Lung cancer is a leading cause of cancer-related deaths worldwide and poses a significant health burden. Early diagnosis is critical for reducing lung cancer mortality. Lung Cancer with Cystic Airspaces (LCCA) is a distinct morphological subtype of lung cancer, characterized on imaging by cystic regions accompanied by solid components and/or ground-glass opacities. LCCA is relatively rare, with an incompletely understood pathogenesis, marked heterogeneity, and complex imaging manifestations. It accounts for approximately one-quarter of lung cancer cases that are missed or diagnosed late. With the widespread implementation of lung cancer screening, the detection rate of LCCA is increasing and has drawn growing attention. However, current research is limited by small sample sizes and predominantly retrospective study designs, posing significant clinical challenges in LCCA management. This article reviews the definition and underlying mechanisms of LCCA, systematically summarizes the clinical value of noninvasive imaging in diagnosis, classification, invasiveness prediction, staging, and prognosis assessment of LCCA, and discusses the limitations of existing studies as well as future research directions and challenges. The goal is to provide a theoretical basis for optimizing early lung cancer screening pathways and developing individualized intervention strategies, which holds important clinical significance for reducing lung cancer-related mortality.

Chronic kidney disease (CKD) is a major health burden. Intrarenal microcirculation impairment occurs early in CKD and precedes measurable declines in renal function. We investigated whether contrast-free multiparametric MRI (mp-MRI) can characterize intrarenal microcirculation alterations and improve early CKD detection. This retrospective study included 54 patients with pathology-confirmed CKD (25 mild and 29 moderate-severe by the Katafuchi system) and 20 age- and sex-matched healthy controls (HCs) enrolled between March 2020 and August 2022. All participants underwent an mp-MRI protocol comprising arterial spin labeling (ASL), intravoxel incoherent motion imaging (IVIM), blood oxygen level-dependent (BOLD) imaging, and quantitative susceptibility mapping (QSM). Renal biopsy served as the reference standard, with estimated glomerular filtration rate and serum creatinine as clinical comparators. Group differences in MRI metrics were assessed, correlations with histopathology were evaluated, and multivariable logistic regression models were constructed to distinguish CKD (and mild CKD) from healthy controls. Renal blood flow, diffusion and microperfusion metrics (D, D*, f), BOLD-derived R2*, and susceptibility values differed significantly across groups, and each MRI parameter and clinical biomarker correlated with histopathological severity (|r| = 0.33-0.97). A mp-MRI model integrating RBFCortex, D*Cortex, fCortex, and R2*Cortex achieved excellent discrimination for CKD versus HCs (AUC = 0.976; 95% confidence interval [CI]: 0.949-1.000; p < 0.001) and for mild CKD versus HCs (AUC = 0.948; 95% CI: 0.891-1.000; p < 0.001). These findings support a pathophysiology-driven, contrast-free mp-MRI framework for noninvasive assessment of renal microcirculation and early CKD detection.

Accurate, noninvasive assessment of renal fibrosis (RF) in chronic kidney disease (CKD) remains challenging. This study aimed to develop and externally validate a dual-center multi-sequence MRI radiomics nomogram integrating imaging and clinical parameters for evaluating RF severity. This retrospective dual-center study included 164 patients with CKD who underwent multi-sequence MRI and renal biopsy, divided into a training set (n = 128) and an external test set (n = 36). Radiomics features were extracted from intravoxel incoherent motion (IVIM) and blood oxygenation level-dependent (BOLD) MRI. Feature selection involved inter-observer correlation coefficient, Mann–Whitney U test, Pearson correlation coefficients, and least absolute shrinkage and selection operator regression. Three radiomics models (Rad_IVIM, Rad_BOLD, Rad_IVIM+BOLD) and one clinic model were developed to distinguish mild from moderate-to-severe RF. A nomogram was constructed by integrating the Rad_IVIM+BOLD score with significant clinical variables. Model performance was evaluated using area under the curve (AUC), DeLong test, decision curve analysis (DCA), and calibration curves. The Rad_IVIM+BOLD model achieved AUCs of 0.898 (95

