Objective To observe the value of venous phase CT radiomics combined with clinical features for predicting breast cancer susceptibility gene(BRCA)mutation in patients with epithelial ovarian cancer(EOC).Methods A total of 111 EOC patients diagnosed by surgical pathology and BRCA detection were retrospectively enrolled and divided into training set(n=90,35 BRCA mutations[+]and 55 BRCA mutations[-])and test set(n=21,8 BRCA mutations[+]and 13 BRCA mutations[-])at the ratio of 8∶2.Clinical and CT data were analyzed using univariate and multivariate logistic regression(LR)to screen independent predictors of BRCA mutations in EOC patients,and then a clinical model was established.Based on venous phase CT,the best radiomics features of EOC lesions were extracted and screened,radiomics score(Radscore)was calculated.Machine learning(ML)models were established using random forest(RF),support vector machine(SVM)and LR,respectively,and the optimal ML model was screened.Finally a combined model was constructed based on Radscore and independent predictors.The predictive efficacy and clinical value of each model were evaluated.Results Human epididymis protein 4 was the independent predictor of BRCA mutation in EOC patients,and the area under the curve(AUC)of clinical model was 0.648 and 0.742 in training and test sets,respectively.AUC of RF,SVM and LR model was 0.726,0.763 and 0.860 in training set,0.708,0.750 and 0.700 in test set,respectively,and SVM model was the optimal ML model.AUC of combined model was 0.819 and 0.783 in training and test set,respectively,which in training set was higher than that of clinical model(P=0.022).No significant difference of AUC was found by pairwise comparison of other models in both training and test set(all P＞0.05).Decision curve analysis showed that when the threshold was larger than 0.15,the clinical value of combined model was higher than that of clinical and SVM models.Conclusion Venous phase CT radiomics combined with clinical features could effectively predict BRCA mutation in EOC patients.

Renal tumors are common diseases of urinary system.In recent years,the development of radiomics and artificial intelligence(AI)technology had provided new directions of accurate diagnosis,differential diagnosis,evaluating grade and stage,as well as guiding treatment of renal tumors.The research progresses of radiomics and AI for renal tumors were reviewed in this article.

Objective To observe the value of quantitative CT(QCT)analysis of human body components for predicting microvascular invasion(MVI)status of hepatocellular carcinoma(HCC).Methods Totally 60 HCC patients were retrospectively enrolled and divided into positive group(n=15)and negative group(n=45)based on postoperative pathology findings of MVI or not.Human body composition parameters,including bone mineral density(BMD),subcutaneous fat area(SFA),visceral fat area(VFA),total fat area(TFA)and subcutaneous/visceral fat area ratio(SVR),as well as muscle fat area(MFA),muscle area(MA)and muscle fat infiltration(MFI)of posterior vertebral muscle group based on QCT were compared between groups,and the efficacy of the above parameters for predicting MVI status of HCC was observed.Results SFA,TFA,MFA and MFI were all higher,while MA was lower in positive group than those in negative group(all P＜0.05).The area under the curve(AUC)of SFA,VFA,TFA,MA,MFA and MFI for predicting MVI status of HCC ranged from 0.673 to 0.790(all P＜0.05).TFA and M FI were both independent risk factors of HCC MVI(both P＜0.05),with AUC of 0.790 and 0.759,respectively.Conclusion QCT analysis of human body components was helpful to predicting MVI status of HCC.

Diffuse large B-cell lymphoma(DLBCL)is the most common subtype of non-Hodgkin lymphoma,which demonstrates significant heterogeneity.Some DLBCL exhibit poor responses to chemotherapy,highlighting the urgent need for precise prognostic evaluation methods.As a critical biological parameter,tumor burden closely associated with disease progression and unfavorable prognosis,but representing tumor burden of DLBCL only with anatomical parameters was not enough to comprehensively reflect its biology features.Multiple parameters derived from 18F-FDG PET/CT could characterize metabolic features of tumors,hence enabling accurate quantification of tumor burden and providing a theoretical basis for individualized treatment of DLBCL.The research progresses of 18 F-FDG PET/CT for assessing tumor burden of DLBCL were reviewed in this article.

