Abstract:Pheochromocytomas present with diverse clinical manifestations,and surgical resection is the optimal treatment.However,intraoperative risks are challenging to assess effectively.Computed tomography(CT)imaging is a crucial tool for localization,diagnosis,and predicting therapeutic efficacy.In recent years,radiomics research based on CT has demonstrated significant advantages and potential applications in tumor differential diagnosis,classification,biological behavior assessment,and intraoperative risk evaluation.Moreover,the development of omics models based on tumor characteristics offers a reliable and non-invasive alternative to guide precision medicine procedures.This study aimed to explore the application and value of CT radiomics in the intraoperative risk assessment of pheochromocytomas,assisting physicians in related departments to better understand the research findings associated with radiomics.

Abstract:Objective:In this study,we aim to investigate the correlation between carotid artery fat density and atherosclerotic stenosis,providing a clinical reference for the early identification of carotid atherosclerotic stenosis.Methods:A retrospective analysis was conducted on patients with complete clinical data and confirmed diagnoses who underwent carotid computed tomography angiography(CTA)at Panjin Central Hospital between January 2023 and August 2023.A total of 224 blood vessels were included in the study.Patients were divided into a stenosis group and a control group based on the presence or absence of atherosclerosis.The stenosis group was further categorized into mild,moderate,and severe stenosis,and classified into Groups Ⅰ,Ⅱ,and Ⅲ based on age.Additionally,patients were classified into symptomatic and asymptomatic groups based on their symptom status,and the correlation between perivascular fat density(PFD),carotid atherosclerotic stenosis,and cerebrovascular events was explored.Results:Hypertension,hyperlipidemia,and age were significantly associated with carotid atherosclerotic stenosis.PFD increased with the degree of stenosis and age.Correlation analysis revealed a positive correlation between PFD,age,history of hypertension,history of hyperlipidemia,and carotid artery stenosis.The PFD in the symptomatic group was higher than in the asymptomatic group,and the difference remained statistically significant after binary logistic correction for confounding factors.Conclusion:Carotid artery PFD is an independent risk factor for carotid atherosclerotic stenosis.Patients with symptomatic carotid artery stenosis exhibit higher carotid fat density compared to their asymptomatic counterparts.

Abstract:Objective:To analyze the factors affecting the objective image quality of third-generation high-pitch dual-source coronary CT angiography,optimize the scanning protocol to enhance image quality,and reduce radiation dose and iodine intake.Methods:A total of 684 consecutive patients who underwent third-generation high-pitch dual-source coronary CT angiography were divided into two groups based on objective image quality(poor or good).Differences in basic clinical information and scanning parameters between the two groups were analyzed,and a prediction model was developed.Results:Significant differences were observed between the two groups in body mass index(BMI),contrast concentration,contrast dosage,injection rate,and tube voltage.A binary logistic regression model was constructed,yielding a sensitivity of 61.32%and a specificity of 83.54%.The model was further transformed into a nomogram prediction model.Conclusion:Individualized scanning protocols for third-generation high-pitch dual-source coronary CT angiography can help achieve high-quality imaging while minimizing radiation dose and iodine intake.

Abstract:This study explores the feasibility of opportunistic osteoporosis screening using an artificial intelligence(AI)-based bone mineral density(BMD)measurement system on chest computed tomography(CT)scans.A retrospective analysis was conducted on 462 patients who underwent both dual-energy X-ray absorptiometry(DXA)and chest CT in our department between August 2023 and July 2024.The cohort included 317 postmenopausal women and 145 men aged>50 years.BMD measurements from the AI system and DXA were compared.Using the T-value measured by DXA as the reference standard,the consistency and correlation between AI-based and DXA-measured BMD were analyzed.Significant differences in height,weight,DXA T-value,and AI-derived BMD were observed between men aged>50 years and postmenopausal women.The AI-derived BMD showed a correlation coefficient of 0.767 with DXA T-values and a κ value of 0.697.The area under the ROC curve for AI-based diagnosis of osteoporosis was 0.941(95%CI 0.914-0.968),with a sensitivity of 85.71%and a specificity of 93.84%.The AI-based BMD measurement system demonstrates strong correlation and good agreement with DXA,supporting its feasibility for opportunistic osteoporosis screening.

