Objective:To investigate the surgical treatment effect and prognostic factors of hilar cholangiocarcinoma.Methods:This is an ambispective cohort study. From August 2005 to December 2022,data of 510 patients who diagnosed with hilar cholangiocarcinoma and underwent surgical resection at the Hepatobiliary Center of the First Affiliated Hospital of Nanjing Medical University were retrospectively collected. In the cohort,there were 324 males and 186 females,with an age of ( M (IQR)) 63(13)years (range:25 to 85 years). The liver function at admission was Child-Pugh A (343 cases,67.3%) and Child-Pugh B (167 cases,32.7%). Three hundred and seventy-two(72.9%) patients had jaundice symptoms and the median total bilirubin was 126.3(197.6) μmol/L(range: 5.4 to 722.8 μmol/L) at admission. Two hundred and fourty-seven cases (48.4%) were treated with percutaneous transhepatic cholangial drainage or endoscopic nasobiliary drainage before operation. The median bilirubin level in the drainage group decreased from 186.4 μmol/L to 85.5 μmol/L before operation. Multivariate Logistic regression was used to identify the influencing factors for R0 resection,and Cox regression was used to construct multivariate prediction models for overall survival(OS) and disease-free survival(DFS). Results:Among 510 patients who underwent surgical resection,Bismuth-Corlett type Ⅲ-Ⅳ patients accounted for 71.8%,among which 86.1% (315/366) underwent hemi-hepatectomy,while 81.9% (118/144) underwent extrahepatic biliary duct resection alone in Bismuch-Corlett type Ⅰ-Ⅱ patients. The median OS time was 22.8 months, and the OS rates at 1-,3-,5-and 10-year were 72.2%,35.6%,24.8% and 11.0%,respectively. The median DFS time was 15.2 months,and the DFS rates was 66.0%,32.4%,20.9% and 11.0%,respectively. The R0 resection rate was 64.5% (329/510), and the OS rates of patients with R0 resection at 1-,3-,5-and 10-year were 82.5%, 48.6%, 34.4%, 15.2%,respectively. The morbidity of Clavien-Dindo grade Ⅲ-Ⅴ complications was 26.1%(133/510) and the 30-day mortality was 4.3% (22/510). Multivariate Logistic regression indicated that Bismuth-Corlett type Ⅰ-Ⅲ ( P=0.009), hemi-hepatectomy and extended resection ( P=0.001),T1 and T2 patients without vascular invasion (T2 vs. T1: OR=1.43 (0.61-3.35), P=0.413;T3 vs. T1: OR=2.57 (1.03-6.41), P=0.010;T4 vs. T1, OR=3.77 (1.37-10.38), P<0.01) were more likely to obtain R0 resection. Preoperative bilirubin,Child-Pugh grade,tumor size,surgical margin,T stage,N stage,nerve infiltration and Edmondson grade were independent prognostic factors for OS and DFS of hilar cholangiocarcinoma patients without distant metastasis. Conclusions:Radical surgical resection is necessary to prolong the long-term survival of hilar cholangiocarcinoma patients. Hemi-hepatectomy and extended resection,regional lymph node dissection and combined vascular resection if necessary,can improve R0 resection rate.

