Objective To construct a model for predicting ki-67 expression in hepatocellular carcinoma using the intratumoral and peritumoral radiomic features of contrast enhanced magnetic resonance imaging(CEMRI)in the arterial phase as well as clinical imaging features.Methods A total of 120 patients pathologically diagnosed with hepatocellular carcinoma(HCC)from January 2016 to December 2024 in No.910 Hospital of the Joint Logis-tics Support Force of the Chinese People's Liberation Army were retrospectively enrolled and randomly divided into a training set(84 cases)and a test set(36 cases)in a ratio of 7∶3.ITK-SNAP software was used to delineate the global region of interest(ROI)of HCC on the arterial phase MR images.The ROIs of all patients were automatically expanded outward by 2 mm,and then the intratumoral ROI areas were eliminated to obtain the peritumoral ROI.With the help of PyRadiomics software,1 198 intratumoral and peritumoral radiomic features were extracted.Spearman correlation analysis,maximum relevance-minimum redundancy(mRMR),and least absolute shrinkage and selection operator(LASSO)regression were used to reduce the data dimension and select the best features.Then,a radiomics model of the logistic regression(LR)machine learning algorithm was constructed.A combined model including clinical imaging features and radiomics features was established.The area under the curve(AUC),accuracy,sensitivity,specificity,positive predictive value(PPV),negative predictive value(NPV),calibration curve and decision curve analysis(DCA)were used to evaluate the efficacy of the intratumoral and peritumoral radiomics features combined with clinical imaging features model in predicting ki-67 expression in hepatocellular car-cinoma.Results The intratumor model exhibited an efficacy in predicting the expression of ki-67 in hepatocellular carcinoma with AUC values of 0.817 and 0.787 in the training set and test set,respectively.The peritumoral model showed an efficacy with AUC values of 0.805 and 0.633 in the training set and test set,respectively.The intratumoral and peritumoral model demonstrated AUC values of 0.874 and 0.836 in the training set and test set,respectively.The combined model constructed by integrating the intratumoral and peritumoral model with clinical imaging features yielded AUC values of 0.877 and 0.849 in the training set and test set,respectively,indicating clinical imaging features improved the performance of the model.DCA showed that the combined models all had good clinical benefits,with the intratumoral and peritumoral model performing the best.Conclusion The intratumoral and peritumoral radiomics model based on CEMRI arterial phase combined with clinical imaging data can accurately predict the expression of ki-67 in hepatocellular carcinoma.This combined model yields the best clinical benefit.

Objective To explore its application value of LNM in patients with gastric adenocarcinoma based on the construction of a radiomic nomogram prediction model for preoperative lymph node metastasis in gastric adenocarcinoma using enhanced CT imaging features and parameters.Methods 131 patients with gastric adenocarcinoma who underwent radical gastric cancer surgery(Billroth Ⅱ)+lymph node dissection in our hospital from August 2019 to October 2023 were retrospectively analysed,and the preoperative enhancement CT extracted lesions,histological features of lymph node images,and pathological examination of LNM were recorded respectively,and the statistically significant Enhanced CT image histological features and parameters,multifactorial logistic regression to analyse the independent risk factors of gastric adenocarcinoma LNM(+)and construct a column-line diagram,and evaluate its performance.The performance and clinical value of the prediction model were evaluated using subject work characteristic(ROC)curves,and the column-line diagram was internally validated.Results The results of univariate analysis showed that the maximum diameter of the tumour,the lymph node status,the short-axis length and volume of the largest lymph node in the lymph node group and the sum of the short-axis lengths of all the lymph nodes were associated with the occurrence of LNM,and the difference was statistically significant(P＜0.05);multifactorial logistic regression analysis suggested that the maximum diameter of the tumour was ≥15 mm and the lymph node status was positive in the enhanced CT imaging examination,maximum lymph node short-axis length ≥ 7 mm in the lymph node group,the sum of short-axis lengths of all lymph nodes ≥ 11 mm,and the maximum lymph node short-axis volume ≥ 300 mm3 in the lymph node group were the independent risk factors for gastric adenocarcinoma patients with LNM(+)(P＜0.05);the area under the curve of the model was plotted using a ROC curve with an AUC=0.816(95％ CI 0.810-0.939),with the sensitivity of 0.91 and the specificity of 0.86.Model validation was performed using the BOOTSTRAP method containing 500 resamples,and the results suggested that the differences between the fitted curves and the ideal curves of the constructed column-line graphical model were not significant,and the validity and reliability were good.Conclusion The radiomic nomogram prediction model based on enhanced CT imaging features and parameters can effectively predict preoperative lymph node metastasis in gastric adenocarcinoma,providing strong support for clinical decision-making in gastric adenocarcinoma patients.

