) and prediction of end-stage renal disease (ESRD) in diabetic kidney disease (DKD). Materials and methods A prospective cohort of 133 biopsy-proven DKD patients underwent BOLD-MRI. The semi-automated 12-layer concentric-objects method was used to analyze BOLD-MRI variables. Prognostic markers for ESRD were identified using univariate and multivariate Cox regression. Feature importance was used to select key diagnostic variables and establish logistic regression and machine-learning differential diagnosis models. Results Among 133 patients (44 DN, 55 NDRD, 34 combined), 20 (15.5%) progressed to ESRD over a mean of 21.8 months. Higher renal medullary R2* (MR2*) (> 24 1/s) reduced ESRD risk by 52% (HR, 0.48) in DKD. Prognostic models integrating pathological grouping, hemoglobin levels, and cysC levels achieved a c-index of 0.90. For the DN and combined groups, MR2*, glomerular grading, interstitial lesions, interstitial fibrosis, and tubular atrophy were predictive of ESRD, with a c-index of 0.91. For differential diagnosis, the random forest (RF) model achieved an AUC of 0.901, with diabetic retinopathy, diabetes duration, albumin, blood urea nitrogen, MR2*, hypertension, and glycosylated hemoglobin as the most contributing factors. For the combined group classified as DN, the AUC of the RF model was 0.791; when classified as NDRD, the AUC was 0.856. Conclusion MR2* shows potential value as a non-invasive diagnostic and prognostic tool in the assessment of DKD. However, BOLD-MRI remains a promising yet exploratory technique that requires external validation and interventional studies before clinical implementation. Critical relevance statement Blood oxygen level-dependent-MRI-derived renal medullary R2* robustly predicts ESRD risk and distinguishes DN without biopsy, offering an immediately translatable, non-invasive biomarker for the precision management of DKD in routine nephrology practice. Trial registration ClinicalTrials.gov, NCT03865914. Key Points Blood oxygen level-dependent-MRI medullary R2*(MR2*) > 24 s− 1 halves DKD ESRD risk (HR 0.48). MR2* integrated with clinical variables drives c-index to 0.90 for ESRD prognosis. RF leveraging MR2* and clinical traits attains an AUC of 0.901 for diagnosing DN. Graphical Abstract

BACKGROUND:Although the clear cell likelihood score (ccLS) v2.0 demonstrates high specificity for clear cell renal cell carcinoma (ccRCC), its performance to characterize general malignancy in small renal masses (SRMs) remains limited. PURPOSE:To develop and validate a modified clear cell likelihood score (m-ccLS) incorporating the pseudocapsule to improve malignancy detection in SRMs while preserving specificity for diagnosing ccRCC. STUDY TYPE:This study was retrospective in type. SUBJECTS:352 patients with pathologically proven SRMs were included: development (n = 235), internal validation (n = 60), and external validation (n = 57). FIELD STRENGTH/SEQUENCE:Imaging was performed at 3.0 and 1.5 T using fast spin-echo T2-weighted imaging, single-shot echo planar diffusion-weighted imaging, 3D spoiled gradient echo (GRE) T1-weighted dynamic contrast-enhanced imaging, and in- and opposed-phase using T1-weighted GRE. ASSESSMENT:14 radiologists blinded to histopathology independently evaluated each SRM using ccLS v2.0 and m-ccLS scores in separate reading sessions; four, five, and five readers interpreted the development, internal, and external cohorts, respectively. STATISTICAL TESTS:Random-effects logistic regression, receiver operating characteristic curve, DeLong test, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and Fleiss Kappa test were used. The statistical significance level was p < 0.05. RESULTS:For malignancy detection, m-ccLS showed a significantly higher area under the curve (AUC) than ccLS v2.0 across the development (0.850 vs. 0.772), internal validation (0.856 vs. 0.779), and external validation (0.803 vs. 0.720) cohorts with improved classification (NRI = 0.270, 0.045, and 0.028) and discrimination (IDI = 0.132, 0.206, and 0.120). For diagnosing ccRCC, m-ccLS and ccLS v2.0 showed similar results (0.908 vs. 0.894, p = 0.250; 0.912 vs. 0.898, p = 0.134; 0.865 vs. 0.838, p = 0.065) in development, internal, and external validation cohorts, respectively. m-ccLS category 3 contained fewer ccRCCs (33.3% vs. 72.5%; 15.8% vs. 47.2%; 7.6% vs. 26.9%) and malignancies (79.2% vs. 88.7%; 71.6% vs. 73.0%; 55.4% vs. 63.9%) than ccLS v2.0 category 3. DATA CONCLUSION:m-ccLS improves malignancy detection in SRMs compared with ccLS v2.0 without impairing diagnostic performance for ccRCC. EVIDENCE LEVEL:4. TECHNICAL EFFICACY:Stage 2.

