Objective To observe the value of machine learning(ML)model based on chest non-contrast CT(NCCT)radiomics for diagnosing metabolic syndrome(MetS)in males.Methods A total of 792 males who would undergo chest NCCT and bone density CT examination for physical check-up were prospectively enrolled and divided into training set(n=554,including 171 cases of MetS)and validation set(n=238,including 70 cases of MetS)at the ratio of 7∶3.Chest NCCT was performed,ROI of liver,intra-abdominal fat and skeletal muscle were delineated,and visceral fat area(VFA)at L2-3 intervertebral disc level was measured.Then radiomic signature(RS)of liver,intra-abdominal fat and skeletal muscle were established,and ML models were constructed using logistic regression(LR),random forests(RF)and extreme gradient boosting(XGBoost)algorithms,respectively,and their diagnostic performance were observed.Results Significant difference of age was found between MetS and non-MetS males in training set(P=0.010),while of RS scores were noticed in both training set and validation set(all P＜0.001).Combined ML models were constructed with age and RS.The area under the curve(AUC)of combined LR,RF and XGBoost models for diagnosing male MetS in training set was 0.899,0.996 and 0.943,while that in validation set was 0.861,0.860 and 0.876,respectively.Combined XGBoost model had the best performance.Conclusion XGBoost model based on chest NCCT radiomics was helpful for diagnosing male MetS.Combining with age could further improve its efficacy.

Objective: To evaluate the clinical value of combining low-dose energy spectrum CT with virtual un-enhanced(VUE) scanning and deep-learning image reconstruction(DLIR) in aortic CT angiography(CTA). Methods : In a prospective study, 94 patients scheduled for aortic CTA were randomized into two groups: a low-dose energy spectrum group and a standard 100 kVp enhancement group, with 47 patients in each. All patients initially underwent a true un-enhanced(TUE) scan at 120 kVp using adaptive statistical iterative reconstruction-V(ASIR-V) at 40% for image reconstruction. The low-dose group received enhanced scans using gemstone spectral imaging(GSI) mode with DLIR-H, producing 60 keV virtual monoenergetic images(VMIs) and VUE images. The standard group was scanned at 100 kVp, with images reconstructed using ASIR-V at 50%. Parameters were measured including CT values, noise(SD), signal-to-noise ratio(SNR), and contrast-to-noise ratio(CNR) for key vascular and muscular areas, alongside the effective radiation dose(ED). Two radiologists evaluated the image quality using a 5-point scale. Results : The low-dose group exhibited significantly higher SNR and CNR values in the ascending aorta, descending aorta, abdominal aorta, and common iliac artery compared to the standard group(P<0.05), with comparable subjective quality scores. The VUE images also demonstrated superior SNR values in the abdominal aorta, common iliac artery, and psoas major muscle, and CNR value in the ascending aorta compared to TUE images, with similar subjective quality. Importantly, the ED in the low-dose group was about 40% lower than that of the standard group. Conclusion Low-dose energy spectrum CT with DLIR in aortic CTA can significantly enhance SNR and CNR, while approximating the image quality of traditional TUE scans, thereby substantially reducing radiation exposure.

Objective: To explore the brain-predicted age difference (Brain-PAD) in patients with type 2 diabetes mellitus (T2DM) by a machine learning prediction model based on structural magnetic resonance ( sMRI) in the Southwest University Adult Lifespan Dataset (SALD) , and to reveal the relationship between Brain-PAD and dura- tion of T2DM and cognition . Methods: Group comparisons about demographic variables and cognitive function were conducted respectively in local database of 104 T2DM patients and 83 healthy controls (HC) . The prediction model via Gaussian process regression (GPR) was constructed by training sMRI data of 329 healthy volunteers in SALD , then its performance was validated and evaluated . Furthermore , Brain-PAD ( predicted age-chronological age) in the local database was calculated . Group comparisons of Brain-PAD between T2DM patients and HCs were conducted by Mann-Whitney U test. Finally , Pearson correlation coefficient (r) was calculated between Brain-PAD and duration of disease and cognition . Results: Poor performance in auditory verbal learning test (AVLT)-delayed recall , AVLT-recognition , symbol digital modalities test (SDMT) (P < 0. 05) , and increased Brain-PAD were ob- served in T2DM patients , compared with HCs [1 . 619 ( - 4. 001 , 8. 272) years vs - 1 . 289 ( - 4. 128 , 4. 134) years , Z = 2. 056 , P = 0. 034] . Notably , the median of Brain-PAD in T2DM group was positive , indicating that the brain of T2DM patient maybe relatively “older”than his chronological age . Brain-PAD in T2DM group was as- sociated with performance in AVLT-immediate recall ( r = 0. 291 , P = 0. 003) , AVLT-delayed recall ( r = 0. 248 , P = 0. 011) , SDMT( r = 0. 376 , P = 0. 001) and trail making test (TMT)-A ( r = - 0. 206 , P = 0. 036) . However , the relationships between Brain-PAD and duration of T2DM were not explored . Conclusion Decreased cognitive function in patients with T2DM is demonstrated in this study . The machine learning prediction model based on sMRI supports the identification of brain aging objectively in patients with T2DM .