Objective:To investigate the surgical treatment effect and prognostic factors of hilar cholangiocarcinoma.Methods:This is an ambispective cohort study. From August 2005 to December 2022,data of 510 patients who diagnosed with hilar cholangiocarcinoma and underwent surgical resection at the Hepatobiliary Center of the First Affiliated Hospital of Nanjing Medical University were retrospectively collected. In the cohort,there were 324 males and 186 females,with an age of ( M (IQR)) 63(13)years (range:25 to 85 years). The liver function at admission was Child-Pugh A (343 cases,67.3%) and Child-Pugh B (167 cases,32.7%). Three hundred and seventy-two(72.9%) patients had jaundice symptoms and the median total bilirubin was 126.3(197.6) μmol/L(range: 5.4 to 722.8 μmol/L) at admission. Two hundred and fourty-seven cases (48.4%) were treated with percutaneous transhepatic cholangial drainage or endoscopic nasobiliary drainage before operation. The median bilirubin level in the drainage group decreased from 186.4 μmol/L to 85.5 μmol/L before operation. Multivariate Logistic regression was used to identify the influencing factors for R0 resection,and Cox regression was used to construct multivariate prediction models for overall survival(OS) and disease-free survival(DFS). Results:Among 510 patients who underwent surgical resection,Bismuth-Corlett type Ⅲ-Ⅳ patients accounted for 71.8%,among which 86.1% (315/366) underwent hemi-hepatectomy,while 81.9% (118/144) underwent extrahepatic biliary duct resection alone in Bismuch-Corlett type Ⅰ-Ⅱ patients. The median OS time was 22.8 months, and the OS rates at 1-,3-,5-and 10-year were 72.2%,35.6%,24.8% and 11.0%,respectively. The median DFS time was 15.2 months,and the DFS rates was 66.0%,32.4%,20.9% and 11.0%,respectively. The R0 resection rate was 64.5% (329/510), and the OS rates of patients with R0 resection at 1-,3-,5-and 10-year were 82.5%, 48.6%, 34.4%, 15.2%,respectively. The morbidity of Clavien-Dindo grade Ⅲ-Ⅴ complications was 26.1%(133/510) and the 30-day mortality was 4.3% (22/510). Multivariate Logistic regression indicated that Bismuth-Corlett type Ⅰ-Ⅲ ( P=0.009), hemi-hepatectomy and extended resection ( P=0.001),T1 and T2 patients without vascular invasion (T2 vs. T1: OR=1.43 (0.61-3.35), P=0.413;T3 vs. T1: OR=2.57 (1.03-6.41), P=0.010;T4 vs. T1, OR=3.77 (1.37-10.38), P<0.01) were more likely to obtain R0 resection. Preoperative bilirubin,Child-Pugh grade,tumor size,surgical margin,T stage,N stage,nerve infiltration and Edmondson grade were independent prognostic factors for OS and DFS of hilar cholangiocarcinoma patients without distant metastasis. Conclusions:Radical surgical resection is necessary to prolong the long-term survival of hilar cholangiocarcinoma patients. Hemi-hepatectomy and extended resection,regional lymph node dissection and combined vascular resection if necessary,can improve R0 resection rate.

In the past 20 years,the development of artificial intelligence has made rapid progress,and it is increasingly applied in the medical field,including medical image-assisted diagnosis and treatment,health management,disease risk prediction and so on.In this paper,the application status of artificial intelligence-assisted detection and diagnosis system based on deep learning in anorectal diseases is summarized,and the new methods related to the diagnosis and treatment of anorectal diseases at home and abroad are summarized.It mainly reviews the research progress of artificial intelligence technology in the diagnosis and treatment of anal fistula,perianal abscess,hemorrhoids and other anorectal diseases.

Objective:To investigate the effect of DNA methylation of laminin α3 (LAMA3) on the prognosis of platinum-resistant epithelial ovarian cancer (EOC) and its possible mechanism.Methods:(1) The relationship between DNA methylation of LAMA3 and platinum resistance in EOC was evaluated by bioinformatics. (2) A total of 67 EOC patients treated at Guangxi Medical University Cancer Hospital from January 2000 to December 2012 were selected to detect the levels of LAMA3 DNA methylation in EOC tissues using pyrophosphate sequencing technology to explore its diagnostic efficacy for platinum resistance and prognosis in EOC patients. Furthermore, its impact on chemotherapy efficacy and prognosis of platinum resistant EOC patients were also analyzed.Results:(1) Ten proteins highly interacting with LAMA3 were screened from the Gene Interaction Retrieval Platform (STRING) database, including laminin β (LAMB) 3, laminin γ (LAMC) 3, integrin α (ITGA) 6, intestine protein β4 (ITGB4), ITGA3, LAMC1,LAMB2, dystrophin associated glycoprotein 1 (DAG1), LAMB1 and cytochrome P450c17α (COL17A1) protein; kyoto encyclopedia of genes and genomes (KEGG) enrichment analysis showed that LAMA3 and its related interacting proteins participate in the regulation of malignant tumor occurrence and development through signaling pathways such as apoptosis, cell cycle, DNA damage response, epithelial mesenchymal transition (EMT), androgen receptor (AR), estrogen receptor (ER), phosphatidylinositol 3 kinase (PI3K)/protein kinase B (Akt), RAS/mitogen activated protein kinase (MAPK), receptor tyrosine kinase (RTK), tuberous sclerosis protein complex (TSC)/mammalian target of rapamycin (mTOR), and their expression levels were related to the sensitivity of chemotherapy drugs such as cisplatin in EOC. (2) Our clinical data analysis found that the LAMA3 DNA methylation level in EOC tissue of the platinum-sensitive group (35 cases) was 71% (25/35), which was higher than 69% (22/32) in the platinum-resistant group (32 cases), with statistically insignificant difference ( χ2=0.057, P=0.811). The area under the curve (AUC) of LAMA3 DNA methylation level for assessing platinum resistance in EOC was 0.601, and the AUC for predicting EOC patient prognosis was 0.686. The chemotherapy efficacy of EOC patients with high methylation of LAMA3 DNA was worse than that of patients with low methylation, 50% (12/24) vs 15/15, with statistically significant difference ( χ2=10.833, P=0.001). The level of LAMA3 DNA methylation had a significant impact on the progression free survival and overall survival of EOC patients (both P<0.05). Conclusion:The level of LAMA3 DNA methylation has certain diagnostic and predictive value for platinum resistance and prognosis in EOC patients, which may be closely related to the regulatory mechanism, platinum resistance and prognosis of EOC.