Abstract:Objective:To analyze the value of coronary CT angiography(CCTA)using dual-source CT with Turbo-Flash mode to evaluate coronary artery stenosis.Methods:A total of 150 patients who underwent CCTA in hospital between January 2023 and December 2024 were selected and divided into an observation group(dual-source CT with Turbo-Flash mode,n=75)and control group(retrospective electrocardiographic-gating mode,n=75)according to the scan mode used.The scan parameters(CT-derived fractional flow reserve(CT-FFR),intraluminal contrast density,Agatston scores for calcification,and calcification volume),image quality(CT value and signal-to-noise ratio(SNR)),and radiation doses(dose length product(DLP),volume CT dose index(CTDIvol),and ED)of the two groups were analyzed.Results:CT-FFR,intraluminal contrast density,and Agatston score for calcification were greater in the observation group than in the control group.Under dual-source CT with Turbo-Flash mode,as the degree of coronary artery stenosis increased,the CT-FFR,intraluminal contrast density,and Agatston score for calcification increased.Taking DSA as the gold standard,the diagnostic sensitivity,specificity,and accuracy for moderate-severe coronary artery stenosis in the observation group were 96.43％,87.23％,and 90.67％,respectively.No statistically significant difference was observed compared with the control group.The differences in CT values,SNR,and image quality between the two groups were not statistically significant.DLP,CTDIvol,and ED were lower in the observation group than in the control group.Conclusion:Dual-source CT with Turbo-Flash mode for CCTA can achieve high accuracy and image quality when evaluating coronary artery stenosis.The degree of stenosis can be evaluated through quantitative parameters.Moreover,the DLP,CTDIvol,and ED are relatively low.These findings are worthy of clinical promotion and application.

Abstract:Objective:To explore the application value of whole-brain computed tomographic perfusion(CTP)imaging in the assessment of collateral circulation status in acute ischemic stroke.Method:Clinical data were retrospectively collected from 92 patients with acute ischemic stroke,admitted to the Suqian First People's Hospital between January 2021 and December 2023.All patients underwent whole-brain CTP examination within 12h after symptom onset.The patients were divided into two groups based on their collateral circulation status:poor collateral circulation group(n=43)and good collateral circulation group(n=49).Emphasis was placed on the role of CTP in evaluating collateral circulation status in patients with acute ischemic stroke.Results:The time from onset to hospitalization in the poor collateral circulation group was longer than that in the good collateral circulation group,and the proportion of patients with hypertension and hyperlipidemia in the poor collateral circulation group was higher than that in the good collateral circulation group.In addition,among CTP parameters,cerebral blood volume(CBV)and cerebral blood flow(CBF)in the infarcted area of the poor collateral circulation group were lower than those in the good collateral circulation group,and the mean transit time(MTT)was longer than that in the good collateral circulation group.Multivariate logistic regression analysis showed that CBV,CBF,and MTT are all factors influencing collateral circulation status in patients with acute ischemic stroke.Receiver operating characteristic(ROC)curves were drawn,and the results showed that the area under the curve(AUC)values of CBV,CBF,and MTT in evaluating the collateral circulation status of patients with acute ischemic stroke were all greater than 0.7,which had a certain evaluation value.The AUC of the combined evaluation was higher at 0.961.Conclusion:The whole-brain CTP parameters CBV,CBF,and MTT are related to the collateral circulation status in acute ischemic stroke and can be used as effective imaging examination tools for the clinical evaluation of collateral circulation status.