Objective:To investigate the effect and safety of etonogestrel implant and levonorgestrel-releasing intrauterine system (LNG-IUS) in the treatment of adenomyosis.Methods:Eighty patients with adenomyosis in Northwest Women's and Children's Hospital were selected from September 2021 to September 2023. According to the random number table method, they were divided into observation group and control group, with 45 cases in each group. The patients in observation group were treated with etonogestrel implant, while the patients in control group were given LNG-IUS. The uterine conditions, visual analogue scale (VAS) score, menstrual pattern, sex hormones [estradiol, luteinizing hormone (LH) and follicle stimulating hormone (FSH)] and laboratory indicators [hemoglobin, serum ferritin (SF) and carbohydrate antigen 125] before treatment and after 12 months of treatment and incidence of adverse reactions were compared between the two groups of patients. Measurement data were expressed as xˉ±s. Repeated measures analysis of variance was used for comparison between the two groups at multiple time points. LSD-t test was used for pairwise comparison. Two independent sample t test was used for comparison between the two groups. Paired t test was used for comparison before and after treatment. Enumeration data were expressed as n (%), and χ2 test was used for comparison between groups. Results:After 12 months of treatment, the uterine volume and endometrial thickness in observation group and control group were reduced compared to before treatment [observation group: (122.72±13.52) cm 3 vs. (202.72±20.75) cm 3, (6.83±1.35) mm vs. (9.84±1.76) mm, t=21.67,9.10, respectively, both P<0.001; control group: (134.82±17.64) cm 3 vs. (203.46±20.03) cm 3, (7.52±1.52) mm vs. (9.79±1.82) mm, t=17.25,6.42, respectively, both P<0.001], and the indicators in observation group were lower than those in control group ( t=3.65, 2.28, P<0.001, P=0.025, respectively). The levels of estradiol, LH and FSH were lower than those before treatment[observation group: (1.40±0.30) nmol/L vs. (2.42±0.41) nmol/L, (10.12±1.14) U/L vs. (12.84±2.63) U/L, (5.32±0.87) U/L vs. (9.34±1.35) U/L, t=13.47,6.36,10.03, respectively, all P<0.001; control group: (1.68±0.33) nmol/L vs. (2.40±0.48) nmol/L, (11.41±1.53) U/L vs. (12.96±2.25) U/L, (7.03±1.04) U/L vs. (9.53±1.31) U/L, t=8.29,3.82,16.79, respectively, all P<0.001], and the observation group had lower levels than the control group( t=4.21,4.54,8.46, respectively, all P<0.001). Hemoglobin and SF levels were higher than those before treatment, and the levels in observation group were higher than those in control group [observation group: (116.46±3.07) mg/L vs. (109.46±3.64) mg/L, (117.33±16.46) μg/L vs. (53.82±7.52) μg/L, t=9.86,18.95, respectively, both P<0.001; control group: (114.63±3.48) mg/L vs. (110.63±3.48) mg/L, (95.34±12.63) μg/L vs. (52.58±8.21) μg/L, t=5.45,23.61, respectively, both P<0.001], and the levels in observation group were higher than those in control group( t=2.64,7.11, P=0.010, P<0.001, respectively). The level of carbohydrate antigen 125 was lower than that before treatment, [observation group:(40.31±3.10) kU/L vs.(68.31±4.75) kU/L, t=33.12, P<0.001;control group:(57.45±4.27) kU/L vs.(67.64±4.83) kU/L, t=10.60, P<0.001], and the level in observation group was lower than that in control group ( t=21.79, P<0.001). At 3, 6 and 12 months after treatment, the VAS score in both group decreased gradually, and the scores in observation group were lower than those in control group [(4.35±0.88) points vs. (4.71±0.75) points, (3.21±0.73) points vs. (3.63±0.82) points, (2.64±0.51) points vs. (3.16±0.64) points, all P<0.05]. Before treatment, there was no statistically significant difference in menstrual patterns between the two groups of patients ( P>0.05). After 12 months of treatment, the proportion of normal menstrual patterns in the implant group was higher than that in the sustained-release group [68.9% (31/45) vs. 46.7% (21/45), χ2=4.56, P=0.033], while the proportion of frequent bleeding was lower than that in the sustained-release group [6.7% (3/45) vs. 22.2% (10/45), χ2=4.41, P=0.036]. There was no statistical significant difference in the incidence of adverse reactions between the two groups during treatment [8.9% (4/45) vs. 11.1% (5/45), χ2=0.00, P=1.000]. Conclusion:Compared with LNG-IUS, etonogestrel can more effectively improve the uterine conditions, relieve the dysmenorrhea symptoms, and improve the blood related indicators, and with high safety.

