Cardiovascular disease has high disability and mortality rates,posing a serious threat to human health.Carotid atherosclerosis is closely related to cardiovascular events.Being non-invasive,high resolution(HR)-MRI has high resolution and unique advantages for evaluating characteristics of carotid plaques.The research progresses in correlations of HR-MRI characteristics of carotid atherosclerotic plaque and cardiovascular events were reviewed in this article.

Chronic liver disease is one of the leading causes of death worldwide.Accurate early assessment of the severity of hepatic fibrosis is crucial for management of liver disease.Ultrasonography,with its non-invasive,portable and real-time imaging characteristics,has become the preferred method for imaging evaluation of chronic liver diseases.Artificial intelligence(AI)technology can extract massive quantitative features from ultrasound images for subsequent analysis,hence attracted increasing attention in evaluation of hepatic fibrosis.The research progresses of ultrasound combined with AI for evaluating hepatic fibrosis were reviewed in this article.

Objective To observe the value of CT angiography(CTA)radiomics for evaluating the risk of basilar tip aneurysm(BTA)rupture.Methods Totally 133 BTA patients were retrospectively enrolled and divided into ruptured group(n=39)and unruptured group(n=94)based on BT A ruptured or not,also divided into training set(n=93)and test set(n=40)at the ratio of 7∶3.CTA radiomics features of BTA were extracted,the best radiomics features were screened,and the radiomics score(Radscore)was calculated.Then machine learning(ML)models were established with logistic regression(LR),random forest(RF),decision tree(DT)and K-nearest neighbor(KNN)algorithms,respectively.Radscore model was also established,and finally a combined model was constructed based on clinical data,routine imaging findings and Radscore.The efficacy of the above models for evaluating the risk of BTA rupture were comparatively analyzed.Results Finally 4 radiomics features of BTA were obtained.The area under the curve(AUC)of LR,RF,DT and KNN radiomics models for differentiating ruptured and unruptured BTA in training set was 0.770,0.816,0.817 and 0.795,respectively,while that in test set was 0.795,0.793,0.786 and 0.824,respectively,both being not significant different(both P＞0.05).Patient's gender,alcohol consumption history,BTA morphology and Radscore were all independent impact factors of BT A rupture(all P＜0.05),which were used to establish a clinical-routine imaging model.For all 133 cases,AUC of the combination model for differentiating ruptured and unruptured BTA was 0.877,of Radscore model was 0.775,while that of clinical-routine imaging model was 0.677,of the former was significantly higher than of the last two(both P＜0.05).Conclusion CTA radiomics was helpful for evaluating the risk of BTA rupture.Combining with clinical data and routine imaging findings could further improve the value of CTA radiomics.

The mortality and disability rates of intracranial aneurysm(IA)remain extremely high.CT angiography(CTA)has been widely used for first-line examination of IA,yet with limited diagnostic accuracy and time-consuming procedures.Artificial intelligence(AI)developed continuously in recent years,which could help to improve the accuracy of diagnosing IA and predicting its rupture.The research progresses of AI in CT A evaluating IA were reviewed in this article.

Objective To observe the value of machine learning(ML)models based on CT angiography(CTA)morphology combined with blood inflammation indicators for predicting rupture of intracranial aneurysms(IA).Methods Totally 286 IA patients were enrolled,including 143 cases in ruptured group and 143 case in unruptured group.Among them 200 cases(100 in ruptured subgroup and 100 in unruptured subgroup)were taken as training set,while 86 cases(43 in ruptured subgroup and 43 in unruptured subgroup)were taken as validation set.CTA morphological parameters and blood inflammation indicators were compared between subgroups in training set,and the impact factors of IA ruptured among univariate variables were screened using stepwise logistic regression analysis.Logistic regression(LR),classification and regression tree(CART)and backpropagation neural network(BPNN)models were constructed based on the above impact factors,respectively.Receiver operating characteristic curves were drawn,the area under the curves(AUC)were calculated to evaluate the efficacy of these models for predicting IA rupture.Results Neutrophil,neutrophil-lymphocyte ratio,interleukin-10,tumor necrosis factor-α,transforming growth factor-β,as well as tumor width,height and size ratio(SR)were all impact factors of IA rupture(all P＜0.05),and collinearity diagnosis suggested that no covariate relationship existed among these factors.LR,CART and BPNN models had good efficacy for predicting IA rupture in both training and validation sets with AUC of 0.878-0.993,and BPNN model had the best predictive efficacy(AUC of 0.993,0.976).Conclusion ML models based on CTA morphology combined with blood inflammation indicators could be used to predict IA rupture effectively,among which BPNN model had the best efficacy.