Abstract:Objective:To investigate the feasibility of using non-gated high-pitch chest computed tomography(CT)combined with artificial intelligence(AI)technology to measure the coronary artery calcium score.Methods:In this retrospective analysis,we reviewed the images of 24 patients who underwent both non-gated high-pitch chest CT and coronary artery calcium scoring CT.The scanning parameters were as follows:(1)non-gated high-pitch chest CT scan:CarekV and CareDose 4D,ref.kV 110,ref.mAs 80,pitch 3,filter core BR40;(2)ECG-gated coronary artery calcification score CT:CarekV,CareDose 4D,ref.kV 120,ref.mAs 50,pitch 0.15,acquisition R-R interval 35％and 75％,filter core QR36.The image window width/window level of the two groups was 345/50,and the slice thickness/interval was 3 mm/1.5 mm.The images of the two scan groups were divided into three subgroups according to the three measurement methods(Syngo.via workstation measurement,AI measurement,and AI+manual correction measurement).The image calcification score(agatston score,AS)was measured,risk classification was performed,and the time taken for the workstation measurement and the AI+manual correction measurement was recorded.The volume(CT)dose index(CTDIvol)and dose-length product(DLP)of the two examinations were recorded,and the effective dose(ED)was calculated.SPSS Statistics software(version 27.0)was used for the statistical analysis.Results:The tube voltages of the high-pitch chest CT were 100,110,and 120kV,and the coronary artery calcium score was 120kV.EDs of high-pitch chest CT and coronary artery calcium score CT were(2.1±0.4)and(2.1±0.7)mSv,respectively.The three measurement methods used for high-pitch chest CT showed significant differences in AS,but the consistency of AS was high(ICC:0.988).Regarding AS measurement,high-pitch chest CT combined with AI(ICC:0.990),high-pitch chest CT using a workstation(ICC:0.988),and gated calcium scoring combined with AI(ICC:0.980)showed no significant differences or high consistency compared to the workstation for coronary artery calcium scoring.The risk classification obtained by the AI was highly consistent,and the weighted kappa coefficients were between 0.818 and 1.000.The time taken for measurements using the workstation and AI+manual correction in both scanning groups showed significant differences.Conclusion:Non-gated high-pitch chest CT combined with AI can provide reliable results for artery calcium scores and risk classification with reduced time consumption,demonstrating substantial clinical utility.

Abstract:Purpose:To assess the clinical efficacy of integrating deep learning reconstruction(DLR)with contrast-enhancement-boost(CE-boost)in 80kVp head and neck CT angiography(CTA)using substantially lowered radiation and contrast medium(CM)doses,compared to the standard 100kVp protocol using hybrid iterative reconstruction(HIR).Methods:Sixty-six patients were prospectively enrolled and randomly assigned to one of two groups:the low-dose group(n=33),receiving 80kVp and 28mL contrast medium(CM)with a noise index(NI)of 15;and the regular-dose group(n=33),receiving 100kVp and 40mL CM with an NI of 10.For the low-dose group,images underwent reconstruction using both hybrid iterative reconstruction(HIR)and deep learning reconstruction(DLR)at mild-,standard-,and strong-strength levels,both before and after combination with contrast enhancement-boost(CE-boost).This generated eight distinct datasets:L-HIR,L-DLRmild,L-DLRstandard,L-DLRstrong,L-HIR-CE,L-DLRmild-CE,L-DLRstandard-CE,and L-DLRstrong-CE.Images for the regular-dose group were reconstructed solely with HIR(R-HIR).Quantitative analysis involved calculating and comparing CT attenuation,image noise,signal-to-noise ratio(SNR),and contrast-to-noise ratio(CNR)within six key vessels:the aortic arch(AA),internal carotid artery(ICA),external carotid artery(ECA),vertebral arteries(VA),basilar artery(BA),and middle cerebral artery(MCA).Two radiologists independently assessed subjective image quality using a 5-point scale,with statistical significance defined as P<0.05.Results:Compared to the regular-dose group,the low-dose protocol achieved a substantial reduction in contrast media volume(28mL versus 40mL,a 30%decrease)and radiation exposure((0.41±0.08)mSv versus(1.18±0.12)mSv,a 65%reduction).Both L-DLRstandard and L-DLRstrong delivered comparable or superior SNR and CNR across all vascular segments relative to R-HIR.However,subjective image quality scores for L-DLR at all strength levels fell below those for R-HIR(all P<0.05 for both readers).Combining CE-boost with the low-dose protocol significantly enhanced the objective image performance of L-DLRstrong-CE(all P<0.05)and produced subjective image scores comparable to R-HIR(reader 1:P=0.15;reader 2:P=0.06).Conclusion:When compared to the standard 100kVp head and neck CTA,the combination of the DLR and CE-boost techniques at 80kVp can achieve a 30%reduction in contrast dose and a 65%reduction in radiation dose,while maintaining both objective and subjective image quality.