The treatment of hepatobiliary malignant tumor is characterized by the coexistence of multiple treatment methods and multiple disciplines. In order to evaluate the clinical efficacy of different treatment measures or multiple treatment combinations, and to promote the standardized development of comprehensive treatment patterns for hepatobiliary malignant tumor, the Hepatobiliary Center of the First Affiliated Hospital of Nanjing Medical University constructs the registry and follow-up database in hepatobiliary tumor patients based on the information-based platform of the hospital, which will help guide clinicians to make scientific decisions and improve the level of clinical diagnosis and treatment. This study describes the framework design, function modules, data acquisition process and quality control of the database of hepatobiliary malignant tumor. Based on the observational bidirectional cohort study design, the previous clinical data can be sorted to match the current database, on the other hand, the clinical data can be prospectively collected including basic information, admission evaluation, surgical information and postoperative situation, comprehensive treatment measures, regular reexaminations and long-term follow-up, etc. The data quality control system can be improved by formulating standardized operation procedures, regularly personnel training and full-process data management plans. This database will provide high-quality real-world data for clinicians, researchers, and guideline experts, and then provide high-level medical evidence for the standardized development of comprehensive treatment patterns of hepatobiliary malignancies.

Objective:To investigate more safe, effective and standard perioperative managements of infant patients with Kasabach-Merritt phenomenon (KMP).Methods:We made a retrospective analysis on the clinical data of KMP infant patients, who received surgical intervention in our department between January 2017 and September 2019. Inclusion criteria : (1) diagnosed as KMP that characterized by a large hemangioma (located in trunk or limb), profound thrombocytopenia and consumptive coagulopathy; (2) received surgical treatment in our center during January 2017 and September 2019; (3) age ≤1 year. Before surgical treatment, all the patients were given glucocorticoid and continued to the operation day in the sensitive group. The insensitive group received single large dose of platelet (PLT) transfusion 1 day before surgery, for the purpose of correcting thrombocytopenia and coagulopathy. Endotracheal intubation and intravenous anesthesia, combined with deep vein catheterization, arterial puncture catheterization and continuous invasive blood pressure monitoring were used to maintain hemodynamic stability. Radical resection of the tumor, combined with flap plasty or in situ skin grafting was carried out when necessary; after the operation, the endotracheal tube was routinely taken to ICU, and the endotracheal tube was removed as appropriate after the recovery of respiratory and circulation. The patient was kept overnight in ICU, and patient was transferred out after evaluation of stability. The dynamic changes of platelet were monitored and nutritional support was strengthened. Patients with lesions in limbs (except those with in situ skin grafting) were given passive rehabilitation training on the third day after surgery. The patients were followed up for 6-36 months. Routine blood examination, coagulation function, color Doppler ultrasonography and MRI were performed when necessary. The range of motion and muscle strength of adjacent joints were examined during the follow-up visit. Results:A total of 55 infant patients with KMP were included in this study. Peripheral blood test at 1 h before surgery showed platelets > 100×10 9/L in 54 cases and > 80×10 9/L in 1 case, and hemoglobin was corrected to more than 10 g/L. The operation time was 48-135 min, with an average of 87 min. There was no intraoperative or postoperative death. It took 4 to 36 hours for platelet to return to normal level, with an average of 8.4 hours. All surgical specimens were found to be KMP. The hospital stay was 9-30 d, with an average period of 16.7 d. Delayed incision healing in 3 cases, scar contracture in 1 case, scar hyperplasia in 3 cases. There was no death during the follow-up period, and the platelet was stable in the normal range. Conclusions:Surgical treatment of vascular tumors complicated with KMP has definite curative effect, rapid effect, short course of treatment and low cost. A series of perioperative treatments, including active preoperative preparation, effective coagulation function correction measures, perfect anesthesia and monitoring methods, stable hemodynamic support, fine surgical operation and early postoperative rehabilitation exercise are the necessary guarantee for the success of surgical treatment.