Imaging examination is a crucial part in diagnosis and treatment of central nervous system infection(CNSI),involving complex imaging sequences and parameters.This consensus was jointly written by multiple CNSI imaging experts in China,aimed to standardize imaging examination of CNSI.

Objective To observe the value of prenatal ultrasound graded management of Sylvian fissure for diagnosing fetal lissencephaly.Methods Totally 39 fetuses with MRI diagnosed lissencephaly who underwent prenatal ultrasound examination were retrospectively enrolled and divided into non-graded management group(n=20)and graded management group(n=19)according to prenatal ultrasound examination before or after the application of prenatal ultrasound graded management of Sylvian fissure(i.e.prenatal ultrasound routine screening for fetal Sylvian fissure morphology).The diagnosis of prenatal ultrasound were compared and analyzed between groups,and the diagnostic value of graded management was evaluated.Results Among 20 fetuses in non-graded management group,prenatal ultrasound showed lissencephaly in 4 fetuses,but only other structural abnormalities in 16 fetuses.Then the latter were re-evaluated based on prenatal ultrasound graded management of Sylvian fissure,among which 4 fetuses could not be evaluated since not standard ultrasonic section,2 fetuses with severe hydrocephalus and Sylvian fissure could not be seen,while Sylvian fissure morphology did not match the corresponding gestational week in 4 fetuses,and type Ⅰ(no platform type)and type Ⅴ(Z-shaped)were noticed in 5 and 1 fetus,respectively.In graded management group,prenatal ultrasound indicated 15 fetuses with lissencephaly,including Sylvian fissure morphology did not match the corresponding gestational week in 6 fetuses,type Ⅰ(no platform type),type Ⅲ(linear type)and type Ⅴ(Z-shaped)were detected in 7,1 and 1 fetus,respectively,while no clear diagnosis was obtained in 4 fetuses.Prenatal ultrasound detection rate of fetal lissencephaly in graded management group(15/19,78.95％)was significantly higher than that in non-graded management group(4/20,20.00％)(P＜0.01).Conclusion Based on graded management of Sylvian fissure could improve the efficiency of prenatal ultrasound for diagnosing fetal lissencephaly.

Objective To observe the value of enhanced MRI"strawberry sign"for differentiating solitary predominantly cystic brain metastasis and glioma.Methods Thirty-four patients with solitary predominantly cystic(cystic proportion greater than 50％)brain metastasis(metastasis group)and 43 with solitary predominantly cystic glioma(glioma group)were retrospectively enrolled,and the value of"strawberry sign"showed on contrast enhanced T1WI(CE-T1WI)for differentiation was analyzed.Results The detection rate of"strawberry sign"in metastasis group was 44.12％(15/34),and the primary cancer was lung adenocarcinoma in 6 cases(6/15,40.00％),small cell lung cancer in 3 cases(3/15,20.00％),as well as lung squamous cell carcinoma,breast cancer,colon adenocarcinoma,endometrioid carcinoma,fallopian tube adenocarcinoma and rectal melanoma each in 1 case(1/15,6.67％).Meanwhile,the detection rate of"strawberry sign"in glioma group was 18.60％(8/43),and all were observed in WHO grade 4 gliomas.The detection rate of"strawberry sign"in metastasis group was higher than that in glioma group,which was not related to patients' gender(P=0.442).The sensitivity,specificity,accuracy,positive predictive value and negative predictive value of"strawberry sign"for differentiating solitary predominantly cystic brain metastasis and glioma was 44.12％,81.40％,64.94％,65.22％and 64.81％,respectively.Conclusion"Strawberry sign"showed on CE-T1WI was helpful for differentiating solitary predominantly cystic brain metastasis and glioma.