To develop a grading system integrating MRI and clinicopathological features for predicting positive surgical margin (PSM) following robotic-assisted laparoscopic prostatectomy (RALP) among patients with prostate cancer. Patients undergoing RALP were retrospectively included with consecutive MRI examinations collected from two centers (center 1 and center 2). The train cohort included patients at center 1 between January 2020 and December 2021, and the validation cohort comprised those between January 2022 and December 2022. Patients from center 2 were assigned to the test cohort. MRI and clinicopathological features associated with PSM were assessed. A logistic regression model was used to develop the grading system. The prediction and calibration performance were evaluated by area under the receiver operating characteristic curves (AUCs) and Hosmer-Lemeshow goodness-of-fit test. AUC values were compared by Delong test. A total of 396 patients and 29.2

To evaluate whether MRI characteristics of septa and walls—specifically enhancement patterns during the corticomedullary (CP), nephrographic (NP), and excretory (EP) phases—can improve malignancy risk stratification in Bosniak III cystic renal masses (CRMs). This single-center, retrospective study analyzed 120 patients with Bosniak III cystic renal masses who underwent renal MRI between January 2009 and December 2021. The cohort included two subcategories: III-WS (enhancing thick wall/septa ≥ 4 mm; n = 22) and III-OP (enhancing irregular wall/septa or convex protrusion ≤ 3 mm; n = 98). All lesions were confirmed either by histopathology (115 CRMs) or ≥ 5 year stability (5 CRMs). Four radiologists (2 senior, 2 junior), blinded to clinical and pathological data, independently assessed septal and wall enhancement (obvious vs. non-obvious) across CP, NP) and EP, a consensus was reached through discussion. Interobserver agreement was evaluated using Conger’s kappa, while diagnostic performance (AUC, sensitivity, specificity, accuracy) of obvious enhancement was assessed via ROC analysis, with AUC comparisons performed using DeLong’s test. The study included 120 patients (mean age: 48 ± 11 years; 94 male), with 95 (79.2

To develop and validate a lesion-based grading system using clinicopathological and MRI features for predicting positive surgical margin (PSM) following robotic-assisted laparoscopic prostatectomy (RALP) among prostate cancer (PCa) patients. Consecutive MRI examinations of patients undergoing RALP for PCa were retrospectively collected from two medical institutions. Patients from center 1 undergoing RALP between January 2020 and December 2021 were included in the derivation cohort and those between January 2022 and December 2022 were allocated to the validation cohort. Patients from center 2 were assigned to the test cohort. PSM associated imaging and clinicopathological predictors were assessed. A grading system was developed through fixed effect logistic regression and classification and regression tree analysis. The area under the curve (AUC), sensitivity and specificity were calculated and compared by Delong test and McNemar test. A total 489 lesions from 396 patients were included and 82 (29.1

BACKGROUND:T1-hyperintensity in cystic renal masses (CRMs) complicates Bosniak classification assessment due to inherent signal interference from hemorrhage and proteinaceous content, potentially obscuring enhancement visibility. PURPOSE:To investigate whether MR subtraction imaging improves interobserver agreement and diagnostic performance in the Bosniak classification of T1-hyperintense CRMs. STUDY TYPE:Retrospective. POPULATION:A total of 139 consecutive patients (mean age, 50 ± 12 years; 97 males) with 141 T1-hyperintense CRMs were included, consisting of surgically confirmed 133 lesions and clinically diagnosed 8 benign CRMs that were stable during follow-up (≥ 5 years). FIELD STRENGTH/SEQUENCE:1.5/3 T. fat-saturated T2-weighted imaging, diffusion-weighted imaging, unenhanced, and triphasic dynamic contrast-enhanced T1-weighted imaging (T1WI). Subtraction images were generated automatically by subtracting unenhanced from triphasic contrast-enhanced T1WI. ASSESSMENT:Six radiologists (half less experienced) independently classified all T1-hyperintense CRMs using the Bosniak classification (v2019) in two sessions, with and without subtraction imaging. A 1-month washout period was implemented between sessions, and the order of cases was re-randomized. Interobserver agreement and diagnostic performance were evaluated in all experienced and less experienced readers. STATISTICAL TESTS:Weighted κ statistics assessed interobserver agreement. Diagnostic performance (the area under the curve [AUC], sensitivity, specificity) was compared using Delong and McNemar tests. Statistical significance was defined as p < 0.05. RESULTS:Subtraction imaging significantly improved interobserver agreement in all radiologists (weighted κ = 0.62 vs. 0.46), and less experienced radiologists (3-5 years of experience, weighted κ = 0.63 vs. 0.42), though not significantly among experienced radiologists (10-15 years of experience, weighted κ = 0.61 vs. 0.52; p = 0.051). Less experienced radiologists showed significantly higher AUC (0.865 vs. 0.804), sensitivity (88.9% vs. 75.5%), and specificity (88.2% vs. 72.5%) with MR subtraction imaging. DATA CONCLUSION:MR subtraction imaging may improve overall interobserver agreement in the Bosniak classification of T1-hyperintense CRMs. Furthermore, it could improve diagnostic accuracy and interobserver agreement among less experienced radiologists. EVIDENCE LEVEL:4. TECHNICAL EFFICACY:Stage 2.