To evaluate the feasibility and accuracy of Fat Analysis Calculation Technique (FACT), a multi-echo Dixon-like sequence, for quantifying renal and perirenal adipose distribution at 5 T. Accuracy of FACT-based Proton density fat fraction (FACT-PDFF) was assessed by comparing with magnetic resonance spectroscopy-based PDFF (MRS-PDFF) in phantom study. In vivo FACT images from 24 volunteers (13 males and 11 females) without kidney-related diseases were acquired at 5 T and evaluated independently by two readers. Repeatability of FACT-PDFF was assessed through three consecutive scans. Spearman correlation examined associations between averaged FACT-PDFF and clinical characteristics. Linear regression, intraclass correlation coefficients (ICCs), and Bland-Altman plots assessed consistency and deviations between fat quantification methods and field strengths. The Wilcoxon signed-rank test compared image quality scores between radiologists. The paired t test compared FACT-PDFF differences across all regions of interest between bilateral kidneys and between renal cortex and medulla. Analysis of covariance compared gender-related renal fat differences. In phantom study, FACT-PDFF showed excellent agreement with MRS-PDFF at both fields (ICCs ≥ 0.995). Linear regression revealed strong correlations (R² ≥ 0.998), and Bland-Altman plots indicated minimal bias. In clinical study, FACT images achieved high quality. Repeatability was excellent (ICCs: 0.837–0.991; CVs: 0.78–4.49

To develop a fully automatic urinary stone detection system (kidney, ureter, and bladder) and to test it in a real clinical environment. The local institutional review board approved this retrospective single-center study that used non-enhanced abdominopelvic CT scans from patients admitted urology (uPatients) and emergency (ePatients). The uPatients were randomly divided into training and validation sets in a ratio of 3:1. We designed a cascade urinary stone map location-feature pyramid networks (USm-FPNs) and innovatively proposed a ureter distance heatmap method to estimate the ureter position on non-enhanced CT to further reduce the false positives. The performances of the system were compared using the free-response receiver operating characteristic curve and the precision-recall curve. This study included 811 uPatients and 356 ePatients. At stone level, the cascade detector USm-FPNs has the mean of false positives per scan (mFP) 1.88 with the sensitivity 0.977 in validation set, and mFP was further reduced to 1.18 with the sensitivity 0.977 after combining the ureter distance heatmap. At patient level, the sensitivity and precision were as high as 0.995 and 0.990 in validation set, respectively. In a real clinical set of ePatients (27.5% of patients contain stones), the mFP was 1.31 with as high as sensitivity 0.977, and the diagnostic time reduced by > 20% with the system help. A fully automatic detection system for entire urinary stones on non-enhanced CT scans was proposed and reduces obviously the burden on junior radiologists without compromising sensitivity in real emergency data.

Background To introduce a three-dimensional convolutional neural network (3D CNN) leveraging transfer learning for fusing PET/CT images and clinical data to predict EGFR mutation status in lung adenocarcinoma (LADC). Methods Retrospective data from 516 LADC patients, encompassing preoperative PET/CT images, clinical information, and EGFR mutation status, were divided into training ( n = 404) and test sets ( n = 112). Several deep learning models were developed utilizing transfer learning, involving CT-only and PET-only models. A dual-stream model fusing PET and CT and a three-stream transfer learning model (TS_TL) integrating clinical data were also developed. Image preprocessing includes semi-automatic segmentation, resampling, and image cropping. Considering the impact of class imbalance, the performance of the model was evaluated using ROC curves and AUC values. Results TS_TL model demonstrated promising performance in predicting the EGFR mutation status, with an AUC of 0.883 (95%CI = 0.849–0.917) in the training set and 0.730 (95%CI = 0.629–0.830) in the independent test set. Particularly in advanced LADC, the model achieved an AUC of 0.871 (95%CI = 0.823–0.919) in the training set and 0.760 (95%CI = 0.638–0.881) in the test set. The model identified distinct activation areas in solid or subsolid lesions associated with wild and mutant types. Additionally, the patterns captured by the model were significantly altered by effective tyrosine kinase inhibitors treatment, leading to notable changes in predicted mutation probabilities. Conclusion PET/CT deep learning model can act as a tool for predicting EGFR mutation in LADC. Additionally, it offers clinicians insights for treatment decisions through evaluations both before and after treatment.