Abstract:In engineering seismic refraction exploration in mountainous areas with strong transverse heterogeneity,an observation system with shots distributed in receivers array is often employed.The velocity profile is then inverted from first-arrival times using ray tomography.However,in the case of a long survey line,the influence of the connecting mode of adjacent arrays on the field workload and inverted profile has not been investigated in detail and clearly.This paper examines three observation systems:adjacent arrays connected head to tail,adjacent arrays connected head to tail and with out-array shots,and adjacent arrays with partial overlap.Through an analysis of the ray coverage in a vertical gradient velocity model,the ray tracing and inversion on the two-layer model,and the inversion of the field data,the inversion quality and field workload of the three observation systems are evaluated comprehensively.Because of its best inversion effect and the lowest field burden,the system with adjacent arrays connected head to tail and with out-array shots is considered to be optimal observation system.

Abstract:Objective:To compare the differences in coronary computed tomography angiography(CCTA)plaque characteristics between ischemic and non-ischemic groups and to explore qualitative and quantitative plaque features that are valuable for diagnosing myocardial ischemia.This study aimed to apply these indicators in clinical practice to identify patients with potential myocardial ischemia as early as possible.Methods:A retrospective analysis was conducted on patients with coronary heart disease who underwent invasive coronary angiography for fractional flow reserve(FFR)measurement and CCTA scanning in the cardiology department of our hospital between January 2022 and December 2024.General information was analyzed at the patient level,whereas CCTA plaque characteristics were analyzed at the vessel level.Plaque analysis was performed by two radiologists with more than five years of experience in CCTA diagnosis using semi-automatic plaque analysis software blinded to the patient groups.Results:A total of 163 patients were included in the study,with no statistically significant differences in general information between the ischemic and non-ischemic groups.A total of 253 vessels were included,with 114 vessels in the ischemic and 139 in the nonischemic vessel groups.Among the qualitative plaque characteristics,the napkin-ring sign and punctate calcification were more prevalent in the ischemic than in the nonischemic vessel group.No statistically significant differences were observed in positive remodeling and low-density plaque indicators between the two groups.Among the quantitative plaque characteristics,statistically significant differences in plaque length(PL),plaque burden(PB),minimum lumen area(MLA),minimum diameter stenosis(MDS),maximum area stenosis(MAS),and remodeling index(RI)were observed between the two groups.There were no statistically significant differences in plaque volume(PV)or edge irregularity(EI).The areas under the curve(AUC)for diagnosing myocardial ischemia in the vascular supply areas of the plaques using PL,PB,MLA,MDS,MAS,and RI were 0.672,0.712,0.843,0.830,0.821,and 0.655,respectively.The AUC for the combined detection was 0.844,which was higher than that for any single indicator.Conclusion:CCTA plaque characteristic analysis has great potential for predicting myocardial ischemia,and the combined use of multiple quantitative plaque indicators provides higher diagnostic efficacy.

Abstract:Objective:To explore the feasibility of cardiac magnetic resonance imaging(MRI)for evaluating the complexity of the left ventricular trabeculae in patients with hypertension,analyze the relationship between MRI characteristics and left ventricular function,and preliminarily investigate the correlation between left ventricular trabecular mass and hypertension severity.Methods:Cardiac function parameters and left ventricular trabecular mass were measured using cardiac MRI in 84 patients with hypertension and 30 healthy volunteers.The left ventricular myocardial trabecular mass was calculated using the following formula:(left ventricular end-diastolic volume-blood volume)×1.05-papillary muscle mass.Analysis of variance(ANOVA)was used to investigate differences in left ventricular function and left ventricular trabecular mass among the participants,and multivariate linear regression was used to analyze independent correlations between myocardial trabeculae and clinical indicators,as well as left ventricular MRI parameters.Results:When comparing left ventricular function parameters,left ventricular end-diastolic volume(LVEDV),left ventricular end-systolic volume(LVESV),second peak filling rate(PFR2),second filling volume(FV2)and total filling volume(FV)in the normal group were significantly lower than those in the hypertension groups Ⅰ,Ⅱ,and Ⅲ.The data were Bonferroni corrected and the results were consistent.The left ventricular trabecular mass in the hypertension groups Ⅰ,Ⅱ,and Ⅲwas found to be significantly higher than that in the normal group,and there was a significant difference between grade III and grade I hypertension.Multiple linear regression analysis showed that heart rate,systolic blood pressure,left ventricular myocardial mass,and left ventricular ejection fraction(LVEF)were significantly correlated with left ventricular trabecular mass and negatively correlated with left ventricular trabecular mass,while systolic blood pressure and left ventricular myocardial mass were positively correlated.Conclusion:Left ventricular wall hypertrabeculation is a common phenomenon in patients with hypertension.An increase of left ventricular trabeculation is closely related to functional changes in the left ventricle.