BACKGROUND:MRI assessment for extraprostatic extension (EPE) of prostate cancer (PCa) is challenging due to limited accuracy and interobserver agreement. PURPOSE:To develop an interpretable Tabular Prior-data Fitted Network (TabPFN)-based radiomics model to evaluate EPE using MRI and explore its integration with radiologists' assessments. STUDY TYPE:Retrospective. POPULATION:Five hundred and thirteen consecutive patients who underwent radical prostatectomy. Four hundred and eleven patients from center 1 (mean age 67 ± 7 years) formed training (287 patients) and internal test (124 patients) sets, and 102 patients from center 2 (mean age 66 ± 6 years) were assigned as an external test set. FIELD STRENGTH/SEQUENCE:Three Tesla, fast spin echo T2-weighted imaging (T2WI) and diffusion-weighted imaging using single-shot echo planar imaging. ASSESSMENT:Radiomics features were extracted from T2WI and apparent diffusion coefficient maps, and the TabRadiomics model was developed using TabPFN. Three machine learning models served as baseline comparisons: support vector machine, random forest, and categorical boosting. Two radiologists (with > 1500 and > 500 prostate MRI interpretations, respectively) independently evaluated EPE grade on MRI. Artificial intelligence (AI)-modified EPE grading algorithms incorporating the TabRadiomics model with radiologists' interpretations of curvilinear contact length and frank EPE were simulated. STATISTICAL TESTS:Receiver operating characteristic curve (AUC), Delong test, and McNemar test. p < 0.05 was considered significant. RESULTS:The TabRadiomics model performed comparably to machine learning models in both internal and external tests, with AUCs of 0.806 (95% CI, 0.727-0.884) and 0.842 (95% CI, 0.770-0.912), respectively. AI-modified algorithms showed significantly higher accuracies compared with the less experienced reader in internal testing, with up to 34.7% of interpretations requiring no radiologist input. However, no difference was observed in both readers in the external test set. DATA CONCLUSIONS:The TabRadiomics model demonstrated high performance in EPE assessment and may improve clinical assessment in PCa. EVIDENCE LEVEL:4. TECHNICAL EFFICACY:Stage 2.

To evaluate the diagnostic value of the clear cell likelihood score (ccLS) integrated with cystic degeneration or necrosis on renal MR imaging for diagnosing clear cell renal cell carcinoma (ccRCC) in cT1 solid renal masses (SRMs). This retrospective study consecutively enrolled patients with pathologically confirmed SRMs who underwent MRI at the First Medical Center of the Chinese PLA General Hospital between January 2022 and February 2024. Three radiologists independently scored all cT1 SRMs using ccLS and ccLS integrated with cystic degeneration or necrosis (cn-ccLS), with discrepancies reconciled by consensus. Sensitivity, specificity, and accuracy were used to assess the performance of ccLS and cn-ccLS. A total of 287 patients with 293 masses were included in this study. The sample comprised 229 ccRCCs (78

To evaluate the value of preoperative intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) and conventional MRI indicators in identifying sarcomatoid dedifferentiation in renal cell carcinoma (RCC) and tumor thrombus. From September 2016 to April 2023, consecutive patients with RCC and tumor thrombus who received routine MRI examination and IVIM-DWI before radical resection were enrolled prospectively. Kaplan–Meier method with log-rank test was used to calculate and compare the survival probability. The preoperative imaging features were analyzed. Univariate and multivariable logistic regression analyses were employed to identify independent predictors of sarcomatoid dedifferentiation. The predictive ability was evaluated by receiver operating characteristic (ROC) curves. Twenty-two patients (15.3