Objective To explore the association of renal surface nodularity (RSN) with the increased adverse vascular event (AVE) risk in patients with arterial hypertension. Methods This cross-sectional study included patients with arterial hypertension aged 18-60 years who underwent contrasted computed tomography (CT) of kidney from January 2012 to December 2020. The subjects were classified into AVE or not (non-AVE) matched with age (& LE;5 years) and sex. Their CT images were analyzed using both qualitative (semiRSN) and quantitative RSN (qRSN) methods, respectively. Their clinical characteristics included age, sex, systolic blood pressure (SBP), diastolic blood pressure, hypertension course, diabetes history, hyperlipidemia, and estimated glomerular filtration rate (eGFR). Results Compared with non-AVE group (n = 91), AVE (n = 91) was at lower age, higher SBP, and fewer rate of diabetes and hyperlipidemia history (all P < .01). Rate of positive semiRSN was higher in AVE than non-AVE (49.45% vs 14.29%, P < .001). qRSN was larger in AVE than non-AVE [1.03 (0.85, 1.33) vs 0.86 (0.75,1.03), P < .001]. The increased AVE was associated with semiRSN (odds ratio = 7.04, P < .001) and qRSN (odds ratio = 5.09, P = .003), respectively. For distinguishing AVE from non-AVE, the area under receiver operating characteristic was bigger in the models combining the clinical characteristics with either semiRSN or qRSN than that of semiRSN or qRSN alone (P & LE;.01). Conclusion Among the patients with arterial hypertension aged 18-60 years, CT imaging-based RSN was associated with increased AVE risk.

Objective This study aimed to investigate the feasibility of diffusion-weighted imaging with ultrahigh b values ( ub DWI) for the evaluation of renal fibrosis (RF) induced by renal artery stenosis (RAS) in a rabbit model. Methods Thirty-two rabbits underwent left RAS operation, whereas 8 rabbits received sham surgery. All rabbits underwent ub DWI ( b = 0–4500 s/mm 2 ). The standard apparent diffusion coefficient (ADC st ), molecular diffusion coefficient ( D ), perfusion fraction ( f ), perfusion-related diffusion coefficient ( D *) and ultrahigh apparent diffusion coefficient (ADC uh ) were longitudinally assessed before operation and at weeks 2, 4, and 6 after operation. The degree of interstitial fibrosis and the expression of aquaporin (AQP) 1 and AQP2 were determined through pathological examination. Results In the stenotic kidney, the ADC st , D , f , and ADC uh values of the renal parenchyma significantly decreased compared with those at baseline (all P < 0.05), whereas the D * values significantly increased after RAS induction ( P < 0.05). The ADC st , D , D *, and f were weakly to moderately correlated with interstitial fibrosis as well as with the expression of AQP1 and AQP2. Furthermore, the ADC uh negatively correlated with interstitial fibrosis ( ρ = −0.782, P < 0.001) and positively correlated with AQP1 and AQP2 expression ( ρ = 0.794, P < 0.001, and ρ = 0.789, P < 0.001, respectively). Conclusions Diffusion-weighted imaging with ultrahigh b values shows the potential for noninvasive assessment of the progression of RF in rabbits with unilateral RAS. The ADC uh derived from ub DWI could reflect the expression of AQPs in RF.