Allergen-specific immunotherapy（AIT） remains the only therapeutic approach with the potential to modify the natural course of allergic rhinitis（AR）. Nevertheless, considerable inter-individual variability exists in patients'responses to AIT. To facilitate more reliable assessment of treatment efficacy, the China Rhinopathy Research Cooperation Group（CRRCG） convened young and middle-aged nasal experts in China to formulate the present consensus. The recommended subjective outcome measures for AIT comprise symptom scores, medication scores, combined symptom and medication scores, quality-of-life assessments, evaluation of disease control, and assessment of comorbidities. Objective indicators may supplement these measures. Currently available objective approaches include skin prick testing, nasal provocation testing, and allergen exposure chambers. However, these methods remain constrained by practical limitations and are not yet appropriate for routine implementation in clinical efficacy evaluation. In addition, several biomarkers, including sIgE and the sIgE/tIgE ratio, sIgG4, serum IgE-blocking activity, IgA, cytokines and chemokines, as well as immune cell surface molecules and their functional activity, have been shown to have associations with AIT outcomes. While these biomarkers may complement subjective assessments, they are subject to significant limitations. Consequently, large-scale multicenter trials and real-world evidence are required to strengthen the evidence base. The present consensus underscores the necessity of integrating patients'subjective experiences with objective testing throughout the treatment process, thereby providing a more comprehensive and accurate framework for efficacy evaluation. Looking forward, future investigations should prioritize the incorporation of multi-omics data and artificial intelligence methodologies, which hold promise for overcoming current limitations in assessment strategies and for advancing both the standardization and personalization of AIT.
Humans ; Allergens/immunology* ; China ; Consensus ; Desensitization, Immunologic ; Immunoglobulin E ; Quality of Life ; Rhinitis, Allergic/therapy* ; Treatment Outcome ; East Asian People

Objective To explore the relationship between serum S100 calcium-binding protein(S100)A4,S100A12 and the infection type and prognosis of neonatal infectious pneumonia(NIP).Methods A total of 300 children with NIP admitted to the Neijiang Second People's Hospital from January 2021 to March 2024 were selected and divided into the bacterial infection group(214 cases)and the non-bacterial infection group(86 cases)according to the types of pathogenic bacteria.Another 150 healthy newborns in the same hospital during the same period were selected as the control group.The levels of serum S100A4 and S100A12 were de-tected by enzyme-linked immunosorbent assay.Pearson correlation analysis was conducted to examine the cor-relations between serum S100A4,S100A12 and procalcitonin(PCT),white blood cell count(WBC),albumin(Alb),and platelet count(PLT).The receiver operating characteristic(ROC)curve was used to evaluate the differential value of serum S100A4,S100A12,PCT,WBC,Alb,and PLT alone and in combination for NIP bac-terial infection.According to the prognosis,children with NIP were divided into the poor prognosis group(63 cases)and the good prognosis group(237 cases).Multivariate Logistic regression model was used to analyze the influencing factors of poor prognosis in children with NIP,and ROC curve was used to analyze the value of each factor in predicting poor prognosis in children with NIP.Results The levels of serum S100A4,S100A12,PCT,WBC,and PLT in the bacterial infection group were higher than those in the non-bacterial infection group and the control group,while Alb was lower than that in the non-bacterial infection group and the control group,the differences were statistically significant(P<0.05).Pearson correlation analysis showed that serum S100A4 and S100A12 in children with NIP were positively correlated with PCT,WBC and PLT(P<0.05),and negatively correlated with Alb(P<0.05).The results of ROC curve analysis showed that the area under the curve(AUC)of serum S100A4 and S100A12 in differentiating NIP infection types was slightly lower than that of PCT,WBC,Alb,and PLT in differentiating NIP infection types.The results of multivariate Logistic re-gression analysis showed that elevated S100A4,elevated S100A12,elevated PCT,bacterial infection,and lung consolidation were independent risk factors for poor prognosis in children with NIP(P<0.05).The AUC of bacterial infection,lung consolidation,PCT,S100A4,and S100A12 for predicting the poor prognosis of chil-dren with NIP was 0.903.It was greater than the AUC predicted separately by bacterial infection,lung consol-idation,PCT,S100A4,and S100A12 levels(Z=9.989,9.460,5.514,4.084,4.376,P<0.001).Conclusion The combination of serum S100A4 and S100A12 with traditional markers has certain discrimina-tory value for the infection types of NIP,and the levels of serum S100A4 and S100A12 are related to the prog-nosis of NIP.