BACKGROUND:Identification of non-diabetic renal disease (NDRD) in patients with type 2 diabetes mellitus (T2DM) may help tailor treatment. Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) is a promising tool to evaluate renal function but its potential role in the clinical differentiation between diabetic nephropathy (DN) and NDRD remains unclear. PURPOSE:To investigate the added role of IVIM-DWI in the differential diagnosis between DN and NDRD in patients with T2DM. STUDY TYPE:Prospective. POPULATION:Sixty-three patients with T2DM (ages: 22-69 years, 17 females) confirmed by renal biopsy divided into two subgroups (28 DN and 35 NDRD). FIELD STRENGTH/SEQUENCE:3 T/ T2 weighted imaging (T2WI), and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI). ASSESSMENT:The parameters derived from IVIM-DWI (true diffusion coefficient [D], pseudo-diffusion coefficient [D*], and pseudo-diffusion fraction [f]) were calculated for the cortex and medulla, respectively. The clinical indexes related to renal function (eg cystatin C, etc.) and diabetes (eg diabetic retinopathy [DR], fasting blood glucose, etc.) were measured and calculated within 1 week before MRI scanning. The clinical model based on clinical indexes and the IVIM-based model based on IVIM parameters and clinical indexes were established and evaluated, respectively. STATISTICAL TESTS:Student's t-test; Mann-Whitney U test; Fisher's exact test; Chi-squared test; Intraclass correlation coefficient; Receiver operating characteristic analysis; Hosmer-Lemeshow test; DeLong's test. P < 0.05 was considered statistically significant. RESULTS:The cortex D*, DR, and cystatin C values were identified as independent predictors of NDRD in multivariable analysis. The IVIM-based model, comprising DR, cystatin C, and cortex D*, significantly outperformed the clinical model containing only DR, and cystatin C (AUC = 0.934, 0.845, respectively). DATA CONCLUSION:The IVIM parameters, especially the renal cortex D* value, might serve as novel indicators in the differential diagnosis between DN and NDRD in patients with T2DM. EVIDENCE LEVEL:2 TECHNICAL EFFICACY: Stage 2.

To differentiate mixed epithelial and stromal tumor family (MESTF) of the kidney from predominantly cystic renal cell carcinoma (RCC) using the magnetic resonance imaging (MRI)-based Bosniak classification system version 2019 (v2019). The study included 36 consecutive patients with MESTF and 77 with predominantly cystic RCC who underwent preoperative renal MRI. One radiologist evaluated and documented the clinical and MRI characteristics (age, sex, laterality, R.E.N.A.L. Nephrometry Score [RNS], surgical approach, the signal intensity on T2-weighted imaging, restricted diffusion and enhancement features in corticomedullary phase). Blinded to clinical and pathological information, another two radiologists independently evaluated Bosniak category of all masses. Interobserver agreement based on Bosniak classification system v2019 was measured by the weighted Cohen/Conger’s Kappa coefficient. Furthermore, predominantly cystic RCCs and MESTFs were divided into low (categories I, II, and IIF) and high-class (categories III, and IV) tumors. The independent sample t test (Mann–Whitney U test) or Pearson Chi-square test (Fisher’s exact probability test) was utilized to compare clinical and imaging characteristics between MESTFs and predominantly cystic RCCs. The performance of the Bosniak classification system v2019 in distinguishing MESTF from predominantly cystic RCC was investigated via receiver operating characteristic curve analysis. MESTF and predominantly cystic RCC groups significantly differed in terms of age, lesion size, RNS, restricted diffusion, and obvious enhancement in corticomedullary phase, but not sex, laterality, surgical approach, and the signal intensity on T2WI. Interobserver agreement was substantially based on the Bosniak classification system v2019. There were 24 low-class tumors and 12 high-class tumors in the MESTF group. Meanwhile, 13 low-class tumors and 64 high-class tumors were observed in the predominantly cystic RCC group. The distribution of low- or high-class tumors significantly differed between the MESTF and predominantly cystic RCC groups. Bosniak classification system v2019 had excellent discrimination (cutoff value = category III), and an area under curve value was 0.81; accuracy, 80.5

