Purpose To investigate the feasibility of multi-sequence MRI-based radiomics for predicting epidermal growth factor receptor(EGFR)mutation status in brain metastases from non-small cell lung cancer(NSCLC).Materials and Methods This retrospective study included 237 patients with NSCLC brain metastases from the Second Xiangya Hospital of Central South University(January 1,2017 to December 31,2023)who underwent EGFR genetic testing.All patients underwent pretreatment brain MRI including contrast-enhanced T1-weighted,T2-weighted FLAIR,and T2-weighted sequences,along with chest CT for primary lung lesions.EGFR mutations were identified in 120 patients.Using December 31,2021 as the cutoff date,patients were divided into training(n=146)and validation(n=91)cohorts.Senior radiologists delineated brain metastases on multi-sequence MRI and primary lesions on CT.A total of 851 radiomic features were extracted using PyRadiomics.Following feature selection,machine learning models were constructed using support vector machine algorithm and compared with least absolute shrinkage and selection operator-derived radiomic signatures.Five models were developed:three single-sequence MRI models,a multi-sequence MRI fusion model,and a CT model,with diagnostic performance evaluated by area under the receiver operating characteristic curve.Results The multi-sequence MRI fusion model demonstrated superior performance across all imaging types.The least absolute shrinkage and selection operator and support vector machine models achieved training set area under the curve of 0.854(95%CI 0.748-0.960)and 0.948(95%CI 0.923-0.973),respectively,and validation set area under the curve of 0.810(95%CI 0.751-0.869)and 0.951(95%CI 0.917-0.985),respectively.The optimal prediction model utilized support vector machine algorithm with multi-sequence MRI features.Conclusion Pretreatment multi-sequence MRI radiomics combined with machine learning accurately predicts EGFR mutation status in NSCLC patients with brain metastases.

Purpose To investigate the feasibility of multi-sequence MRI-based radiomics for predicting epidermal growth factor receptor(EGFR)mutation status in brain metastases from non-small cell lung cancer(NSCLC).Materials and Methods This retrospective study included 237 patients with NSCLC brain metastases from the Second Xiangya Hospital of Central South University(January 1,2017 to December 31,2023)who underwent EGFR genetic testing.All patients underwent pretreatment brain MRI including contrast-enhanced T1-weighted,T2-weighted FLAIR,and T2-weighted sequences,along with chest CT for primary lung lesions.EGFR mutations were identified in 120 patients.Using December 31,2021 as the cutoff date,patients were divided into training(n=146)and validation(n=91)cohorts.Senior radiologists delineated brain metastases on multi-sequence MRI and primary lesions on CT.A total of 851 radiomic features were extracted using PyRadiomics.Following feature selection,machine learning models were constructed using support vector machine algorithm and compared with least absolute shrinkage and selection operator-derived radiomic signatures.Five models were developed:three single-sequence MRI models,a multi-sequence MRI fusion model,and a CT model,with diagnostic performance evaluated by area under the receiver operating characteristic curve.Results The multi-sequence MRI fusion model demonstrated superior performance across all imaging types.The least absolute shrinkage and selection operator and support vector machine models achieved training set area under the curve of 0.854(95%CI 0.748-0.960)and 0.948(95%CI 0.923-0.973),respectively,and validation set area under the curve of 0.810(95%CI 0.751-0.869)and 0.951(95%CI 0.917-0.985),respectively.The optimal prediction model utilized support vector machine algorithm with multi-sequence MRI features.Conclusion Pretreatment multi-sequence MRI radiomics combined with machine learning accurately predicts EGFR mutation status in NSCLC patients with brain metastases.