Objective To explore the value of amide proton transfer(APT)imaging combined with diffusion weighted imaging(DWI)in the assessment of neurovascular invasion(NVI)of stage T3/T4 rectal cancer.Methods The clinical and MR imaging data of 46 patients with rectal cancer were analyzed retrospectively and divided into NVI positive group and NVI negative group according to the pathological results of NVI.The differences of APT values[maximum APT(APTmax)value,minimum APT(APTmin)value,mean APT(APTmean)value]and apparent diffusion coefficient(ADC)value between the two groups were compared,and the diagnostic efficiency was analyzed by receiver operating characteristic(ROC)curve.Results The APTmax and APTmean values in the NVI positive group were significantly higher than those in the NVI negative group,while the ADC value in the NVI positive group was significantly lower than that in the NVI negative group(P＜0.05).The area under the curve(AUC)of APTmax,APTmean and ADC values for NVI identification were 0.717,0.722 and 0.751,respectively.The AUC of the three indexes combined to identify NVI was 0.858.The combined AUC of the three indexes was larger than that of APTmax,APTmean and ADC alone(P＜0.05).Conclusion APT imaging combined with DWI has a high value in the evaluation of NVI of stage T3/T4 rectal cancer,which can provide guidance for clinical treatment.

Objective To explore the value of amide proton transfer(APT)imaging combined with diffusion weighted imaging(DWI)in the assessment of neurovascular invasion(NVI)of stage T3/T4 rectal cancer.Methods The clinical and MR imaging data of 46 patients with rectal cancer were analyzed retrospectively and divided into NVI positive group and NVI negative group according to the pathological results of NVI.The differences of APT values[maximum APT(APTmax)value,minimum APT(APTmin)value,mean APT(APTmean)value]and apparent diffusion coefficient(ADC)value between the two groups were compared,and the diagnostic efficiency was analyzed by receiver operating characteristic(ROC)curve.Results The APTmax and APTmean values in the NVI positive group were significantly higher than those in the NVI negative group,while the ADC value in the NVI positive group was significantly lower than that in the NVI negative group(P＜0.05).The area under the curve(AUC)of APTmax,APTmean and ADC values for NVI identification were 0.717,0.722 and 0.751,respectively.The AUC of the three indexes combined to identify NVI was 0.858.The combined AUC of the three indexes was larger than that of APTmax,APTmean and ADC alone(P＜0.05).Conclusion APT imaging combined with DWI has a high value in the evaluation of NVI of stage T3/T4 rectal cancer,which can provide guidance for clinical treatment.