Background Renal surface nodularity (RSN) is a subclinical biomarker of renal injury and may be associated with arterial hypertension. Purpose To explore the association of RSN with arterial hypertension compared to normotensive patients. Material and Methods A total of 205 inpatients with or without high blood pressure (HBP vs. control group) who underwent abdominal computed tomography (CT) scans were included. Their clinical characteristics included age, sex, HBP course, HBP grade, history of diabetes mellitus (DM), and renal function (estimated glomerular filtration rate [eGFR]). The HBP group included HBP/+DM and HBP/–DM based on the presence or absence of DM. The CT-based RSN grade was scored from 0 to 2 by two radiologists, respectively, where RSN grade 0 indicated smooth renal surface, grade 1 was mild RSN, and grade 2 was marked RSN. Results The inter-rater agreement on RSN was good (Kappa = 0.76). The age-specific rate of RSN grade 1–2 was bigger in the HBP group than in the control group (42.86% [40%–49.22%] vs. 2.18% [0.00%–22.5%]; P = 0.005). RSN grade was associated with HBP course ( P < 0.02). The rates of RSN grade 1–2 and of RSN grade 2 were bigger in the HBP/+DM group than those in the HBP/–DM group (48.84% vs. 37.84%, and 18.61% vs. 1.35%, respectively; all P = 0.001). Neither HBP course nor HBP grade correlated with rate of RSN grade ( P > 0.05). The eGFR was similar among the RSN grades in HBP or between the HBP and control groups ( P > 0.05). Conclusion RSN was associated with HBP compared to normotensive patients.

Abstract Background This study aims to construct radiomics models based on [18F]FDG PET/CT using multiple machine learning methods to predict the EGFR mutation status of lung adenocarcinoma and evaluate whether incorporating clinical parameters can improve the performance of radiomics models. Methods A total of 515 patients were retrospectively collected and divided into a training set (n = 404) and an independent testing set (n = 111) according to their examination time. After semi-automatic segmentation of PET/CT images, the radiomics features were extracted, and the best feature sets of CT, PET, and PET/CT modalities were screened out. Nine radiomics models were constructed using logistic regression (LR), random forest (RF), and support vector machine (SVM) methods. According to the performance in the testing set, the best model of the three modalities was kept, and its radiomics score (Rad-score) was calculated. Furthermore, combined with the valuable clinical parameters (gender, smoking history, nodule type, CEA, SCC-Ag), a joint radiomics model was built. Results Compared with LR and SVM, the RF Rad-score showed the best performance among the three radiomics models of CT, PET, and PET/CT (training and testing sets AUC: 0.688, 0.666, and 0.698 vs. 0.726, 0.678, and 0.704). Among the three joint models, the PET/CT joint model performed the best (training and testing sets AUC: 0.760 vs. 0.730). The further stratified analysis found that CT_RF had the best prediction effect for stage I–II lesions (training set and testing set AUC: 0.791 vs. 0.797), while PET/CT joint model had the best prediction effect for stage III–IV lesions (training and testing sets AUC: 0.722 vs. 0.723). Conclusions Combining with clinical parameters can improve the predictive performance of PET/CT radiomics model, especially for patients with advanced lung adenocarcinoma.

Background: It is of great importance to predict the early recurrence (ER) of hepatocellular carcinoma (HCC) after hepatectomy using preoperative imaging modalities. Nevertheless, no comparative studies have been conducted to determine which modality, CT or MRI with radiomics analysis, is more effective. Methods: We retrospectively enrolled 119 HCC patients who underwent preoperative CT and MRI. A total of 3776 CT features and 4720 MRI features were extracted from the whole tumor. The minimum redundancy and maximum relevance algorithm (MRMR) and least absolute shrinkage and selection operator (LASSO) regression were applied for feature selection, then support vector machines (SVMs) were applied for model construction. Multivariable logistic regression analysis was employed to construct combined models that integrate clinical–radiological–pathological (CRP) traits and radscore. Receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) were used to compare the efficacy of CT, MRI, and CT and MRI models in the test cohort. Results: The CT model and MRI model showed no significant difference in the prediction of ER in HCC patients (p = 0.911). RadiomicsCT&MRI demonstrated a superior predictive performance than either RadiomicsCT or RadiomicsMRI alone (p = 0.032, 0.039). The combined CT and MRI model can significantly stratify patients at high risk of ER (area under the curve (AUC) of 0.951 in the training set and 0.955 in the test set) than the CT model (AUC of 0.894 and 0.784) and the MRI model (AUC of 0.856 and 0.787). DCA demonstrated that the CT and MRI model provided a greater net benefit than the models without radiomics analysis. Conclusions: No significant difference was found in predicting the ER of HCC between CT models and MRI models. However, the multimodal radiomics model derived from CT and MRI can significantly improve the prediction of ER in HCC patients after resection.