Background Fibrosis has important pathoetiological and prognostic roles in chronic liver disease. This study evaluates the role of radiomics in staging liver fibrosis.Method After literature search in electronic databases (Embase, Ovid, Science Direct, Springer, and Web of Science), studies were selected by following precise eligibility criteria. The quality of included studies was assessed, and meta-analyses were performed to achieve pooled estimates of area under receiver-operator curve (AUROC), accuracy, sensitivity, and specificity of radiomics in staging liver fibrosis compared to histopathology.Results Fifteen studies (3718 patients; age 47 years [95% confidence interval (CI): 42, 53]; 69% [95% CI: 65, 73] males) were included. AUROC values of radiomics for detecting significant fibrosis (F2-4), advanced fibrosis (F3-4), and cirrhosis (F4) were 0.91 [95%CI: 0.89, 0.94], 0.92 [95%CI: 0.90, 0.95], and 0.94 [95%CI: 0.93, 0.96] in training cohorts and 0.89 [95%CI: 0.83, 0.91], 0.89 [95%CI: 0.83, 0.94], and 0.93 [95%CI: 0.91, 0.95] in validation cohorts, respectively. For diagnosing significant fibrosis, advanced fibrosis, and cirrhosis the sensitivity of radiomics was 84.0% [95%CI: 76.1, 91.9], 86.9% [95%CI: 76.8, 97.0], and 92.7% [95%CI: 89.7, 95.7] in training cohorts, and 75.6% [95%CI: 67.7, 83.5], 80.0% [95%CI: 70.7, 89.3], and 92.0% [95%CI: 87.8, 96.1] in validation cohorts, respectively. Respective specificity was 88.6% [95% CI: 83.0, 94.2], 88.4% [95% CI: 81.9, 94.8], and 91.1% [95% CI: 86.8, 95.5] in training cohorts, and 86.8% [95% CI: 83.3, 90.3], 94.0% [95% CI: 89.5, 98.4], and 88.3% [95% CI: 84.4, 92.2] in validation cohorts. Limitations included use of several methods for feature selection and classification, less availability of studies evaluating a particular radiological modality, lack of a direct comparison between radiology and radiomics, and lack of external validation.Conclusion Although radiomics offers good diagnostic accuracy in detecting liver fibrosis, its role in clinical practice is not as clear at present due to comparability and validation constraints.

BackgroundClear cell likelihood score (ccLS) is reliable for diagnosing small renal masses (SRMs). However, the diagnostic value of Clear cell likelihood score version 1.0 (ccLS v1.0) and v2.0 for common subtypes of SRMs might be a potential score extension.PurposeTo compare the diagnostic performance and interobserver agreement of ccLS v1.0 and v2.0 for characterizing five common subtypes of SRMs.Study TypeRetrospective.Population797 patients (563 males, 234 females; mean age, 53 ± 12 years) with 867 histologically proven renal masses.Field Strength/Sequences3.0 and 1.5 T/T2 weighted imaging, T1 weighted imaging, diffusion‐weighted imaging, a dual‐echo chemical shift (in‐ and opposed‐phase) T1 weighted imaging, multiphase dynamic contrast‐enhanced imaging.AssessmentSix abdominal radiologists were trained in the ccLS algorithm and independently scored each SRM using ccLS v1.0 and v2.0, respectively. All SRMs had definite pathological results. The pooled area under curve (AUC), accuracy, sensitivity, and specificity were calculated to evaluate the diagnostic performance of ccLS v1.0 and v2.0 for characterizing common subtypes of SRMs. The average κ values were calculated to evaluate the interobserver agreement of the two scoring versions.Statistical TestsRandom‐effects logistic regression; Receiver operating characteristic analysis; DeLong test; Weighted Kappa test; Z test. The statistical significance level was P < 0.05.ResultsThe pooled AUCs of clear cell likelihood score version 2.0 (ccLS v2.0) were statistically superior to those of ccLS v1.0 for diagnosing clear cell renal cell carcinoma (ccRCC) (0.907 vs. 0.851), papillary renal cell carcinoma (pRCC) (0.926 vs. 0.888), renal oncocytoma (RO) (0.745 vs. 0.679), and angiomyolipoma without visible fat (AMLwvf) (0.826 vs. 0.766). Interobserver agreement for SRMs between ccLS v1.0 and v2.0 is comparable and was not statistically significant (P = 0.993).ConclusionThe diagnostic performance of ccLS v2.0 surpasses that of ccLS v1.0 for characterizing ccRCC, pRCC, RO, and AMLwvf. Especially, the standardized algorithm has optimal performance for ccRCC and pRCC. ccLS has potential as a supportive clinical tool.Evidence Level4.Technical EfficacyStage 2.