Objective To observe the value of machine learning(ML)model based on chest non-contrast CT(NCCT)radiomics for diagnosing metabolic syndrome(MetS)in males.Methods A total of 792 males who would undergo chest NCCT and bone density CT examination for physical check-up were prospectively enrolled and divided into training set(n=554,including 171 cases of MetS)and validation set(n=238,including 70 cases of MetS)at the ratio of 7∶3.Chest NCCT was performed,ROI of liver,intra-abdominal fat and skeletal muscle were delineated,and visceral fat area(VFA)at L2-3 intervertebral disc level was measured.Then radiomic signature(RS)of liver,intra-abdominal fat and skeletal muscle were established,and ML models were constructed using logistic regression(LR),random forests(RF)and extreme gradient boosting(XGBoost)algorithms,respectively,and their diagnostic performance were observed.Results Significant difference of age was found between MetS and non-MetS males in training set(P=0.010),while of RS scores were noticed in both training set and validation set(all P＜0.001).Combined ML models were constructed with age and RS.The area under the curve(AUC)of combined LR,RF and XGBoost models for diagnosing male MetS in training set was 0.899,0.996 and 0.943,while that in validation set was 0.861,0.860 and 0.876,respectively.Combined XGBoost model had the best performance.Conclusion XGBoost model based on chest NCCT radiomics was helpful for diagnosing male MetS.Combining with age could further improve its efficacy.

Objective:To investigate the value of nomogram based on radiomics features of CT enterography (CTE) combined with clinical characteristics to predict secondary loss of response (SLOR) after infliximab (IFX) treatment in patients with Crohn′s disease (CD).Methods:This study was a case-control study. Clinical and imaging data of 155 patients with CD diagnosed at the First Affiliated Hospital of Anhui Medical University from March 2015 to July 2022 were retrospectively collected. The patients were divided into a training set ( n=108) and a testing set ( n=47) in the ratio of 7∶3 by stratified sampling method. All patients were treated according to the standardized protocol and were classified as SLOR (43 in the training set and 18 in the testing set) and non-SLOR (65 in the training set and 29 in the testing set) according to treatment outcome. Based on the data from the training group, independent clinical predictors of SLOR after IFX treatment were screened in the clinical data using univariate and multivariate logistic regression analysis to establish a clinical model. Intestinal phase images were selected to be outlined layer by layer along the margin of the lesion to obtain the volume of the region of interest to extract the radiomics features. The radiomics features were screened using univariate analysis and the minimum absolute shrinkage and selection operator to establish the radiomics model. Multivariate logistic regression analysis was used to build a combined clinical-radiomics model based on the screened clinical independent predictors and radiomics characters, then a nomogram was drawn. The predictive efficacy of the 3 models for SLOR after IFX treatment was assessed by receiver operating characteristic curves, and the area under the curve (AUC) was calculated. The decision curve analysis was applied to evaluate the clinical utility of the models. Results:Disease duration ( OR=1.983, 95% CI 1.966-2.000, P=0.046) and intestinal stenosis ( OR=1.246, 95% CI 1.079-1.764, P=0.015) were identified as the independent predictors of SLOR in the clinical data, and a clinical model was established. Totally 9 radiomics features were included in the radiomics model. The AUCs of clinical, radiomics, and combined models for predicting SLOR after IFX treatment in CD patients were 0.691 (95% CI 0.591-0.792), 0.896 (95% CI 0.836-0.955), and 0.910 (95% CI 0.855-0.965) in the training set, and 0.722 (95% CI 0.574-0.871), 0.866 (95% CI 0.764-0.968), and 0.889 (95% CI 0.796-0.982) in the testing set. Decision curve analysis in the testing set showed higher net clinical benefits for both the radiomics model and combined model than the clinical model, and combined model had higher net clinical benefits than the radiomics model over most threshold probability intervals. Conclusions:CTE-based radiomics model can effectively predict SLOR after IFX treatment in patients with CD, and a combined model by incorporating clinical characteristics of disease duration and intestinal stenosis can further improve the predictive efficacy.

Objective To explore the value of combined prediction model based on clinical and CT radiomics features in discriminating atypical pulmonary hamartoma(APH)from atypical lung adenocarcinoma(ALA).Methods A total of 290 patients with APH and ALA confirmed by pathology were retrospectively selected.250 patients from the First Affiliated Hospital of Anhui Medical University were randomly assigned into a training set(APH=91,ALA=84)and an internal validation set(APH=39,ALA=36)at a ratio of 7∶3,and other 40 patients from the First Affiliated Hospital of USTC were assigned as an external validation set(APH=21,ALA=19).The independent model and multivariate logistic regression combined model were constructed using the selected clinical-CT features and radiomics features,respectively,and a nomogram was drawn.Receiver operating characteristic(ROC)curve and DeLong test were used to evaluate and compare the performances of the models.Results The area under the curve(AUC)of the combined model established by 3 clinical-CT features and 4 radiomics features in the training set was 0.980,which was higher than that of clinical-CT model(AUC=0.885,P＜0.001)and radiomics model(AUC=0.975,P=0.042).The AUC of the combined model in the internal and external validation sets(0.963 vs 0.917)were also higher than those of clinical-CT model(0.858 vs 0.774)and radiomics model(0.953 vs 0.897),respectively.Conclusion The combined prediction model based on clinical and CT radiomics features can improve the differential diagnosis ability of APH and ALA.