Objective:To examine clinical efficacy and prognostic factors of hepatocellular carcinoma(HCC) patients with different China Liver Cancer Staging (CNLC) after hepatectomy.Methods:From January 2010 to December,2019,549 patients underwent surgical resection and pathologically proven HCC were retrospectively reviewed in the First Affiliated Hospital of Nanjing Medical University. There were 462 males(84.2%) and 87 females(15.8%);the median age was 57 years (range: 21-84 years). Preoperative parameters,intraoperative and postoperative conditions,and postoperative pathological examination were observed.Survival analysis was performed by Kaplan-Meier method and the Log-rank test. Factors associated with disease-free survival(DFS) and overall survival(OS) of HCC patients were identified using univariate and multivariate Cox proportional hazards regression models.Results:Among the 549 patients underedwent liver resection,200 patients(36.4%) belonged to CNLC Ⅰa,whiles 148 patients(27.0%) belonged to CNLC Ⅰb. Furthermore,there were 49 patients(8.9%) with CNLC Ⅱa,32 patients(5.8%) with CNLC Ⅱb, 101 patients(18.4%) with CNLC Ⅲa and 19 patients(3.5%) with CNLC Ⅲb.The 1-,3-,5-,10-year OS for the entire cohort was 83.8%,69.0%,54.2%,37.7%,respectively,while 1-,3-, 5-year DFS was 61.0%,44.2%,36.0%, respectively. The 1-,3-, 5-year OS and DFS for CNLC Ⅰa were 97.3%,90.6%,80.5% and 83.9%,65.0%,54.0%,respectively;The 1-, 3-, 5-years OS and DFS for CNLC Ⅰb were 87.9%,71.0%,47.7%,and 58.4%,42.3%,33.4%,respectively.The 5-year OS for CNLC Ⅱa (37.2%) and Ⅱb(44.3%) were similar to CNLC Ⅰb. The 1-, 3-, 5-year OS and DFS for CNLC Ⅲb were 35.3%,13.2%,0 and 23.5%,0 and 0,respectively. Univariate analysis showed that preoperative symptoms,AFP level,total protein level,AST level,total bilirubin level,intraoperative blood loss,intraoperative or postoperative blood transfusion,postoperative complications,tumor number and size,microvascular invasion,macrovascular invasion and tumor differentiation were prognostic factors for long-term survival(≥5 years)(all P<0.05). The multivariate analysis suggested that AST level,intraoperative blood loss,tumor number and size,macrovascular invasion and tumor differentiation were the independent prognostic factors of long-term OS (all P<0.05). Conclusions:HCC patients with different stages of CNLC have different recurrence patterns and prognosis.After strict preoperative evaluation,patients with CNLC Ⅱa-Ⅲb can also benefit from radical resection. AST level,intraoperative blood loss,tumor number,tumor size,macrovascular invasion and tumor differentiation were independent factors that affect long-term survival. This will provide an important basis for the choice of treatment and the evaluation of surgical prognosis for patients with HCC.