Background Venous tumor thrombus (VTT) consistency of renal cell carcinoma (RCC) is an important consideration in nephrectomy plus thrombectomy. However, evaluation of VTT consistency through preoperative MR imaging is lacking. Purpose To evaluate VTT consistency of RCC through intravoxel incoherent motion‐diffusion weighted imaging (IVIM‐DWI) derived parameters ( D t , D p , f , and ADC) and the apparent diffusion coefficient (ADC) value. Study Type Retrospective. Population One hundred and nineteen patients (aged 55.8 ± 11.5 years, 85 male) with histologically‐proven RCC and VTT who underwent radical resection. Field Strength/Sequences 3.0‐T; two‐dimensional single‐shot diffusion‐weighted echo planar imaging sequence at 9 b ‐values (0–800 s/mm 2 ). Assessment IVIM parameters and ADC values of the primary tumor and the VTT were calculated. The VTT consistency (friable vs. solid) was determined through intraoperative findings of two urologists. The accuracy of VTT consistency classification based on the individual IVIM parameters of primary tumors and of VTT, and based on models combining parameters, was assessed. Type of operation, intra‐operative blood loss, and operation length were recorded. Statistical Tests Shapiro–Wilk test; Mann–Whitney U test; Student's t ‐test; Chi‐square test; Receiver operating characteristic (ROC) analysis. Statistical significance level was P < 0.05. Results Of the enrolled 119 patients, 33 patients (27.7%) had friable VTT. Patients with friable VTT were significantly more likely to experience open surgery, have significantly more intraoperative blood loss, and significantly longer operative duration. The area under the ROC curve (AUC) values of D t of the primary tumor and VTT in classifying VTT consistency were 0.758 (95% CI 0.671–0.832) and 0.712 (95% CI 0.622–0.792), respectively. The AUC value of the model combining D p and D t of VTT was 0.800 (95% CI 0.717–0.868). Furthermore, the AUC of the model combining D p and D t of VTT and D t of the primary tumor was 0.886 (95% CI 0.814–0.937). Conclusion IVIM‐derived parameters had the potential to predict VTT consistency of RCC. Evidence Level: 3 Technical Efficacy: Stage 2

Objective: To investigate the intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI) in the differential diagnosis of diabetic nephropathy (DN) and non-diabetic renal disease (NDRD) among patients with type 2 diabetes mellitus (T2DM). Methods: A diagnostic test. In this prospective study, patients with T2DM who underwent both IVIM-DWI and renal biopsy at the First Medical Center of Chinese PLA General Hospital between October 2017 and September 2021 were consecutively enrolled. IVIM-DWI parameters including perfusion fraction (f), pure diffusion coefficient (D), and pseudo-diffusion coefficient (D*) were measured in the renal cortex, medulla, and parenchyma. Patients were divided into the DN group and NDRD group based on the renal biopsy results. IVIM-DWI parameters, clinical information, and diabetes-related biochemical indicators between the two groups were compared using Student's t-test or Mann-Whitney U test. The correlation of IVIM-DWI parameters with diabetic nephropathy histological scores were analyzed using Spearman's correlation analyzes. The diagnostic efficiency of IVIM-DWI parameters for distinguishing between DN and NDRD were assessed using the receiver operating characteristic (ROC) curves. Results: A total of 27 DN patients and 23 NDRD patients were included in this study. The DN group comprised 19 male and 8 female patients, with an average age of 52±9 years. The NDRD group comprised 16 male and 7 female patients, with an average age of 49±10 years. The DN group had a higher D* value in the renal cortex and a lower f value in the renal medulla than the NDRD group (9.84×10-3 mm2/s vs. 7.35×10-3 mm2/s, Z=-3.65; 41.01% vs. 46.74%, Z=-2.29; all P<0.05). The renal medulla D* value was negatively correlated with DN grades, interstitial lesion score, and interstitial fibrosis and tubular atrophy (IFTA) score (r=-0.571, -0.409, -0.409; all P<0.05) while the renal cortex f value was positively correlated with vascular sclerosis score (r=0.413, P=0.032). The renal cortex D* value had the highest area under the curve (AUC) for discriminating between the DN and NDRD groups (AUC=0.802, sensitivity 91.3%, specificity 55.6%). Conclusion: IVIM-derived renal cortex D* value can be used non-invasively to differentiate DN from NDRD in patients with T2DM that can potentially facilitate individualized treatment planning for diabetic patients.