Objective To investigate the mechanism by which swertiamarin(STM)ameliorates CD-like colitis in mice.Methods A Caco-2 cell model of TNF-α-stimulated apoptosis was established and divided into three groups:Con,TNF-α and STM,and the effects of STM on apoptosis and barrier function were assessed by Tunel staining,western blotting,immunofluorescence,and transepithelial electric resistance(TEER).A mouse model of 2,4,6-trinitrobenzenesulfonic acid(TNBS)-induced CD-like colitis was established to assess the effects of STM on colitis,intestinal barrier function and epithelial cell apoptosis.The regulatory role of the PI3K/AKT pathway in STM-induced resistance to intestinal epithelial cell apoptosis was investigated in both the cell model and mouse models.Results TUNEL staining showed that in Caco-2 cells with TNF-α stimulation,STM treatment significantly reduced the percentage of TUNEL-stained cells(P<0.05).STM obviously reduced TNF-α-induced enhancement of cleaved-caspase 3 and Bax expressions(P<0.05),increased Bcl-2 expression(P<0.05),protected intestinal barrier integrity and function by restoring transepithelial electrical resistance(TEER)of the cells,promoted normal localization and expressions of the tight junction proteins(ZO1 and claudin 1)(P<0.05),and inhibited the expression of pro-inflammatory factors(IL-6 and CCL3)(P<0.05)in TNF-α-stimulated Caco-2 cells.In the mouse models,STM significantly alleviated TNBS-induced CD-like colitis and intestinal barrier dysfunction(P<0.05)as shown by improved weight loss,lowered Disease Activity Index(DAI)score and inflammation score,reduction of IL-6 and CCL3 release,and restoration of intestinal barrier permeability,colonic TEER,bacterial translocation,and localization and expressions of the tight junction proteins.Mechanistically,STM inhibited the expressions of p-PI3K and p-AKT in both the cell model and mouse model(P<0.05),and treatment with 740Y-P(a PI3K/AKT pathway activator)significantly attenuated the inhibitory effect of STM on TNF-α-induced apoptosis in Caco-2 cells(P<0.05).Conclusion STM inhibits intestinal epithelial cell apoptosis at least in part by suppressing activation of the PI3K/AKT pathway to ameliorate intestinal barrier dysfunction and colitis in mice.

Objective To discuss the value of clinical radiomic nomogram(CRN)and deep convolutional neural network(DCNN)in distinguishing atypical pulmonary hamartoma(APH)from atypical lung adenocarcinoma(ALA).Methods A total of 307 patients were retrospectively recruited from two institutions.Patients in institu-tion 1 were randomly divided into the training(n=184:APH=97,ALA=87)and internal validation sets(n=79:APH=41,ALA=38)in a ratio of 7∶3,and patients in institution 2 were assigned as the external validation set(n=44:APH=23,ALA=21).A CRN model and a DCNN model were established,respectively,and the performances of two models were compared by delong test and receiver operating characteristic(ROC)curves.A human-machine competition was conducted to evaluate the value of AI in the Lung-RADS classification.Results The areas under the curve(AUCs)of DCNN model were higher than those of CRN model in the training,internal and external validation sets(0.983 vs 0.968,0.973 vs 0.953,and 0.942 vs 0.932,respectively),however,the differences were not statistically significant(p=0.23,0.31 and 0.34,respectively).With a radiologist-AI com-petition experiment,AI tended to downgrade more Lung-RADS categories in APH and affirm more Lung-RADS cat-egories in ALA than radiologists.Conclusion Both DCNN and CRN have higher value in distinguishing APH from ALA,with the former performing better.AI is superior to radiologists in evaluating the Lung-RADS classification of pulmonary nodules.