Objective To observe the correlation between brain abnormal glucose metabolism and striatal dopaminergic neuron damage in early-stage Parkinson disease(PD)patients.Methods Thirty-two early-stage PD patients(PD group)and 18 healthy individuals(control group)were prospectively enrolled,and 18F-FDG and 18F-9-fluoropropyl-(+)-dihydrotetrabenazine(18 F-FP-DTBZ)PET/MR brain imaging were performed.The degrees of uptake were compared between groups,and the correlation between brain abnormal glucose metabolism and striatal dopaminergic neuron damage was analyzed.Results Compared with control group,18F-FDG PET showed that in PD group glucose metabolism decreased in bilateral frontal and parietal lobes but increased in bilateral putamen,pons and bilateral cerebellum(all P＜0.05),while18 F-FP-DTBZ PET showed that in PD group glucose metabolism decreased in bilateral caudate nucleus,anterior putamen and posterior putamen(all P＜0.05).In PD group,the mean standard uptake value(SUVmean)of putamen was positively correlated with the standard uptake value ratio(SUVR)of contralateral caudate nucleus(r=0.305,P=0.014),while SUVmean of frontal cortex was positively correlated with SUVR of contralateral and symptomatic caudate nucleus(r=0.352,0.324,both P＜0.05)as well as anterior putamen(r=0.300,0.314,both P＜0.05),SUVmean of the partial cortex in parietal lobe was positively correlated with SUVR of contralateral and symptomatic caudate nucleus and contralateral anterior putamen(r=0.329,0.303,0.330,all P＜0.05).Conclusion Brain abnormal glucose metabolism had certain correlation with striatal dopaminergic neuron damage in early-stage PD patients.

Objective To observe brain function changes in insomnia disorder(ID)patients and therapeutic effect of repeated transcranial magnetic stimulation(rTMS)based on resting-state functional MRI(rs-fMRI).Methods Totally 37 patients with ID(ID group)and 20 healthy subjects(control group)were prospectively enrolled.The scores of sleep condition and psychological state scales were compared between groups,also within ID group before and after rTMS treatment.Brain regions with amplitude of low frequency fluctuations(ALFF)and regional homogeneity(ReHo)being significantly different between groups were evaluated based on brain rs-fMRI,and voxel-based resting-state functional connectivity(FC)analysis was performed in the above regions and the predefined regions of interest.Results Before treatment,Pittsburgh sleep quality index(PSQI),insomnia severity index(ISI),Epworth sleepiness score(ESS),Beck depression inventory(BDI)score and Beck anxiety inventory(BAI)score in ID group were all higher than those in control group(all P＜0.05).ALFF values and ReHo of the right median cingulate and paracingulate gyrus(Cingulum_Mid_R)were lower in ID group than those in control group(all FWE correctedP＜0.05).FC between Cingulum_Mid_R and the left anterior cingulate gyrus and cingulate gyrus(Cingulum_Ant_L)decreased,so did that between the left hippocampus(Hippocampus_L)and the right frontal gyrus(Frontal_Mid_R)(all FWE corrected P＜0.05).After rTMS,PSQI,ISI and ESS scores of ID patients decreased compared to those before treatment(all P＜0.05),but no significant change of the above neuroimaging indicators was detected(all FWE corrected P＞0.05).Conclusion ID caused synchronous decrease of Cingulum_Mid_R ALFF value and ReHo,as well as weakened FC between frontal cingulate gyrus and frontal with lobe limbic system.rTMS could improve sleep and mental state of ID patients,but its impact on neuroimaging needed further investigation.