Objective:To investigate more safe, effective and standard perioperative managements of infant patients with Kasabach-Merritt phenomenon (KMP).Methods:We made a retrospective analysis on the clinical data of KMP infant patients, who received surgical intervention in our department between January 2017 and September 2019. Inclusion criteria : (1) diagnosed as KMP that characterized by a large hemangioma (located in trunk or limb), profound thrombocytopenia and consumptive coagulopathy; (2) received surgical treatment in our center during January 2017 and September 2019; (3) age ≤1 year. Before surgical treatment, all the patients were given glucocorticoid and continued to the operation day in the sensitive group. The insensitive group received single large dose of platelet (PLT) transfusion 1 day before surgery, for the purpose of correcting thrombocytopenia and coagulopathy. Endotracheal intubation and intravenous anesthesia, combined with deep vein catheterization, arterial puncture catheterization and continuous invasive blood pressure monitoring were used to maintain hemodynamic stability. Radical resection of the tumor, combined with flap plasty or in situ skin grafting was carried out when necessary; after the operation, the endotracheal tube was routinely taken to ICU, and the endotracheal tube was removed as appropriate after the recovery of respiratory and circulation. The patient was kept overnight in ICU, and patient was transferred out after evaluation of stability. The dynamic changes of platelet were monitored and nutritional support was strengthened. Patients with lesions in limbs (except those with in situ skin grafting) were given passive rehabilitation training on the third day after surgery. The patients were followed up for 6-36 months. Routine blood examination, coagulation function, color Doppler ultrasonography and MRI were performed when necessary. The range of motion and muscle strength of adjacent joints were examined during the follow-up visit. Results:A total of 55 infant patients with KMP were included in this study. Peripheral blood test at 1 h before surgery showed platelets > 100×10 9/L in 54 cases and > 80×10 9/L in 1 case, and hemoglobin was corrected to more than 10 g/L. The operation time was 48-135 min, with an average of 87 min. There was no intraoperative or postoperative death. It took 4 to 36 hours for platelet to return to normal level, with an average of 8.4 hours. All surgical specimens were found to be KMP. The hospital stay was 9-30 d, with an average period of 16.7 d. Delayed incision healing in 3 cases, scar contracture in 1 case, scar hyperplasia in 3 cases. There was no death during the follow-up period, and the platelet was stable in the normal range. Conclusions:Surgical treatment of vascular tumors complicated with KMP has definite curative effect, rapid effect, short course of treatment and low cost. A series of perioperative treatments, including active preoperative preparation, effective coagulation function correction measures, perfect anesthesia and monitoring methods, stable hemodynamic support, fine surgical operation and early postoperative rehabilitation exercise are the necessary guarantee for the success of surgical treatment.

Objective:To examine clinical efficacy and prognostic factors of hepatocellular carcinoma(HCC) patients with different China Liver Cancer Staging (CNLC) after hepatectomy.Methods:From January 2010 to December,2019,549 patients underwent surgical resection and pathologically proven HCC were retrospectively reviewed in the First Affiliated Hospital of Nanjing Medical University. There were 462 males(84.2%) and 87 females(15.8%);the median age was 57 years (range: 21-84 years). Preoperative parameters,intraoperative and postoperative conditions,and postoperative pathological examination were observed.Survival analysis was performed by Kaplan-Meier method and the Log-rank test. Factors associated with disease-free survival(DFS) and overall survival(OS) of HCC patients were identified using univariate and multivariate Cox proportional hazards regression models.Results:Among the 549 patients underedwent liver resection,200 patients(36.4%) belonged to CNLC Ⅰa,whiles 148 patients(27.0%) belonged to CNLC Ⅰb. Furthermore,there were 49 patients(8.9%) with CNLC Ⅱa,32 patients(5.8%) with CNLC Ⅱb, 101 patients(18.4%) with CNLC Ⅲa and 19 patients(3.5%) with CNLC Ⅲb.The 