OBJECTIVE: To explore the implementation effect of hour-1 bundle for sepsis patients based on crisis resource management (CRM) system. METHODS: A historical control study was conducted. The hour-1 bundle for sepsis based on CRM was used to train 24 nurses in the emergency department from October 2022 to March 2023. Clinical data of sepsis patients admitted to the emergency department of the First People's Hospital of Zunyi from April 2022 to September 2023 were collected. The patients were divided into three groups based on different stages of CRM system construction: control group (before construction, from April to September in 2022), improvement group (during construction, from October 2022 to March 2023) and observation group (after construction, from April to September in 2023). The baseline data, implementation rate of hour-1 bundle [including blood culture, antibiotic usage, blood lactic acid (Lac) detection, fluid resuscitation, hypertensors usage], identification and diagnosis time, and prognosis parameters [including correction rate of hypoxemia, intensive care unit (ICU) occupancy rate, and 28-day survival rate]. Sepsis cognition survey and non-technical skill (NTS) evaluation of nurses in emergency department were conducted before and after training. RESULTS: Finally 43 cases were enrolled in the control group, improvement group and observation group, respectively. There was no statistically significant difference in baseline data including the gender, age, primary site, heart rate, systolic blood pressure, acute physiology and chronic health evaluation II (APACHE II) score, sequential organ failure assessment (SOFA) score, mechanical ventilation ratio among the three groups with comparability. With the gradual improvement of the CRM system, the implementation rate of 1-hour bundle was gradually increased, and the implementation rate in the control group, improvement group and observation group were 65.12% (28/43), 74.42% (32/43) and 88.37% (38/43), respectively, with statistically significant difference (P < 0.05). It was mainly reflected in the completion rate of blood culture, antibiotic usage rate, Lac detection rate and hypertensors usage rate within 1 hour, which were significantly higher in the observation group than those in the control group [completion rate of blood culture: 90.70% (39/43) vs. 62.79% (27/43), antibiotic usage rate: 88.37% (38/43) vs. 60.47% (26/43), Lac detection rate: 93.02% (40/43) vs. 72.09% (31/43), hypertensors usage rate: 88.37% (38/43) vs. 60.47% (26/43), all P < 0.05]. The fluid resuscitation rates within 1 hour in the three groups were all over 90%, with no statistically significant difference among the three groups. The recognition and diagnosis time in the observation group was significantly shorter than that in the control group and the improvement group (hours: 0.41±0.15 vs. 0.61±0.21, 0.51±0.18, both P < 0.05), the correction rate of hypoxemia and 28-day survival rate were significantly higher than those in the control group [correction rate of hypoxemia: 95.35% (41/43) vs. 74.42% (32/43), 28-day survival rate: 83.72% (36/43) vs. 60.47% (26/43), both P < 0.05], and ICU occupancy rate was significantly lower than that in the control group [72.09% (31/43) vs. 93.02% (40/43), P < 0.05]. After training in the CRM system, the score of the sepsis awareness survey questionnaire for emergency department nurses was significantly increased as compared with before training (60.42±5.29 vs. 44.17±9.21, P < 0.01), and NTS also showed significant improvement. CONCLUSION CRM plays a significant role in promoting the implementation of sepsis hour-1 bundle, which can improve the implementation rate of hour-1 bundle and NTS of medical staff, effectively improve patients' hypoxemia, reduce patients' ICU occupancy rate and 28-day risk of death.
Humans ; Sepsis/therapy* ; Emergency Service, Hospital ; Patient Care Bundles ; Intensive Care Units ; Female ; Male ; Middle Aged

Although low temperature plasma ablation technology has significant advantages in clinical applications,its poor stability,high power consumption and thermal injuries to the tissues are still key factors limiting its widespread use.To address these issues,a device that uses bipolar pulses to excite plasma is developed,and it can flexibly adjust its output voltage,frequency and duty cycle,effectively reducing breakdown voltage and power consumption.By conducting simulation and saltwater discharge experiments,the excitation process of plasma is elaborated in detail.Meanwhile,the effects of two different pulse excitation modes on plasma excitation are discussed and compared.The results show that the bipolar pulse excitation mode is advantageous in reducing discharge current and breakdown voltage,and shortening the formation time of the vapor layer,which effectively relieves thermal injuries to the tissues.Finally,the broad application potential of the plasma ablation device is demonstrated in plasma ablation experiments which are conducted at different voltages,with pork as the experimental material.The study provides a new theoretical basis and practical guidance for the application of plasma ablation technology in minimally invasive surgery.

