Objective:To develop a prediction model based on imaging features by contrast-enhanced MRI radiomics combined with clinical features for early recurrence of hepatocellular carcinoma (HCC) after radical resection.Methods:A retrospective study was carried out on 109 HCC patients who underwent radical resection at the Fifth Affiliated Hospital of Wenzhou Medical University from January 2015 to December 2020. Of 109 patients enrolled in this study, there were 96 males and 13 females, aged (58.3±10.7) years. Based on whether there was recurrence within 12 months after operation, the patients were divided into the early recurrence group ( n=31) and the control group ( n=78). These 109 patients were then randomly divided into the validation set ( n=23) and the training set ( n=86) at a ratio of 1∶4. Based on preoperative multi-phase contrast-enhanced MRI scanning, the tumor lesions were delineated on the Radcloud platform, and 1 409 quantitative radiomic features were extracted. Dimension reduction and screening of these features were carried out using variance threshold, SelectKBest and LASSO. Combined with clinical features (alpha fetoprotein, tumor size), several prediction model were established through machine learning. The predictive efficiencies of these models were evaluated using the area under the receiver operating characteristic (ROC) curve, accuracy rate, recall rate and balanced F score. Results:The proportions of irregular tumor shape and unclear tumor boundary, as well as maximum tumor diameter in the early recurrence group were significantly higher than that in the control group, but the proportion of pseudocapsule was significantly lower than that in the control group (all P<0.05). A total of 465 features were screened from the 1 409 features using the variance threshold method, followed by 38 features were screened using the method of SelectKBest. Finally 7 optimal radiomic features were screened based on the LASSO method. When combined with clinical features, 5 prediction models were established through machine learning. These models were support vector machine, Gaussian naive bayes, logistic regression, Multinomial naive bayes and K-nearest neighbor (KNN), respectively. Among these 5 models, the prediction efficiency of the KNN model was relatively highest, with the area under the ROC curve, accuracy rate, recall rate and balanced F score being 0.90, 0.98, 0.74 and 0.84 in the training set, and 0.76, 0.92, 0.75 and 0.83 in the verification set, respectively. Thus, the KNN model was selected as the best prediction model in this study. Conclusion:The prediction model of KNN was developed for early recurrence of HCC after radical resection based on preoperative contrast-enhanced MRI radiomics combined with clinical features.

Objective To explore the impact of artificial intelligence(AI)-assisted computing systems on the success rate of surgery,stereoscopic vision,and quality of life in patients with intermittent exotropia.Methods A total of 108 children(216 eyes)with intermittent exotropia who visited Ziyang Hospital of West China Hospital,Sichuan University from March 2021 to April 2023 were collected and randomly divided into Group A and Group B,with 54 children(108 eyes)in each group.Group A used the traditional calculation method,while Group B used the AI-assisted calculation method to determine the surgical volume of strabismus in children by the angles of strabismus at 6m and 33 cm.The success rate of surgery,postoperative angle of strabismus,stereoscopic visual function,horizontal and vertical perceptual eye positions,and quality of life[Child Intermittent Exotropia Questionnaire(CIXTQ)score]were compared between the two groups at 1 day,1 month,3 months and 6 months after surgery.Results At 1 day,1 month,3 months and 6 months after surgery,the success rate of surgery in Group B was significantly higher than that in Group A(all P＜0.05).Compared with the val-ues at 1 day after surgery,the angles of strabismus at 6 m and 33 cm in the two groups were significantly reduced at 1 month,3 months and 6 months after surgery(all P＜0.05);Group B had significantly lower angles of strabismus at 6 m and 33 cm than Group A at 1 day,1 month,3 months and 6 months after surgery(all P＜0.05).At 1 month,3 months and 6 months after surgery,the central and far stereoscopic visions of children in the two groups gradually increased,with the increase rate in Group B being significantly higher than that in Group A(Finter-group=76.59,P＜0.05);the proportion of children without stereoscopic vision in both groups gradually decreased,with a decrease rate in Group B being significantly higher than that in Group A(Finter-group=137.74,P＜0.05).At 1 month,3 months and 6 months after surgery,the horizon-tal and vertical perceptual eye positions in Group B showed a significant descend range compared with those in Group A(all P＜0.05).At 1 day,1 month,3 months and 6 months after surgery,the exotropia displacement of children in both groups gradually increased,and the displacement of children in Group B was significantly smaller than that in Group A at 1 month,3 months and 6 months postoperatively(all P＜0.05).At 1 month,3 months and 6 months after surgery,the CIX-TQ scores of children in the two groups increased gradually,with CIXTQ scores in Group B being significantly higher than those of Group A(all P＜0.05).Conclusion AI-assisted computing systems can effectively improve the success rate of intermittent exotropia surgery,enhance the establishment of stereoscopic visual function,improve visual quality,and sig-nificantly improve the quality of life of children.

Objective Visual electrophysiology and optical correlation tomography angiography(OCTA)were used to investigate differences in preoperative retinal function in patients with type 2 diabetic cataract(DC)without obvious retinopathy(NDR)and to determine the clinical application of whole-process blood glucose man-agement(WBGM)for improving postoperative vision in DC patients.Methods This study investigated the preop-erative and postoperative visual electrophysiology(N75,P100,photopic FERG,and scotopic FERG),peripapil-lary retinal nerve fiber layer(pRNFL)and peripapillary capillary vessel density(ppVD)data,as well as trends in these data changes during blood glucose management intervention.Results As the course of T2DM progressed,FBG and HbA1c increased,the N75 and P100 lategraduancy periods of patients gradually lengthened,and the photopic FERG,scotopic FERG,pRNFL,and ppVD values decreased at each postoperative time point.At the same time,the best corrected visual acuity(BCVA)of patients after surgery gradually decreased(P<0.05).Compared with that at 1 week after surgery,the BCVA of Group A(without whole-process blood glucose manage-ment)gradually increased at 1 month and 3 months after surgery but showed a downward trend at 1 year after sur-gery.The BCVA of Group B(with whole-process blood glucose management)gradually stabilized at 1 month after surgery,and at all time points after surgery,the BCVA of Group B was better than that of Group A.The results showed that N75 and P100 in Group A were greater than those in Group B,while the photopic and scotopic FERG,pRNFL,and ppVD(%)in Group A were lower than those in Group B.In addition,N75 and P100 in Group A showed a gradual prolongation trend at various time points after surgery,while photopic FERG,scotopic FERG,pRNFL,and ppVD(%)showed a gradually decreasing trend.However,the above data in Group B gradu-ally stabilized at 3 months after DC surgery,approaching the preoperative level of the group(P<0.05).In the state of whole blood glucose management,although N75 and P100 both reached their longest durations at 1 week af-ter surgery,N75,P100,photopic FERG,scotopic FERG,and pRNFL showed a gradually decreasing trend at 1 month and 3 months after surgery,while ppVD(%)gradually increased(P<0.05).At various time points from 3 months to 1 year after surgery,the overall trend of the above indicators remained stable and close to the preoperative values(P>0.05).Conclusion According to the results of the quantitative analysis of visual electrophysiology and OCTA,in DC patients without obvious retinopathy and with the worsening of diabetes,retinal function decreased,but whole-process blood glucose management effectively restored retinal function and improved visual quality after surgery.