Objective:To investigate the correlation between the SUV index (SUV max of the lesion/SUV mean of the liver) in 18F-FDG PET/CT imaging and the invasiveness of early lung adenocarcinoma presenting as ground-glass nodule (GGN). Methods:From January 2012 to March 2020, 167 GGN patients (49 males, 118 females; age: (61.5±9.0) years) with early lung adenocarcinoma who underwent PET/CT imaging in Changzhou First People′s Hospital were retrospectively enrolled. The image parameters including the GGN number, location, type, edge, shape, abnormal bronchus sign, vacuole sign, pleural depression, vessel convergence sign, GGN diameter ( DGGN), solid component diameter ( Dsolid), consolidation to tumor ratio (CTR, Dsolid/ DGGN), CT values (CT value of ground-glass opacity (CT GGO), CT value of lung parenchyma (CT LP), ΔCT GGO-LP (CT GGO-CT LP)) and SUV index were analyzed. Single and multivariate logistic regressions were used to analyze the correlation between SUV index and infiltration. The generalized additive model was used for curve fitting, and the piece-wise regression model was used to further explain the nonlinearity. Results:In 189 GGNs, invasive adenocarcinoma accounted for 85.2% (161/189). Single logistic regression showed that the GGN number, type, shape, edge, abnormal bronchus sign, pleural depression, vessel convergence sign, DGGN, Dsolid, CTR, CT GGO, ΔCT GGO-LP and SUV index were related factors of infiltration (odds ratio ( OR) values: 0.396-224.083, P<0.001 or P<0.05). After fully adjusting for confounding factors, SUV index was significantly correlated with increased risk of invasion ( OR=2.162 (95% CI: 1.191-3.923), P=0.011). Curve fitting showed that the SUV index was non-linearly related to the risk of infiltration, and the risk of infiltration increased significantly only when the SUV index was greater than 0.43 ( OR=3.509 (95% CI: 1.429-8.620), P=0.006). The correlation between SUV index and infiltration had no interaction between age, vacuoles, pleural depression and CTR subgroups (all P>0.05). Conclusions:SUV index is an independent factor related to the invasiveness of early lung adenocarcinoma. The higher the SUV index, the greater the risk of invasion; but the two are not simply linearly correlated.

To investigate whether the maximum standardized uptake value (SUVmax) of 18F-deoxyglucose (FDG) PET imaging can increase the diagnostic efficiency of CT radiomics-based prediction model in differentiating benign and malignant pulmonary ground-glass nodules (GGNs). We retrospectively collected 190 GGNs from 165 patients who underwent 18F-FDG PET/CT examination from January 2012 to March 2020. Propensity score matching (PSM) was performed to select GGNs with similar baseline characteristics. LIFEx software was used to extract 49 CT radiomic features, and the least absolute shrinkage and selection operator (LASSO) algorithm was used to select parameters and establish the Rad-score. Logistic regression analysis was performed combined with semantic features to construct a CT radiomics model, which was combined with SUVmax to establish the PET + CT radiomics model. Receiver operating characteristic (ROC) was used to compare the diagnostic efficacy of different models. After PSM at 1:4, 190 GGNs were divided into benign group (n = 23) and adenocarcinoma group (n = 92). After texture analysis, the Rad-score with three CT texture features was constructed for each nodule. Compared with the Rad-score and CT radiomics model (AUC: 0.704 (95%CI: 0.562-0.845) and 0.908 (95%CI: 0.842-0.975), respectively), PET + CT radiomics model had the best diagnostic efficiency (AUC: 0.940, 95%CI: 0.889-0.990), and there was significant difference between each two of them (P = 0.001-0.030). SUVmax can effectively improve CT radiomics model performance in the differential diagnosis of benign and malignant GGNs. PET + CT radiomics might become a noninvasive and reliable method for differentiating of GGNs.