Objective To observe the value of machine learning(ML)models based on ultrasound radiomics for preoperatively distinguishing atypical parathyroid tumor(APT)/parathyroid carcinoma(PC)and parathyroid adenoma(PA).Methods Totally 330 primary hyperparathyroidism patients who underwent surgical treatments were retrospectively enrolled and categorized into APT/PC group(n=78)and PA group(n=252)according to surgical pathology and clinical follow-up results,also divided into training set(n=231)and test set(n=99)at the ratio of 7∶3.Based on preoperative ultrasound,545 radiomics features were extracted,and recursive feature elimination(RFE),Kruskal-Wallis or analysis of variance methods were used to screen the features,respectively.Support vector machine(SVM),linear discriminant analysis(LDA),least absolute shrinkage and selection operator logistic regression(LRLASSO),also random forest(RF)and decision tree(DT)algorithms were adopted to construct ML models for differentiating APT/PC and PA,respectively.Then the models were trained in training set,their performance were verified in test set,and a 5-fold cross-validation was adopted to screen out the better combinations.Results Compared with Kruskal-Wallis and analysis of variance methods,the distinguishing efficacy of SVM,LDA,LRLASSO,RF and DT models constructed based on features screened out using RFE method in training set(area under the curve[AUC]=0.870,0.878,0.850,0.847,1.000)and test set(AUC=0.856,0.842,0.827,0.847 and 0.704)were all relatively higher.In test set,the AUC of SVM,LDA,LRLASSO and RF models constructed based on the features screened out using RFE method(included 25,23,17 and 23 features)were all higher than that of DT model(8 features)(all P＜0.001).No significant difference of AUC was found between SVM,LRLASSO or RF models and LDA model(all P＞0.05).The AUC of SVM and RF models were higher than that of LRLASSO model(both P＜0.05),while of SVM and RF models were not significantly different(P＞0.05),indicating that SVM,LDA and RF models were better ones.Conclusion SVM,LDA,LRLASSO,RF and DT models based on ultrasound radiomics could effectively distinguish APT/PC and PA preoperatively,among which SVM,LDA and RF models had better diagnostic efficacy.

Fetal optic nerve,optic chiasma(OC)and optic tract are collectively referred to as OC structures.With the improvement of ultrasound instrument accuracy and scanning methods,prenatal observation of fetal OC structures has become possible,and evaluation on the morphology and size of fetal OC structures can provide reference for clinical diagnosis of related diseases.The research progresses of prenatal ultrasound evaluation on fetal OC structures were reviewed in this article.

Objective To investigate the value of geometric parameters of vertebrobasilar artery(VBA)for judging whether vertebral artery(VA)provide cross blood supply of posterior cerebral artery(PCA)blood supply area.Methods MR T2-fluid attenuated inversion recovery(FLAIR),3D time of flight(TOF)MR angiography(MRA)and territorial arterial spin labeling(t-ASL)images of 244 healthy adults were prospectively acquired.The angles between left VA(LVA)or right VA(RVA)and basilar artery(BA)were measured,and the sum and difference between the two angles were calculated(referred to as the sum of VA angles and the difference of VA angles),and the differences of diameters of LVA and RVA were measured and calculated(referred to as the difference of VA diameters).VA perfusion distribution type in PCA blood supply area were observed,and those with type Ⅲ or Ⅵ were enrolled in cross group,while those with type Ⅱ or Ⅴ were enrolled in non-cross group,respectively.The geometric parameters of VBA were compared between groups.Receiver operating characteristic(ROC)curve of parameters being significant different between groups were drawn,and the efficacy of these parameters for judging whether VA provide cross blood supply of PCA area were evaluated.Results There were 34 subjects in cross group and 75 in non-cross group.The sum of VA angles and the difference of VA angles in cross group were both larger than those in non-cross group(both P＜0.05),while the difference of VA diameters were not significantly different between groups(P＞0.05).The AUC of the difference of VA angles for judging whether VA provide cross blood supply of PCA area was 0.676(P＜0.05),while of the sum of VA angles was 0.598(P=0.103).Conclusion The angle differences of LVA and RVA with BA had certain application value for judging whether VA provide cross blood supply of PCA area.