Background and purpose:Human papilloma virus(HPV)infection status is crucial for diagnosing cervical precancerous lesions and classifying cervical cancer.High-risk(HR)HPV is often linked to P16 protein overexpression,so P16 detection via immunohistochemistry(IHC)is commonly used to assess HPV infection.However,the differences between HPV status and P16 expression remains unclear.An in-depth study of the correlation between HPV and P16 is essential for clinical guidance.Methods:We retrospectively collected clinical and pathological data of cervical lesions from 618 patients diagnosed at the Department of Pathology,Fudan University Shanghai Cancer Center from January 2020 to December 2023(Ethical number:050432-4-2307E).Polymerase chain reaction(PCR)reverse dot hybridization was used to detect HPV including HR and low-risk(LR)subtypes,and immunohistochemistry was used to detect P16 for comparative analysis.Based on different clinical and pathological diagnoses,the sensitivity and specificity of P16 expression in evaluating HPV infection were evaluated.Among the 618 cases of cervical lesions,there were 92 cases of cervical squamous cell carcinoma,257 cases of cervical adenocarcinoma,79 cases of high-grade squamous intraepithelial lesions(HSIL),105 cases of low-grade squamous intraepithelial lesions(LSIL),and 85 cases of chronic cervical inflammation.Results:According to clinical diagnosis,the HR-HPV positive rate in cervical squamous cell carcinoma was 88.0%(81/92),the P16 positive rate was 91.3%(84/92),and the overall consistency rate between P16 and HPV detection was 90.2%(88/92);for HR-HPV infection,the sensitivity and specificity of P16 were 96.3%and 45.5%.The positive rate of HR-HPV in adenocarcinoma was 54.5%(140/257),the positive rate of P16 was 58.8%(151/257),and the overall consistency rate between P16 and HPV detection was 82.5%(212/257);for HR-HPV infection,the sensitivity and specificity of P16 were 87.9%and 76.1%.In HSIL,the HR-HPV positive rate was 75.9%(60/79),the positive rate of P16 was 70.9%(56/79),and the overall consistency rate between P16 and HR-HPV detection was 82.2%(65/79);for HR-HPV infection,the sensitivity and specificity of P16 were 85.0%and 73.7%.In LSIL,the HR-HPV positive rate was 73.3%(77/105),the positive rate of P16 was 8.5%(9/105),and the overall consistency rate between P16 and HR-HPV detection was 33.3%(35/105);for HR-HPV infection,the sensitivity and specificity of P16 were 10.4%and 96.4%.In chronic cervical inflammation,the HR-HPV positive rate was 20%(17/85),the positive rate of P16 was 0.0%(0/85);for HR-HPV infection,the sensitivity and specificity of P16 were 0.0%and 100.0%.There was a significant positive correlation between P16 positivity and HPV16/18 in cervical squamous cell carcinoma,adenocarcinoma,and HSIL(P=0.000),while there was no significant correlation in LSIL and chronic cervical inflammation(P＞0.05).Conclusion:In cervical squamous cell carcinoma and adenocarcinoma,the consistency of P16 expression and HPV DNA positivity are high,especially in HPV16/18 subtype.There is a good concordance between HR-HPV positivity and P16 protein overexpression.The positive expression of P16 in HSIL may initially reflect HPV infection status.However,in LSIL and chronic cervicitis,P16 expression may not accurately correlate with HPV infection.The inconsistency between P16 and HPV DNA testing could be influenced by multiple factors,including HPV subtypes,histopathological categories,specimen quality,and technical limitations.In clinical practice,it is recommended to conduct comprehensive analysis or employ multiple diagnostic methods to confirm HPV infection status for precise evaluation.