Rationale and Objectives: To evaluate qualitative and quantitative indicators generated from Dual-energy computed tomography (DECT) for preoperatively differentiating between invasive adenocarcinoma (IAC) and preinvasive or minimally invasive adenocarcinoma (MIA) lesions manifesting as ground-glass opacity-predominant (GGO-predominant) nodules. Materials and Methods: We retrospectively enrolled 143 cases of completely resected GGO-predominant lung adenocarcinoma with DECT examinations between December 2017 and July 2019. Qualitative and quantitative parameters of GGO-predominant nodules were compared after grouping nodules into IAC and preinvasive-MIA groups. A multivariate logistic regression models were used for analyzing these parameters. The diagnostic performance of different parameters was compared by receiver operating characteristic (ROC) curves and Z tests. Results: This study included 137 patients (58 years +/- 11; male: female = 52:91) with 143 GGO-predominant nodules. The proportion of margins, internal dilated/distorted/cut-off bronchi, internal thickened/stiff/distorted vasculature, pleural indentation, and vascular convergence were higher in the IAC group than in the preinvasive-MIA group, as were the maximum diameter (Dmax), the diameter of the solid component (Dsolid) and the enhanced monochromatic CT value at 40 keV-190 keV (CT40 keV-190 keV) (p range: 0.001-0.019). Logistic regression analyses revealed that margin, Dmax, and CT60 keV values were independent predictors of the IAC group. The area under the curve (AUC) for the combination of margin, Dmax, and CT60 keV was 0.896 (90.2% sensitivity, 70.7% specificity, 84.6% accuracy), which was significantly higher than that for each two of them (all p < 0.05). Conclusion: The combined prediction model generated from DECT allows for effective preoperative differentiation between IAC and preinvasive-MIA in GGO-predominant lung adenocarcinomas. (c) 2020 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

患者女,75岁,双腹侧肋下疼痛2个月,双下肢麻木乏力1个月.神经系统检查示:双下肢肌力V-级,肌张力正常,膝腱、跟腱反射减弱,T7以下针刺觉减退,震动觉减退.实验室检查:血清TPPA(+),RPR 1∶16,HIV(-);脑脊液TPPA(+),RPR ∶2,白细胞计数123 ×106/L,蛋白0.7 g/L;细菌、抗酸杆菌、真菌、墨汁染色隐球菌均阴性.脊髓MRI提示"翻转征".诊断:梅毒性脊髓脊膜炎.

To explore the association between 18 F-FDG PET/CT-based SUV index and malignant risk of persistent ground-glass nodules (GGNs). We retrospectively analyzed a total of 166 patients with GGN who underwent PET/CT examination from January 2012 to October 2019. There were 113 women and 53 men, with an average age of 60.8 ± 9.1 years old. A total of 192 GGNs were resected and confirmed by pathology, including 22 in benign group and 170 in adenocarcinoma group. They were divided into three groups according to SUV index tertiles: Tertile 1 (0.14–0.54), Tertile 2 (0.55–1.17), and Tertile 3 (1.19–6.78), with 64 GGNs in each group. The clinical and imaging data of all patients were collected and analyzed. After adjusting for the potential confounding factors, we found that the malignancy risk of GGN significantly decreased as the SUV index increased (OR, 0.245; 95%CI, 0.119–0.504; P < 0.001), the average probability of malignant GGN was 89.1% (95% CI, 53.1–98.3%), 80.5% (95% CI, 36.7–96.7%), and 34.3% (95%CI, 9.5–72.2%) for Tertile 1 to Tertile 3. And the increasing trend of SUV index was significantly correlated with the reduction of malignant risk (OR, 0.099; 95%CI, 0.025–0.394; P = 0.001), especially between Tertile 3 versus Tertile 1 (OR, 0.064; 95%CI, 0.012–0.356; P = 0.002). Curve fitting showed that the SUV index was linearly and negatively correlated with the malignant risk of GGN. SUV index is an independent correlation factor for malignancy risk of GGN, the higher the SUV index, the lower the probability of GGN malignancy.