Abstract:Objective:To investigate the value of constructing a nomogram model based on arterial-phase imaging radiomics features combined with clinical-CT features for the differentiation between squamous lung cancer(SCC)and adenocarcinoma of the lung(ADC).Methods:Retrospectively,85 patients with lung cancer who underwent puncture pathology biopsy or surgery in our hospital,from August 2021 to September 2023,were collected as a training set.Concurrently,40 patients with pathologically confirmed lung cancer in our hospital,from May 2023 to June 2024,were collected as a validation set.All patients underwent chest CT enhancement.The training set was divided into the SCC group(n=29)and the ADC group(n=56)based on the pathology.General clinical data and CT image characteristics of the two groups of patients were compared and differences were identified.Independent predictors were screened using unifactorial and multifactorial logistic regression analyses,and a clinical-CT model was constructed.ITK Snap software was applied to extract the radiomics features of the arterial-phase images,and the intragroup correlation coefficient(ICC),Roruta feature screening,and least absolute shrinkage and selection operator(LASSO)were sequentially used to downsize the extracted radiomics features,screen out the meaningful features,construct the arterial-phase image radiomics model using Logistic regression,and compute the model's image radiomics score(Rad-score).A multifactor logistic regression analysis was used to screen the independent variables with meaningful clinical-CT characteristics and Rad-score to construct a joint model,and a nomogram graph was plotted.ROC curves,calibration curves,H-L test,Delong test,and clinical decision curves(DCA)were applied to evaluate the clinical-CT,radiomics,and nomogram models.Results:The results of univariate analysis showed that there were more lobular signs and necrotic cavity signs,and fewer carcinoembryonic antigen(CEA),vascular cluster signs,pleural pulling,and burr signs in the SCC than in the ADC group.The above independent variables were included in the multifactorial Logistic analysis for further screening,and the results showed that CEA,lobular sign,pleural pull,and burr sign were independent risk factors.The area under the curve(AUC)values for the training and validation sets of the clinical-CT model constructed based on this were 0.623 and 0.786,respectively.A total of eight meaningful features were screened after dimensionality reduction of the radiomics features,which were three first-order features and five second-order features.The ROC curve analysis showed that the AUC values for the training and validation sets of the radiomics model were 0.830 and 0.846,respectively;and the AUC values for the training and validation sets of the nomogram model were 0.913 and 0.922,respectively.The Delong test showed that the AUC values of the nomogram model were all significantly higher than those of the clinical-CT model and the radiomics model;the Hosmer-Lemeshow test showed that the clinical-CT model,the radiomics model,and the nomogram model were all well fitted;calibration curve analysis showed that the predictive probability curve of the nomogram model was closest to the ideal curve,with better predictive accuracy;and DCA analysis showed that the AUC of the nomogram model was the largest,with the highest net clinical benefit.Conclusion:Constructing a nomogram model based on arterial-phase imaging radiomics features combined with clinical-CT features has some diagnostic value in differentiating SCC from ADC,providing a new diagnostic modality for noninvasive differentiation.