Objective To understand the incidence and risk factors of warfarin related hemorrhagic events during anticoagulation therapy with warfarin in patients with cirrhosis and portal vein thrombosis (PVT)after transjugular intrahepatic portosystemic shunt (TIPS). Methods The patients with liver cirrhosis who were treated with warfarin after TIPS due to portal hypertension were followed up from January 2012 in Xijing Hospital of Digestive Diseases,Air Force Military Medical University. The data of medical records and follow-up records up to the end of December 2015 in patients undergoing TIPS were collected and retrospectively analyzed. Cumulative incidence of hemorrhagic events related to warfarin treatment was calculated by Kaplan-Meier method. The patients were divided into warfarin-related bleeding group (bleeding group ) and non warfarin-related bleeding group (non-bleeding group ). The risk factors of hemorrhagic events related to warfarin treatment were analyzed using Cox regression model and the hazard ratio (HR)and the 95% confidence interval (CI)were calculated. Results A total of 179 patients were enrolled,including 117 males and 62 females with ages of 25-79 years and average age of (52 ± 12)years;the bleeding group comprised 47 patients (26.3%)and the non-bleeding group comprised 132 patients (73.7%). The follow-up time after discharge ranged 1-74 months and the average time was (28 ± 21) months. The average portal pressure gradient dropped from (25.4 ± 5.2)to (8.7 ± 3.7)mmHg before and after TIPS (P＜0.001). The median dose of oral warfarin in patients in the bleeding group was 2.5 (ranged from 2.5 to 3.75)mg and the median INR was 3.12 (ranged from 2.04 to 9.41);the median dose of oral warfarin in patients in the non-bleeding group was 1.8 (ranged from 0.63 to 2.5)mg and the median INR was 1.85 (ranged from 1.5 to 3.38). Fifty eight cases of hemorrhagic events occurred in 47 patients in the bleeding group,including 24 cases of gingival bleeding,16 cases of epistaxis,8 cases of cutaneous purpura, 4 cases of conjunctival hemorrhage,2 cases of hemorrhage of digestive tract,2 cases of intracranial hemorrhage,1 cases of hematuria,and 1 cases of menorrhagia. Nine of the 47 patients in the bleeding group had bleeding from multiple sites. The results of Kaplan-Meier analysis showed that the 1-,2-,3-,4-,5-and 6-year cumulative incidences of hemorrhagic events related to warfarin treatment after operation were 19%,23%,24%,30%,41%,and 45%,respectively. Warfarin was stopped in 11 patients and given at reduced doses in 36 patients among the 47 patients in the bleeding group. After that,43 patients'hemorrhagic symptoms disappeared and 3 patients' symptoms relieved,and then warfarin treatments were continued,except that 1 patient with a long history of hypertension died of intracranial hemorrhage. Multiple Cox regression analysis showed that the baseline serum creatinine level ＞115 μmol/L was an independent risk factor for hemorrhagic events related to warfarin treatment (HR＝1.82,95%CI:1.01-3.28,P＝0.045). Conclusions It is relatively safe for patients with liver cirrhosis and PVT receiving warfarin anticoagulation therapy after TIPS. Elevated serum creatinine is an independent risk factor for hemorrhagic events related to warfarin treatment.

Objective To understand the incidence and risk factors of warfarin related hemorrhagic events during anticoagulation therapy with warfarin in patients with cirrhosis and portal vein thrombosis (PVT)after transjugular intrahepatic portosystemic shunt (TIPS). Methods The patients with liver cirrhosis who were treated with warfarin after TIPS due to portal hypertension were followed up from January 2012 in Xijing Hospital of Digestive Diseases,Air Force Military Medical University. The data of medical records and follow-up records up to the end of December 2015 in patients undergoing TIPS were collected and retrospectively analyzed. Cumulative incidence of hemorrhagic events related to warfarin treatment was calculated by Kaplan-Meier method. The patients were divided into warfarin-related bleeding group (bleeding group ) and non warfarin-related bleeding group (non-bleeding group ). The risk factors of hemorrhagic events related to warfarin treatment were analyzed using Cox regression model and the hazard ratio (HR)and the 95% confidence interval (CI)were calculated. Results A total of 179 patients were enrolled,including 117 males and 62 females with ages of 25-79 years and average age of (52 ± 12)years;the bleeding group comprised 47 patients (26.3%)and the non-bleeding group comprised 132 patients (73.7%). The follow-up time after discharge ranged 1-74 months and the average time was (28 ± 21) months. The average portal pressure gradient dropped from (25.4 ± 5.2)to (8.7 ± 3.7)mmHg before and after TIPS (P＜0.001). The median dose of oral warfarin in patients in the bleeding group was 2.5 (ranged from 2.5 to 3.75)mg and the median INR was 3.12 (ranged from 2.04 to 9.41);the median dose of oral warfarin in patients in the non-bleeding group was 1.8 (ranged from 0.63 to 2.5)mg and the median INR was 1.85 (ranged from 1.5 to 3.38). Fifty eight cases of hemorrhagic events occurred in 47 patients in the bleeding group,including 24 cases of gingival bleeding,16 cases of epistaxis,8 cases of cutaneous purpura, 4 cases of conjunctival hemorrhage,2 cases of hemorrhage of digestive tract,2 cases of intracranial hemorrhage,1 cases of hematuria,and 1 cases of menorrhagia. Nine of the 47 patients in the bleeding group had bleeding from multiple sites. The results of Kaplan-Meier analysis showed that the 1-,2-,3-,4-,5-and 6-year cumulative incidences of hemorrhagic events related to warfarin treatment after operation were 19%,23%,24%,30%,41%,and 45%,respectively. Warfarin was stopped in 11 patients and given at reduced doses in 36 patients among the 47 patients in the bleeding group. After that,43 patients'hemorrhagic symptoms disappeared and 3 patients' symptoms relieved,and then warfarin treatments were continued,except that 1 patient with a long history of hypertension died of intracranial hemorrhage. Multiple Cox regression analysis showed that the baseline serum creatinine level ＞115 μmol/L was an independent risk factor for hemorrhagic events related to warfarin treatment (HR＝1.82,95%CI:1.01-3.28,P＝0.045). Conclusions It is relatively safe for patients with liver cirrhosis and PVT receiving warfarin anticoagulation therapy after TIPS. Elevated serum creatinine is an independent risk factor for hemorrhagic events related to warfarin treatment.