1-,3-,5-,10-year OS for the entire cohort was 83.8%,69.0%,54.2%,37.7%,respectively,while 1-,3-, 5-year DFS was 61.0%,44.2%,36.0%, respectively. The 1-,3-, 5-year OS and DFS for CNLC Ⅰa were 97.3%,90.6%,80.5% and 83.9%,65.0%,54.0%,respectively;The 1-, 3-, 5-years OS and DFS for CNLC Ⅰb were 87.9%,71.0%,47.7%,and 58.4%,42.3%,33.4%,respectively.The 5-year OS for CNLC Ⅱa (37.2%) and Ⅱb(44.3%) were similar to CNLC Ⅰb. The 1-, 3-, 5-year OS and DFS for CNLC Ⅲb were 35.3%,13.2%,0 and 23.5%,0 and 0,respectively. Univariate analysis showed that preoperative symptoms,AFP level,total protein level,AST level,total bilirubin level,intraoperative blood loss,intraoperative or postoperative blood transfusion,postoperative complications,tumor number and size,microvascular invasion,macrovascular invasion and tumor differentiation were prognostic factors for long-term survival(≥5 years)(all P<0.05). The multivariate analysis suggested that AST level,intraoperative blood loss,tumor number and size,macrovascular invasion and tumor differentiation were the independent prognostic factors of long-term OS (all P<0.05). Conclusions:HCC patients with different stages of CNLC have different recurrence patterns and prognosis.After strict preoperative evaluation,patients with CNLC Ⅱa-Ⅲb can also benefit from radical resection. AST level,intraoperative blood loss,tumor number,tumor size,macrovascular invasion and tumor differentiation were independent factors that affect long-term survival. This will provide an important basis for the choice of treatment and the evaluation of surgical prognosis for patients with HCC.

Objective:To construct a computed tomography (CT)-based radiomics model for predicting tumor recurrence of early-stage hepatocellular carcinoma (HCC) after resection, and explore its application value.Methods:The retrospective cohort study was conducted. The clinicopathological data of 243 patients with early-stage HCC who underwent hepatectomy in 2 medical centers between January 2009 and December 2016 were collected, including 165 in the First Affiliated Hospital of Nanjing Medical University and 78 in the Wuxi People′s Hospital. There were 182 males and 61 females, aged from 30 to 86 years, with a median age of 57 years. According to the random numbers showed in the computer, 243 patients were randomly assigned into training dataset consisting of 162 patients and test dataset consisting of 81 patients, with a ratio of 2∶1. Using radiomics technique, a total of 3 384 radiomics features were extracted from the tumor and its periphery at arterial-phase and portal-phase images of CT scan. In the training dataset, a radiomics signature was constructed and predicted its performance after dimension reduction of stable features by using aggregated feature selection algorithms [feature ranking via maximal relevance and minimal redundancy (MRMR) combined with random survival forest (RSF) + LASSO-COX regression analysis]. Risk factors for tumor recurrence were selected using the univariate COX regression analysis, and two radiomics models including radiomics 1 (preoperative) and radiomics 2 (postoperative) were constructed and predicted their performance using backward stepwise multivariate COX regression analysis. The two models were validated in the training and test dataset. Observation indicators: (1) follow-up; (2) construction of HCC recurrence-related radiomics signature for early-stage HCC after resection; (3) prediction performance of HCC recurrence-related radiomics signature for early-stage HCC after resection; (4) construction of HCC recurrence-related radiomics prediction model for early-stage HCC after resection; (5) validation of HCC recurrence-related radiomics prediction model for early-stage HCC after resection; (6) comparison of the prediction performance of radiomics model with that of other clinical statistical models and current HCC staging systems; (7) stratification analysis of postoperative recurrence risk based on radiomics models for early-stage HCC after resection. Patients were followed up using outpatient examination or telephone interview once every 3 months within the first 2 years and once every 6 months after 2 years. The follow-up included collection of medical history, laboratory examination, and abdominal ultrasound examination. Contrast-enhanced CT or magnetic resonance imaging (MRI) examination was performed once every 6 