Objective:To investigate the clinical and MRI features of the mixed epithelial and stromal tumor family (MESTF) of the kidney.Methods:From January 2009 to September 2021, 42 patients with pathologically-proven MESTF from the First Medical Center of Chinese PLA General Hospital were collected in this retrospective study. Clinical information, MRI features, and pathological results were documented. According to the Bosniak classification (BC) version 2019, all MESTFs were divided into cystic MESTFs (36 cases) and solid-cystic MESTFs (6 cases). The R.E.N.A.L. nephrometry score (RNS), lesion size, laterality, location, margin, shape, growth pattern, presence of protruding into renal sinus, hemorrhage, and enhancement pattern were evaluated and documented. Based on BC versions 2005 and 2019, all the cystic MESTFs were assessed and divided into low (Ⅰ, Ⅱ, ⅡF) and high (Ⅲ, Ⅳ) grades. The independent sample t test or Mann-Whitney U test were performed to compare age, RNS, and lesion size between cystic MESTFs and solid-cystic MESTFs. Pearson χ 2 test, continuity-adjusted χ 2 test or Fisher exact probability test were utilized to evaluated the differences of clinical and MRI features and the distribution of low or high grades in two versions of BC. Results:Forty-two MESTFs were unilateral and solitary masses, 25 males and 17 females, with a mean age of (41±13) years old. Compared to solid-cystic MESTFs, cystic MESTFs were prone to demonstrate endophytic growth pattern (χ 2=17.77, P<0.001), and no significant differences in other clinical and MRI features were observed between cystic and solid-cystic MESTFs (all P>0.05). There were 7 low-grade and 29 high-grade tumors in the BC version 2005, respectively. Meanwhile, 24 low-grade and 12 high-grade tumors in the BC version 2019, respectively. The distribution of low or high-grade tumors in the two versions of BC had a statistically significant difference (χ 2=16.37, P<0.001). Conclusion:MESTFs demonstrated middle-age onset and no gender predilection. Cystic MESTFs are more likely to exhibit endophytic growth pattern with low-grade classification in BC system version 2019.

Objective:To evaluate the diagnostic value of multiparametric magnetic resonance imaging (mpMRI) based models in the assessment of extra-prostatic extension (EPE) of prostate cancer.Methods:This retrospective study included 168 consecutive men with prostate cancers [aged 48 to 82 (66.6±6.8) years] who underwent radical prostatectomy and preoperative mpMRI examinations at the First Medical Center of the PLA General Hospital from January 2021 to February 2022. According to European Society of Urogenital Radiology (ESUR) score, EPE grade and mEPE score, all cases were independently evaluated by two radiologists, with disagreement reviewed by a senior radiologist as the final result. The diagnostic performance of each MRI-based model for pathologic EPE prediction was assessed using receiver operating characteristic curve (ROC), and the differences between the corresponding area under the curve (AUC) were compared using the DeLong test. The weighted Kappa test was used to evaluate the inter-reader agreement of each MRI-based model.Results:A total of 62 (36.9%) prostate cancer patients had pathologic confirmed EPE after radical prostatectomy. The AUC of ESUR score, EPE grade and mEPE score for predicting pathologic EPE were 0.836 (95% CI: 0.771-0.888), 0.834 (95% CI: 0.769-0.887) and 0.785 (95% CI: 0.715-0.844), respectively. The AUC of ESUR score and EPE grade were both superior to that of mEPE score with significant differences (all P<0.05), while there was no significant difference between the ESUR score and EPE grade models ( P=0.900). EPE grading and mEPE score had good inter-reader consistency, with weighted Kappa values of 0.65 (95% CI: 0.56-0.74) and 0.74 (95% CI: 0.64-0.84), respectively. The inter-reader consistency of ESUR score was moderate, and the weighted Kappa value was 0.52 (95% CI: 0.40-0.63). Conclusion:All MRI-based models showed good preoperative diagnostic value in predicting EPE, among which the EPE grade resulted in more reliable performance with substantial inter-reader agreement.