BACKGROUND:To explore the association between the glucose metabolism level of lung ground-glass nodules (GGNs), as revealed by 18F-flurodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) imaging, and the invasive pathological growth pattern of early lung adenocarcinoma.METHODS:We retrospectively analyzed patients who underwent PET/CT examination and surgical resection due to persistent GGNs, which were confirmed to be early lung adenocarcinoma by postoperative pathology examination. After adjusting for confounding factors and performing stratified analysis, we explored the association between the maximum standard uptake value of PET (SUVmax) and the invasive pathological growth pattern of early stage lung adenocarcinoma.RESULTS:The proportions of invasive adenocarcinoma (INV) in the SUVmax of Tertile 1, Tertile 2, and Tertile 3 were 52.7%, 73.3%, and 87.1%, respectively. After adjusting for potential confounding factors, the risk of INV gradually increased as the GGN SUVmax increased [odds ratio (OR): 1.520, 95% confidence interval (CI): 1.044-2.213, P=0.029]. This trend was statistically significant (OR: 1.678, 95% CI: 1.064-2.647, P=0.026), especially in Tertile 3 vs. Tertile 1 (OR: 4.879, 95% CI: 1.349-17.648, P=0.016). Curve fitting showed that the SUVmax and INV risk were linearly and positively associated. The association was consistent in different subgroups based on GGN number, type, shape, edge, bronchial sign, vacuole sign, pleural depression sign, diameters, and consolidation-to-tumor ratio, suggesting that there was no significant interaction between different grouping parameters and the association (P for interaction range = 0.129-0.909).CONCLUSIONS:In FDG PET, the glucose metabolism level (SUVmax) of lung GGNs is independently associated with INV risk, and this association is linear and positive.

Abstract Purpose This work aims to train, validate, and test a dual-stream three-dimensional convolutional neural network (3D-CNN) based on fluorine 18 (18F)-fluorodeoxyglucose (FDG) PET/CT to distinguish benign lesions and invasive adenocarcinoma (IAC) in ground-glass nodules (GGNs). Methods We retrospectively analyzed patients with suspicious GGNs who underwent 18F-FDG PET/CT in our hospital from November 2011 to November 2020. The patients with benign lesions or IAC were selected for this study. According to the ratio of 7:3, the data were randomly divided into training data and testing data. Partial image feature extraction software was used to segment PET and CT images, and the training data after using the data augmentation were used for the training and validation (fivefold cross-validation) of the three CNNs (PET, CT, and PET/CT networks). Results A total of 23 benign nodules and 92 IAC nodules from 106 patients were included in this study. In the training set, the performance of PET network (accuracy, sensitivity, and specificity of 0.92 ± 0.02, 0.97 ± 0.03, and 0.76 ± 0.15) was better than the CT network (accuracy, sensitivity, and specificity of 0.84 ± 0.03, 0.90 ± 0.07, and 0.62 ± 0.16) (especially accuracy was significant, P-value was 0.001); in the testing set, the performance of both networks declined. However, the accuracy and sensitivity of PET network were still higher than that of CT network (0.76 vs. 0.67; 0.85 vs. 0.70). For dual-stream PET/CT network, its performance was almost the same as PET network in the training set (P-value was 0.372–1.000), while in the testing set, although its performance decreased, the accuracy and sensitivity (0.85 and 0.96) were still higher than both CT and PET networks. Moreover, the accuracy of PET/CT network was higher than two nuclear medicine physicians [physician 1 (3-year experience): 0.70 and physician 2 (10-year experience): 0.73]. Conclusion The 3D-CNN based on 18F-FDG PET/CT can be used to distinguish benign lesions and IAC in GGNs, and the performance is better when both CT and PET images are used together.