Abstract:Phase identification is the most fundamental and important task in seismology and is crucial to in-depth analyses of regional seismic activity and the precise detection of underground structures.The considerable growth in earthquake observation data and the rapid advances in machine learning technology have meant that various machine learning-based seismic phase recognition methods have emerged,such as Eqtransformer and Phasenet,which have significantly promoted the development of this field.However,these models often face challenges when processing short-period dense array data,such as high missed detection rates for small microseismic events and the incomplete waveform recognition of medium-to-strong earthquakes.To address these issues,this study developed a microseismic phase recognition model that uses channel and multi-head attention mechanisms.It effectively integrates coarse-and fine-grained features through residual connections,optimizes feature representation using a channel attention mechanism,and enhances the ability to focus on key information through a multihead attention mechanism.Training data are derived from multiple sources and have high confidence-to-noise ratios;therefore this study adopted a strategic data augmentation method to construct noisy(including Gaussian random white noise and STEAD dataset noise)and denoised datasets in a 6:4 ratio to improve the generalization ability of the model in complex field noise environments.The experimental results show that compared to existing models,such as Eqtransformer and Phasenet,the proposed model significantly improves the recognition rate for small microseismic events and optimizes the recognition accuracy of P-wave and S-wave arrival times.In addition,the model has a fast recognition speed and can complete the comprehensive recognition of one month of data from a single station within ten minutes,which demonstrates that it can efficiently process big data.This study successfully constructed an efficient and accurate microseismic phase recognition model by introducing advanced attention mechanisms and deep-learning architectures.This model considerably improves the ability to identify small and micro earthquakes,enhances model generalization,accelerates the recognition process,and provides a powerful tool for micro earthquake detection.

Abstract:Objective:This study aimed to explore the applicative value of low tube voltage and low-dose contrast agents in coronary computed tomography angiography(CCTA)of 64 rows CT with different body mass indices(BMI).Methods:The participants were 160 patients with clinically suspected coronary heart disease who underwent CCTA examination and divided into groups A(18.5<BMI<24)and B(24≤BMI<28),with 80 cases in each group.Each group was randomly divided into the control(A1/B1)and experimental groups(A2/B2)with 40 patients in each group.The control group was scanned with 120 kV tube voltage,whereas groups A1 and B1 were injected with 60 mL contrast agent+40 mL physiological saline and 80 mL contrast agent+20 mL physiological saline,respectively.All experimental groups adopted a double low-dose method,with group A2 receiving 80 kV tube voltage,40 mL contrast agent+60 mL physiological saline,and group B2 receiving 100 kV tube voltage,60 mL contrast agent+40 mL physiological saline.All other scanning parameters were the same.After scanning,the images were reconstructed,data were collected,and differences in image quality,radiation dose,and iodine intake were compared between the control and experimental groups.Results:Image qualification rate,excellent rate,SNR,and CNR between groups A1 and A2 had no statistically significant difference.However,group A2 had higher aortic CT values and image noise than group A1.The image qualification rate,excellent rate,aortic CT value,signal-to-noise ratio(SNR),and contrant-to-noise ratio(CNR)in group B2 were higher than in group B1,and there was no difference in image noise between group B1.The volume CT dose index(CTDIvol),dose-length product(DLP),and effective dose(ED)of groups A2 and B2 were lower than those of groups A1 and B1.Compared with group A1,group A2 showed a 68.3%decrease in ED,whereas group B2 showed a 41.6%decrease compared to group B1.The iodine intake of groups A2 and B2 decreased by 33.3%and 25%,respectively.Conclusion:Using low tube voltage and low dose contrast agent in CCTA with different BMI not only ensure image quality,but also significantly reduce radiation dose and iodine intake.

Abstract:Objective:To evaluate the application value of dual-source computed tomography(CT)three-dimensional(3D)stereo localization combined with low-dose scanning in lung biopsy to improve the success rate of puncture and reduce radiation dose.Methods:Sixty patients who underwent CT-guided lung biopsy in our hospital between June 2024 and October 2024 were selected and randomly divided into control and experimental groups(30/group).The control group underwent conventional CT positioning combined with routine-dose scanning,whereas the experimental group underwent dual-source 3D stereotactic CT positioning combined with low-dose scanning.The puncture success rate,operation time,radiation dose,and complication rates were compared between groups.Results:The experimental group had 29 successful punctures(29/30),and the control group had 27 successful cases(27/30).The success rate of the experimental group was slightly higher than that of the control group,but the difference was not statistically significant.The operation time in the experimental group was(20.6±0.596)min,significantly shorter than 30.33±0.687 min in the control group,with a statistically significant difference.The experimental group had three complications(3/30),while the control group had seven(7/30).The complication rate in the experimental group was slightly lower than that in the control group,but the difference was not statistically significant.The volume CT dose index(CTDIvol),dose-length product(DLP),and average effective dose(ED)in the experimental group were(2.443±0.055)mGy,(18.653±0.686)mGy·cm,and(0.317±0.012)mSv,respectively.In the control group,these values were(4.958±0.031)mGy,(42.580±0.544)mGy·cm,and(0.724±0.009)mSv,respectively.The radiation dose in the experimental group was significantly lower than that in the control group.Conclusion:Dual-source CT 3D stereo location combined with low-dose scanning provides significant advantages for lung biopsies.This can significantly improve the accuracy of puncture positioning,reduce the occurrence of complications,reduce the radiation dose,and improve the puncture success rate.This technique offers a safer and more effective approach for the diagnosis and treatment of lung diseases and may be considered for broader implementation in clinical practice.