Objective To observe the value of high-resolution vascular wall imaging(HR-VWI)for differentiating perforating branch subtype and other subtype basilar artery(BA)ischemic stroke.Methods Totally 147 patients with posterior circulation ischemic stroke were retrospectively enrolled and divided into perforating branch group(perforating branch BA atherosclerosis,n=57)and multi-mechanism group(artery-to-artery embolism and/or hypoperfusion,n=90)according to MRI findings and Chinese ischemic stroke subclassification(CISS).Clinical data,HR-VWI and MR angiography parameters were compared between groups,and those being significantly different were included in logistic regression analysis to construct a model.Receiver operating characteristic curve was drawn,and the area under the curve(AUC)was calculated to evaluate the efficacy of the model for differentiating perforating branch subtype and other subtype BA ischemic stroke.Results The proportion of diabetes mellitus(DM)and dorsal plaque were both higher,while proportion of ventral plaque in perforating branch group was lower than those in multi-mechanism group(all P＜0.05).No significant difference of the other clinical data,nor of the maximum wall thickness,lumen eccentricity index,lumen area,wall area,vascular stenosis rate,plaque load,vascular remodeling index and BA course of culprit plaques section was found between groups(all P＞0.05).DM and dorsal plaque were both independent risk factors for perforating BA atherosclerosis,whereas ventral plaque was the independent protective factor(all P＜0.05).The sensitivity,specificity and AUC of the model for differentiating perforating branch subtype and other subtypes of BA ischemic stroke was 82.46％,70.00％and 0.839,respectively.Conclusion HR-VWI could be used to differentiating perforating branch subtype and other subtype BA ischemic stroke.

Objective To observe the value of conventional ultrasound(US)and contrast-enhanced ultrasound(CEUS)for diagnosing partially cystic papillary thyroid carcinomas(PCPTC).Methods Thirty patients with PCPTC(32 nodules)and 50 patients with benign partially cystic thyroid nodules(PCTN)(52 nodules)were retrospectively enrolled.US and CEUS manifestations were compared between groups,and the efficacy of US and US combined with CEUS for diagnosing PCPTC were analyzed.Results Significant differences of margin,solid part echo,liquid part location,microcalcification and blood flow distribution of the nodules showed with US,as well as enhancement phase,enhancement intensity,enhancement uniformity,peripheral high-enhancement ring and regression mode of lesions shown on CEUS were found between groups(all P＜0.05).The area under the curve(AUC)of US combined with CEUS for diagnosing PCPTC was 0.942,significantly higher than that of US alone(0.750,P＜0.001).Conclusion US had certain value for diagnosing PCPTC.Combining with CEUS could effectively improve diagnostic efficacy of US for PCPTC.

Objective To comparatively observe the value of 131I whole-body scanning(WBS)and 131I-SPECT/CT for evaluating residual thyroid tissue,lymph node and distant metastasis,as well as risk of recurrence of differentiated thyroid cancer(DTC)after surgical resection and initial radioactive iodine(RAI)treatment.Methods Totally 367 DTC patients who underwent initial RAI treatment after surgical resection and then 131I-WBS and 131I SPECT/CT scanning were retrospectively collected.131I-WBS and 131I SPECT/CT were compared for identifying residual thyroid,lymph node and distant metastases.According to follow-up results,the risk of DTC recurrence was evaluated based on 131I-WBS and 131I-SPECT/CT,respectively.Results Residual thyroid was detected in 353 cases and suspected in 3 cases with 131 I-WBS,which was diagnosed in 349 cases with 131I-SPECT/CT,and no significant difference was found between 2 methods(P=0.289).131I-WBS detected 36 cases with and suspected 67 cases with lymph node metastases,312 without distant metastases,while 131I-SPECT/CT diagnosed lymph node metastases in 52 cases;131I-WBS detected 20 cases with and suspected 35 cases with distant metastases,while 131I-SPECT/CT diagnosed 60 cases with distant metastases but could not diagnose in 3 cases,304 without distant metastases.The detection rate of 131I-SPECT/CT for lymph node and distant metastasis were both higher than that of 131I-WBS(P=0.018,P＜0.001).During follow-up period,there were 94 cases with low risk,155 with medium risk and 118 with high risk of DTC recurrence according to 131I-SPECT/CT,while 116 cases of low risk,137 of medium risk and 114 of high risk based on 131I-SPECT/CT,and the evaluating results were different between 2 methods in 40 cases(40/367,10.90％).Conclusion Compared with 131I-WBS,131I-SPECT/CT had better clinical value for evaluating lymph node and distant metastases and assessing recurrence risk of DTC after initial RAI treatment.