Objectives:To investigate the effect of fat suppression (FS) T 2WI on the interobserver agreement and diagnostic performance of clear cell likelihood score version 2.0 (ccLS v2.0) for clear cell renal cell carcinoma (ccRCC). Methods:In this retrospective study, the MR images of 111 patients with pathologically confirmed small renal masses (SRM) from January to December 2021 were analyzed in the First Medical Centre, Chinese PLA General Hospital. Of the 111 SRM, 82 cases were ccRCC and 29 cases were non-ccRCC. Two radiologists independently assessed ccLS scores based on T 2WI signal intensity (hypointense, isointense, hyperintense) and other MRI features (ccLS-T 2WI). After a one-month interval, the ccLS scores were independently evaluated utilizing the frequency-selective saturation FS-T 2WI and other MRI features (ccLS-FS-T 2WI). Fisher′s exact test was used to compare the difference in SRM signal intensity on T 2WI and FS-T 2WI. The weighted Kappa test was performed to assess the interobserver agreement of the two radiologists, and differences in the weighted Kappa coefficients were compared using the Gwet consistency coefficient. Receiver operating characteristic curves were drawn to evaluate the diagnostic performance of ccLS-T 2WI and ccLS-FS-T 2WI in diagnosing ccRCC, and the area under the curve (AUC) was compared utilizing the DeLong test. Results:The signal intensity of 111 SRM on T 2WI and FS-T 2WI had statistically significant difference (χ 2=126.33, P<0.001), consistent in 88 cases (79.3%) and varied in 23 cases (20.7%). The weighted Kappa coefficient of ccLS-T 2WI was 0.57 (95%CI 0.45-0.69) between the two radiologists, and the weighted Kappa coefficient of ccLS-FS-T 2WI was 0.55 (95%CI 0.42-0.67), and the difference was not statistically significant ( t=-0.65, P=0.520). The AUC of ccLS-T 2WI for ccRCC diagnosis was 0.92 (95%CI 0.86-0.97), while the AUC of ccLS-FS-T 2WI for ccRCC diagnosis was 0.91 (95%CI 0.85-0.96), and the difference was not statistically significant ( Z=1.50, P=0.133). Conclusions:The interobserver agreement and diagnostic performance of ccLS v2.0 based on T 2WI and FS-T 2WI sequences for ccRCC are comparable, and FS-T 2WI is applicable for the clinical application of ccLS v2.0.

PurposeTo assess the performance of ADC values in stratifying high- and low-risk groups of Gleason score of prostate cancer.Materials and methods370 cases of prostate cancer who met the selection criteria between October 2015 and May 2019 were collected in the study. MRI sequences included high-resolution transverse T2WI and DWI (b = 0, 1000, 2000 and 3000 s/mm(2)). Surgical pathological results were obtained in all cases. The ADC values of prostate cancer lesions were measured by two radiologists and the consistency and reproducibility analysis were done. The ADC values were compared between high-risk group and low-risk group lesions and the receiver operating characteristic (ROC) curve was used to evaluate the value of ADC values of different b values in distinguishing high-risk group from low-risk group of Gleason of prostate cancer.ResultsThe consistency and reproducibility of ADC values measured by two radiologists in high- and low-risk group of Gleason of prostate cancer were excellent. The ADC values for high-risk group of Gleason of prostate cancer were significantly lower than those for low-risk group (p < 0.05). The area under the ROC curve (AUC) of different b values distinguishing high-risk group from low-risk group of Gleason of prostate cancer were 0.651, 0.656, 0.692 (reader1) and 0.658, 0.653, 0.695 (reader2), respectively. The diagnostic efficacy of b value (3000 s/mm(2)) is the highest.ConclusionsThe b value of 3000 s/mm(2) is the most useful in differentiating high-risk group from low-risk group of Gleason of prostate cancer.

Identifying brain abnormalities in autism spectrum disorder (ASD) is critical for early diagnosis and intervention. To explore brain differences in ASD and typical development (TD) individuals by detecting structural features using T1-weighted magnetic resonance imaging (MRI), we developed a deep learning-based approach, three-dimensional (3D)-ResNet with inception (I-ResNet), to identify participants with ASD and TD and propose a gradient-based backtracking method to pinpoint image areas that I-ResNet uses more heavily for classification. The proposed method was implemented in a preschool dataset with 110 participants and a public autism brain imaging data exchange (ABIDE) dataset with 1099 participants. An extra epilepsy dataset with 200 participants with clear degeneration in the parahippocampal area was applied as a verification and an extension. Among the datasets, we detected nine brain areas that differed significantly between ASD and TD. From the ROC in PASD and ABIDE, the sensitivity was 0.88 and 0.86, specificity was 0.75 and 0.62, and area under the curve was 0.787 and 0.856. In a word, I-ResNet with gradient-based backtracking could identify brain differences between ASD and TD. This study provides an alternative computer-aided technique for helping physicians to diagnose and screen children with an potential risk of ASD with deep learning model.