Abstract:To investigate the effect of external foreign bodies on radiation dose during chest computed tomography(CT)scans under automatic tube current-modulation technology and to assess the necessity of re-scanning a scout image,we retrospectively categorize historical data into foreign body and non-foreign body cohorts.Propensity score matching is employed to balance five covariates:patient gender,examination age,number of image layers,scanning-bed height,and average cross-sectional area of patients.After balancing,we statistically analyze the effect of foreign bodies on the volume CT dose index(CTDIvol)and dose-length product(DLP),and compare the dose increment with the scout-image dose.The study includes 17342 cases,with 4740 cases(27.3%)in the treatment group.Before matching,all five covariates in the treatment group are significantly lower than those in the control group.After matching,3944 pairs of balanced samples are obtained and no significant differences are observed between the two groups in the five covariates.The treatment group shows slightly higher CTDIvol and DLP values compared with the control group.External foreign bodies can slightly increase the radiation dose,although the incremental dose does not differ statistically from that of the scout image.Operators should flexibly determine whether to re-scan the scout image based on specific clinical circumstances.

Abstract:Objective:To explore the value of computed tomography(CT)radiomics machine learning classification models for predicting the staging of non-small cell lung cancer(NSCLC).Methods:We downloaded the Lung 1 dataset from the Cancer Imaging Database(TCIA),selected 291 eligible cell lung cancer patients,and divided them into two groups:Group 1(Stage I and II)and Group 2(Stage III and IV).We extracted 1037 radiomics features from each lesion and used the t-test and least absolute shrinkage and selection operator(LASSO)algorithm for feature selection.The CT signs of the lesions were screened using t-tests and chi-squared tests.The model was trained,and a prediction model was established using five machine learning classifiers:Logistic regression,random forest,Gaussian NB,support vector machine,and AdaBoost.The performance of the five prediction models was evaluated using receiver operator characteristic(ROC)curves,and the optimal model was selected.Finally,external validation was conducted using data acquired from 91 patients at our hospital.Results:After feature screening,13 radiomics features with high diagnostic value were obtained for the subsequent establishment of an NSCLC patient staging prediction model.Among the five machine-learning classification models,the Random Forest classification prediction model was the best.The validation set AUC value using this model was the highest at 0.740.After external verification,the model exhibited an AUC value of 1.000,sensitivity of 1.000,and specificity of 1.000 in the training set.The AUC value of the test set was 0.698,with a sensitivity of 0.873 and a specificity of 0.500.In the CT morphological features of the case,except for the size of the lesion,there were no statistically significant differences in other features among the patients at different stages.Conclusion:The CT radiomics machine learning classification model can predict the staging of patients with NSCLC.