Background To develop and verify a prediction model for distinguishing malignant from benign ground-glass nodules (GGNs) combined with clinical characteristics and 18F-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) parameters. Methods We retrospectively analyzed 170 patients (56 males and 114 females) with GGNs who underwent PET/CT and high-resolution CT examination in our hospital from November 2011 to December 2019. The clinical and imaging data of all patients were collected, and the nodules were randomly divided into a derivation set and a validation set. For the derivation set, we used multivariate logistic regression to develop a prediction model for distinguishing benign from malignant GGNs. A receiver operating characteristic (ROC) curve was used to evaluate the diagnostic efficacy of the model, and the data in the validation set were used to verify the prediction model. Results Among the 170 patients, 197 GGNs were confirmed via postoperative pathological examination or clinical follow-up. There were 21 patients with 27 GGNs in the benign group and 149 patients with 170 GGNs in the adenocarcinoma group. A total of five parameters, including the patient's sex, nodule location, margin, pleural indentation, and standardized uptake value (SUV) index (the ratio of nodule SUVmax to liver SUVmean), were selected to develop a prediction model for distinguishing benign from malignant GGNs. The area under the curve (AUC) of the model was 0.875 in the derivation set, with a sensitivity of 0.702 and a specificity of 0.923. The positive likelihood ratio was 9.131, and the negative likelihood ratio was 0.322. In the validation set, the AUC of the model was 0.874, which was not significantly different from the derivation set (P=0.989). Conclusions This study developed and validated a prediction model based on 18F-FDG PET/CT imaging and clinical characteristics for distinguishing malignant from benign GGNs. The model showed good diagnostic efficacy and high specificity, which can improve the preoperative diagnosis of high-risk GGNs.

Background: Susceptibility weighted imaging (SWI) could reflect tissue blood oxygen levels, and then whether it could be used to evaluate renal injury remains to be further studied. This study aimed to examine the performance of SWI parameters and SWI-based texture features in evaluating renal dysfunction of type 2 diabetes mellitus (T2DM). Methods: Forty-five patients with T2DM were included. With the estimated glomerular filtration rate (eGFR), the patients were divided into non-moderate-severe renal injured group (non-msRI, eGFR >60 mL/min/1.73 m(2)) and moderate-severe renal injured group (msRI, eGFR <= 60 mL/min/1.73 m(2)). The 3 SWI parameters and 16 SWI-based texture features between non-msRI and msRI were compared. The correlation between the parameters and BUN, Scr was analyzed. Results: The signal intensity ratio of the medulla to psoas muscle (MPswi) was significantly lower than the signal intensity ratio of the cortex to psoas muscle (CPswi) in non-msRI and msRI group (t=8.619, 3.483, respectively, P<0.05). MPswi was higher, and the signal intensity ratio of the cortex to the medulla (CMswi), Skewness, Correlation were lower in msRI than in non-msRI (P<0.05). These parameters showed similar diagnostic efficacies for msRI (P>0.05), and AUCs were 0.703-0.854. CMswi was an independent protective factor for msRI (OR=0.026, P=0.003). MPswi and CMswi were correlated with BUN ( r=0.416, -0.545, P<0.05). CMswi and Correlation were correlated with Scr (r=-0.645, -0.411, P<0.05). Conclusions: SWI was valuable for assessing renal dysfunction, which may be helpful for the evaluation of moderate-severe renal injured patients with T2DM.