months, and they were performed in advance on patients who had suspected recurrence based on laboratory examination or abdominal ultrasound for further diagnosis. Follow-up was up to January 2019. The endpoint was time to recurrence, which was from the date of surgery to the date of first detected disease recurrence or metastasis. Measurement data with normal distribution were represented as Mean± SD, and comparison between groups was analyzed by the t test. Measurement data with skewed distribution were described as M (range), and comparison between groups was analyzed by the Mann-Whitney U test. Count data were described as absolute numbesr or percentages, and comparison between groups was analyzed using the chi-square test. The survival curve and survival rate were respectively drawn and calculated by the Kaplan-Meier method, and the survival analysis was performed using the Log-rank test. Serum alpha-fetoprotein level was analyzed after the natural logarithm transformation. X-tile software was used to select the optimal cut-point for continuous markers. Results:(1) Follow-up: all the 243 HCC patients received follow-up. Patients in the training dataset were followed up for 4.2-109.2 months, with a median follow-up time of 51.6 months. Patients in the test dataset were followed up for 12.7-107.6 months, with a median follow-up time of 73.2 months. The 2-, 5-year disease-free survival rates were 77.8% and 53.1% of the training dataset respectively, versus 86.4% and 61.7% of the test dataset. There was no significant difference in terms of disease-free survival between two datasets ( χ2=1.773, P>0.05). (2) Construction of HCC recurrence-related radiomics signature for early-stage HCC after resection: of the 3 384 radiomics features, 2 426 radiomics features with high stability were selected for analysis. There were 37 radiomics features identified after combining the top 20 radiomics features ranked by MRMR and RSF algorithms. LASSO-COX regression algorithm further reduced their dimensionality to retain 7 radiomics features and construct a radiomics signature. The indicators including region, scanning phase, and weighting coefficient of above mentioned seven features were Feature 1 (peritumoral, arterial phase, 0.041), Feature 2 (peritumoral, arterial phase, -0.103), Feature 3 (peritumoral, arterial phase, -0.259), Feature 4 (intratumoral, arterial phase, 0.211), Feature 5 (peritumoral, portal venous phase, -0.170), Feature 6 (intratumoral, portal venous phase, 0.130), and Feature 7 (intratumoral, portal venous phase, 0.090), respectively. Radiomics signature score=0.041×Feature 1-0.103×Feature 2-0.259×Feature 3+ 0.211×Feature 4-0.170×Feature 5+ 0.130×Feature 6+ 0.090×Feature 7. (3) Prediction performance of HCC recurrence-related radiomics signature for early-stage HCC after resection: the radiomics signature showed favorable prediction performance in both training and test datasets, with respective C-index of 0.648 [95% confidence interval ( CI): 0.583-0.713] and 0.669 (95% CI: 0.587-0.750). (4) Construction of HCC recurrence-related radiomics prediction model for early-stage HCC after resection: results of univariate analysis showed that ln(serum alpha-fetoprotein), liver cirrhosis, tumor margin status, arterial peritumoral enhancement, intratumoral necrosis, radiomics signature, satellite nodules, and microvascular invasion were related factors for tumor recurrence after resection of early-stage HCC ( hazard ratio=1.202, 1.776, 1.889, 2.957, 1.713, 4.237, 4.364, 4.258, 95% CI: 1.083-1.333, 1.068-2.953, 1.181-3.024, 1.462-5.981, 1.076-2.728, 2.593-6.923, 2.468-7.717, 2.427-7.468, P<0.05 ). Results of multivariate analysis showed that the radiomics model 1 (preoperative) consisted of ln(serum alpha-fetoprotein), tumor margin status, and radiomics signature ( hazard ratio=1.145, 1.838, 3.525, 95% CI: 1.029-1.273, 1.143-2.955, 2.172-5.720, P<0.05); the radiomics model 2 (postoperative) consisted of ln(serum alpha-fetoprotein), radiomics signature, microvascular invasion, and satellite nodules ( hazard ratio=1.123, 2.386, 3.456, 3.481, 95% CI: 1.005-1.254, 1.501-3.795, 1.863-6.410, 1.891-6.408, P<0.05). Risk prediction formulas: radiomics model 1 = 0.135×ln(serum alpha-fetoprotein)+ 0.608×tumor margin status (0: smooth; 1: non-smooth)+ 1.260×radiomics signature; radiomics model 2 = 0.116×ln(serum alpha-fetoprotein)+ 0.870×radiomics signature + 1.240×microvascular invasion (0: absent; 1: present)+ 1.247×satellite nodules (0: absent; 1: present). (5) Validation of HCC recurrence-related radiomics prediction model for early-stage HCC after resection: in both training and test datasets, radiomics model 1 provided good prediction performance, with respective C-index of 0.716 (95% CI: 0.662-0.770) and 0.724 (95% CI: 0.642-0.806), while radiomics model 2 provided better prediction performance, with respective C-index of 0.765 (95% CI: 0.712-0.818) and 0.741 (95% CI: 0.662-0.820). Calibration curves demonstrated good agreement between model-predicted probabilities and observed outcomes. (6) Comparison of the prediction performance of radiomics model with that of other clinical statistical models and current HCC staging systems: in the training dataset, the prediction performance of radiomics model 1 for tumor recurrence after resection of early-stage HCC was significantly different from that of ERASL model (preoperative), Barcelona clinic liver cancer (BCLC) staging, Hong Kong liver cancer (HKLC) staging, and cancer of the liver Italian program (CLIP) classification (C-index=0.562, 0.484, 0.520, 0.622, 95% CI: 0.490-0.634, 0.311-0.658, 0.301-0.740, 0.509-0.736, P<0.05); the prediction performance of radiomics model 2 for tumor recurrence after resection of early-stage HCC was significantly different from that of ERASL model (postoperative), Korean model, and the eighth edition TNM staging (C-index=0.601, 0.523, 0.513, 95% CI: 0.524-0.677, 0.449-0.596, 0.273-0.753, P<0.05). In the test dataset, the prediction performance of radiomics model 1 for tumor recurrence after resection of early-stage HCC was significantly different from that of ERASL model (preoperative), BCLC staging, HKLC staging, CLIP classification (C-index=0.540, 0.473, 0.504, 0.545, 95% CI: 0.442-0.638, 0.252-0.693, 0.252-0.757, 0.361-0.730, P<0.05); the prediction performance of radiomics model 2 for tumor recurrence after resection of early-stage HCC was significantly different from that of ERASL model (postoperative), Korean model, and the eighth edition TNM staging (C-index=0.562, 0.513, 0.521, 95% CI: 0.451-0.672, 0.399-0.626, 0.251-0.791, P<0.05). (7) Stratification analysis of postoperative recurrence risk based on radiomics models for tumor recurrence after resection of early-stage HCC: according to the analysis of X-tile, the score of radiomics model 1 < 1.4 (corresponding to total points < 62.0 in nomogram) was classified into low-risk group while the score of radiomics model 1 ≥ 1.4 (corresponding to total points ≥ 62.0 in nomogram) was classified into high-risk group. The score of radiomics model 2 < 1.7 (corresponding to total points < 88.0 in nomogram) was classified into low-risk group while the score of radiomics model 2 ≥ 1.7 (corresponding to total points ≥ 88.0 in nomogram) was classified into high-risk group. In the training dataset, the 2- and 5-year recurrence rates were 14.1%, 35.3% for low-risk patients and 63.0%, 100.0% for high-risk patients, which were predicted by radiomics model 1. There were significant differences between the two groups ( χ2= 70.381, P<0.05). The 2- and 5-year recurrence rates were 12.9%, 38.2% for low-risk patients and 81.8%, 100.0% for high-risk patients, which were predicted by radiomics model 2. There were significant differences between the two groups ( χ2= 98.613, P<0.05). In the test dataset, the 2- and 5-year recurrence rates were 5.6%, 29.3% for low-risk patients and 70.0%, 100.0% for high-risk patients, which were predicted by radiomics model 1. There were significant differences between the two groups ( χ2= 64.453, P<0.05). Ther 2- and 5-year recurrence rates were 5.7%, 28.1% for low-risk patients and 63.6%, 100.0% for high-risk patients, which were predicted by radiomics model 2. There were significant differences between the two groups ( χ2= 58.032, P<0.05). Conclusions:The 7-feature-based radiomics signature is built by selection of CT radiomics features in this study, and then HCC recurrence-related radiomics prediction model for early-stage HCC after resection is constructed. The proposed radiomics models can complement the existing clinical-radiological-pathological prognostic sources, accurately and individually predict tumor recurrence risk preoperatively and postoperatively, which facilitate clinical decision-support for patients with early-stage HCC.