Abstract:Objective:This study aimed to compare and analyze the effects of different keV values of dual-source computed tomography(CT)noise-optimized virtual monoenergetic imaging(VMI+)on the quality of portal vein imaging in patients with portal hypertension and to determine the optimal keV value for VMI+.Methods:Postprocessing was performed on portal venous phase images of 37 patients with portal hypertension who underwent dual-source CT.The VMI+technique was used to reconstruct nine groups of monoenergetic images at 40,45,50,55,60,65,70,75,and 80keV.Compared with the standard mixed images automatically generated with a linear blending coefficient of 0.6(M-0.6),the CT values and standard deviation of the main portal vein(MPV)and liver parenchyma were measured for each group of images.The signal-to-noise ratio(SNR)of the MPV and the contrast-to-noise ratio(CNR)with the liver parenchyma were calculated.On the maximum intensity projection images of the portal venous phase,the luminal diameters of the MPV,splenic vein(SPV),left branch of the portal vein(IHLPV),and right branch of the portal vein(IHRPV)were measured,and the number of detected cases of diseased vessels in each image group was recorded.Objective evaluation was conducted using analysis of variance.Subjective evaluation was performed by two deputy chief radiologists who used a five-point scale to assess the contrast effect of the MPV against the background liver parenchyma and the overall image quality in the 10 groups of images.Results:The CT value,SNR,CNR of the MPV,and subjective image scores measured for the 40-65keV portal vein groups were higher than those for the M-0.6 group,and the difference was statistically significant.The CT value,SNR,CNR of the MPV,and subjective image scores measured for 70keV images were similar to those of the M-0.6 group,with no statistical difference.The CT value,SNR,CNR of the MPV,and subjective image scores measured for the 75 and 80keV groups were lower than those for the M-0.6 group,and the difference was statistically significant.The diameters of the MPV,IHLPV,IHRPV,and SPV were the same among all the groups,and the same number of pathological vessels were detected,with no statistical significance.Among them,the 40keV group had the highest CT values,SNR,and CNR of the MPV among all 10 groups.Conclusion:The application of VMI+technology(40-65keV)in dual-source CT significantly improves the portal-vein image quality of patients with portal hypertension,which is beneficial for displaying portal vein vessels.The optimal monoenergetic energy level is 40keV.

Abstract:Esophageal malignant glomus tumors are rare,and their clinical features and imaging manifestations lack specificity.Preoperative differential diagnosis is difficult,which affects clinical treatment decisions.This article reports a case of a patient with multiple intrahepatic metastases of esophageal malignant glomus tumor admitted to our hospital six years after surgery.The clinical data and imaging findings of this case were retrospectively analyzed to improve the understanding of CT manifestations of esophageal glomus tumors by radiologists and provide assistance for clinical diagnosis and treatment.

Abstract:Objective:This study aims to analyze the impact of the reconstruction algorithm and filter on the measurement of coronary artery calcification scores using artificial intelligence(AI)and to evaluate the accuracy and consistency of risk stratification by AI-measured calcification scores.Methods:A retrospective analysis was conducted on coronary artery calcification score CT images from January 2024 at our hospital.A total of 30 cases were included,with 18 males and 12 females.Twelve groups of images were reconstructed using different reconstruction algorithms(FBP,iterative iDose4 level 1-5)and filtering kernels(Cardiac Standard and Cardiac Sharp).Two methods including an AI image workstation and a CT workstation were used to measure the coronary artery Agatston score(AS),volume score(VS),and mass score(MS)for each group of images,and to calculate risk stratification.The AS,VS,and MS obtained from different reconstruction algorithms were subjected to multiple-sample Friedman tests using measurements from both AI and CT workstations.For images using two different filtering kernels,paired Wilcoxon tests were conducted on the AS,VS,and MS measured by AI and CT workstations.Paired Wilcoxon tests and intraclass correlation coefficients(ICC)were performed on the AS,VS,and MS measured by both methods across the 12 groups of images.The consistency of risk stratification was analyzed using the weighted Kappa coefficient.The results measured by the CT workstation were used as a reference.Results:With the Cardiac Standard filtering kernel,there were statistically significant differences in the Agatston score(AS)and volume score(VS)measured by AI across different reconstruction algorithms,but no significant difference in the mass score(MS).With the Cardiac Sharp filtering kernel,there were no statistically significant differences in AS,VS,and MS measured by AI.Statistically significant differences were observed in AS and VS measured by the CT workstation across different reconstruction algorithms.Statistical differences were present in AS,VS,and MS measured by AI using both filtering kernels and in AS and VS measured by the CT workstation using both filtering kernels.Under the Cardiac Standard filtering kernel,there were no significant differences in AS,VS,and MS between the two measurement methods,while under the Cardiac Sharp filtering kernel,there were significant differences in AS and VS between the two methods,with good consistency(ICC>0.75).The highest consistency in risk stratification was observed in image groups using the Cardiac Standard filtering kernel and iDose levels 1 and 2,with a Kappa coefficient of 0.967.Conclusion:The choice of reconstruction algorithms and filtering kernels greatly affects the accuracy of coronary artery calcification scores.Both AI and CT workstations rely on these choices,making careful selection critical in clinical practice.