Objective To analyze the prognostic factors in treating variceal hemorrhage patients of liver cirrhosis and portal hypertension with transjugular intrahepatic portosystemic shunt (TIPS).Methods From January 2003 to December 2008, the data of 162 variceal hemorrhage patients with liver cirrhosis and portal hypertension treated with TIPS was collected, which included basic information, biochemical examination results within 7 days before the operation, regular follow-up observation after the surgery and survival data. The survival prognostic indexes were assessed with Cox regression model. Results The successful rate of TIPS was 99% (161/162). The median follow up duration was 21 months. Child-Pugh score and blood platelet count (PLT) were closely correlated with survival (P = 0. 003 and 0. 024). The total cumulative survival rate in patients with Child-Pugh score below nine (75%, 102/136) was higher than over nine (50%, 13/26) (χ2 = 9. 12,P=0. 003).The total cumulative survival rate of patients with PLT count over 47 ×109/L (74%, 82/112) was higher than below 47 × 109/L(66 %, 33/50, χ2 =4. 528, P = 0. 033). The one year after operation cumulative survival rate of liver function Child-Pugh class A, B, and C was 92%, 85%, 55% respectively. Conclusion Child-Pugh score and platelet count are independent predictable factors for the survival of variceal hemorrhage patients with liver cirrhosis and portal hypertension treated by TIPS. The risk increase after operation when Child-Pugh score over 9 and/or PLT count less 47×109 /L.

Objective To evaluate the safety and efficacy of percutaneous transluminal angioplasty (PTA) in treating Budd-Chiari syndrome (BCS) and to analyze the long-term follow-up results. Methods From October 1998 to May 2008,98 BCS patients (inferior vena cava obstruction,n = 34 ; hepatic vein obstruction, n = 22; combined obstruction, n = 42) who accepted PTA treatment successfully were investigated. The changes of clinical manifestations and liver function post-operation were observed; the long term survival rate was evaluated. Results Only two patients were complicated with transhepatic puncture tract bleeding, the prognosis was good after emergency operation. Sixty patients presented with low extremities edema, which was fully subsided after PTA.Of eighty-eight ascites patients, ascites disappeared in eighty patients after operation, and in the other eight patients combined with oral diuretic treatment post-operation. The median Rotterdam prognostic score of one month post-operation and the last follow-up time point was 0. 11 and 0. 09, significantly lowered than pre-operation (1.12). The difference was statistical significance (P=0. 000). At 1, 3, 5 years postoperative, the cumulative vessel patency rates were 96%, 94% and 94% respectively, and the cumulative survival rates were 94%, 91% and 87%. Conclusions Treating BCS with PTA has a high success rate, a good safety and a long-term survival rate.

Objective To evaluate the effect of hepatic vein occlusion and stent replacement in treatment for Budd-Chiari syndrome(BCS).Methods Forty three patients with BCS were underwent percutanous puncture,radiography,transjugular angioplasty,balloon dilation and stent placement for hepatic vein under Doppller ultrasounographic guidance from July 2001 to September 2006. Results Technical success was 100%with no complications.The medium vein pressure was reduced from 32.5 tO 20 cm H2O(1 cm H2O-0.098 kPa)after stents replacement(P＜0.01).The hepatic vein angioplasty revealed that all stents were patent and branches were disappeared.The symptoms in 38 patients were disappeared immediately,and improved in 5 patients.All patients were followed up of 32 months(ranged 1-62).Except one patient died of severe gastric bleeding,the 42 patients were survived with symptoms free.Conclusion Hepatic vein occlusion and stent replacement are safe and effective in treatment of BCS.