Objective:To investigate the impact of lupeol on periodontal tissue injury in periodontitis rats by regulating Ras homolog gene family member A(RhoA)/Rho associated coiled coil containing protein kinase(ROCK)signal pathway.Methods:SD rats were randomly divided into control group(NC group),Model group,Lupeol of low(Lupeol-L group,16.67 μg/kg),medium(Lupeol-M group,33.34 μg/kg)and high-dose(Lupeol-H group,66.68 μg/kg)groups,vitamin C(VC)group(100 mg/kg),Rhosin(RhoA inhibitor)group(40 mg/kg)and Lupeol-H+Rhosin group(66.68 μg/kg+40 mg/kg)groups(n=18).Except NC group,the rats in other groups were used to establish periodontitis models.After modeling,the drugs were administered to the mice of the groups respectively,once a day for 21 days.Serum levels of IL-1β and TNF-α were detected by ELISA.Alveolar bone resorption in rats was detected by methylene blue staining.HE staining was used to detect the pathological changes of periodontal tissues.The expres-sion of OPG protein in periodontal tissue was detected by immunohistochemistry.TRAP staining was used to detect the osteoclasts in rat periodontal tissue,and the expression of OPG,RANKL,RhoA,ROCK1 and ROCK2 proteins in periodontal tissue was detected by Western blot.Results:Compared with NC group,pathological injury of periodontal tissue was serious,TNF-α and IL-1β levels,the distance from alveolar crest to enamel cementum junction(CEJ),osteoclasts number and RANKL protein increased,the num-ber of osteoblasts,and the expression of OPG,RhoA,ROCK1 and ROCK2 proteins decreased in model group(P＜0.05).Compared with model group,pathological injury of periodontal tissue in all Lupeol groups and VC group was reduced,the levels of TNF-α and IL-1β,the distance from alveolar crest to CEJ,osteoclasts number and RANKL protein decreased,the number of osteoblasts,and the expression of OPG,RhoA,ROCK1 and ROCK2 proteins increased,the cor-responding indexes of Rhosin group showed the opposite trend(P＜0.05).Rhosin reversed improvement effect of high dose Lupeol on periodontal tissue injury in rats with periodontitis.Conclusion:Lupeol may reduce periodontal tissue injury in rats with peri-odontitis by activating RhoA/ROCK signaling pathway.

Objective To construct a model for predicting ki-67 expression in hepatocellular carcinoma using the intratumoral and peritumoral radiomic features of contrast enhanced magnetic resonance imaging(CEMRI)in the arterial phase as well as clinical imaging features.Methods A total of 120 patients pathologically diagnosed with hepatocellular carcinoma(HCC)from January 2016 to December 2024 in No.910 Hospital of the Joint Logis-tics Support Force of the Chinese People's Liberation Army were retrospectively enrolled and randomly divided into a training set(84 cases)and a test set(36 cases)in a ratio of 7∶3.ITK-SNAP software was used to delineate the global region of interest(ROI)of HCC on the arterial phase MR images.The ROIs of all patients were automatically expanded outward by 2 mm,and then the intratumoral ROI areas were eliminated to obtain the peritumoral ROI.With the help of PyRadiomics software,1 198 intratumoral and peritumoral radiomic features were extracted.Spearman correlation analysis,maximum relevance-minimum redundancy(mRMR),and least absolute shrinkage and selection operator(LASSO)regression were used to reduce the data dimension and select the best features.Then,a radiomics model of the logistic regression(LR)machine learning algorithm was constructed.A combined model including clinical imaging features and radiomics features was established.The area under the curve(AUC),accuracy,sensitivity,specificity,positive predictive value(PPV),negative predictive value(NPV),calibration curve and decision curve analysis(DCA)were used to evaluate the efficacy of the intratumoral and peritumoral radiomics features combined with clinical imaging features model in predicting ki-67 expression in hepatocellular car-cinoma.Results The intratumor model exhibited an efficacy in predicting the expression of ki-67 in hepatocellular carcinoma with AUC values of 0.817 and 0.787 in the training set and test set,respectively.The peritumoral model showed an efficacy with AUC values of 0.805 and 0.633 in the training set and test set,respectively.The intratumoral and peritumoral model demonstrated AUC values of 0.874 and 0.836 in the training set and test set,respectively.The combined model constructed by integrating the intratumoral and peritumoral model with clinical imaging features yielded AUC values of 0.877 and 0.849 in the training set and test set,respectively,indicating clinical imaging features improved the performance of the model.DCA showed that the combined models all had good clinical benefits,with the intratumoral and peritumoral model performing the best.Conclusion The intratumoral and peritumoral radiomics model based on CEMRI arterial phase combined with clinical imaging data can accurately predict the expression of ki-67 in hepatocellular carcinoma.This combined model yields the best clinical benefit.