Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Objective To develop a combined model integrating radiomics and 3D deep learning features for improving the predictive efficacy of overall survival in non-small cell lung cancer(NSCLC)patients undergoing radiotherapy,thereby providing a foundation for optimizing individualized radiotherapy strategies.Methods A retrospective analysis was conducted on 522 NSCLC patients from 3 centers.Radiomics features were extracted from the tumor region of interest on radiotherapy planning CT scans,and a 3D-SE-ResNet was constructed to extract deep learning features.Following feature extraction,features were selected via univariate Cox analysis and Lasso-Cox regression,and a combined model was established by fusing the two feature types through principal component analysis.The discriminative ability of the model was evaluated using the concordance index(C-index)and the area under the receiver operating characteristic curve(AUC),while the risk stratification efficacy was verified by Kaplan-Meier survival analysis.Results The predictive performance of deep learning features was significantly superior to that of radiomics features(C-index:0.73 vs 0.65).The combined model achieved the highest predictive performance in the training set,internal test set,and external test set(C-index:0.74,0.69,0.72 respectively),with higher AUC values for predicting 1-year,2-year,and 3-year OS than either single model.Kaplan-Meier analysis showed significant differences in survival between the high-and low-risk groups(Log-rank test,P<0.001),and calibration curves indicated good consistency between predicted and actual survival outcomes.Conclusion The combined model integrating radiomics and 3D deep learning features can accurately predict survival outcomes in NSCLC patients undergoing radiotherapy.The multi-center validation results support its potential application in prognosis stratification for individualized radiotherapy.

Objective To explore the microsurgical method in treating ruptured aneurysms treatment and evaluating the treatment of the complication during or after the operation.Methods 36 cases of patients with intracranial aneurysm were analyzed retrospectively.All of the patients were subarachnoid hemorrhage (SAH) by CT scan on admission.The intracranial aneurysms were confirmed in 35 cases by DSA examination and A2 aneurysm was confirmed by explorative operation in 1 case.The microsurgical treatment was performed in 36 cases at the early or intermediate stage,22 cases were treated in the early stage,the other 14 cases were treated in the intermediate stage (early stage means within 3 days post SAH;intermediate stage means from 4 days to 10 days post SAH).Results After the operation,21 cases were GOS grade Ⅰ,4 cases were COS grade Ⅱ,4 cases were COS grade Ⅲ,4 cases were GOS grade Ⅳ.Of all the patients,CT scan was done after the operation,finding no intracranial bemorrhage,and cerebral infarction was disclosed in 5 cases.3 cases were dead,one suffered occipital lobe infaret after the PCoA aneurysm clipped,brain hernia occurred at last,one's Hunt Hess grade was Ⅴ,ACoA aneurysm was disclosed by DSA examination,severe brain edema occurred after the operation,the other suffered tonsillar hernia one week after the aneurysm clipping,which ruptured after endovascular treatment of ACoA aneurysm 2 years later.DSA examinations were done in 26 cases after operation,declaring 1 ACoA aneurysm was unclipped,1 PCoA aneurysm was incompletely clipped,and 1 PCoA was sacrificed.Conclusions It is a valuable method to clip the ruptured intracranial aneurysms in early and intermediate stage.The cerebral ischemia is the severe complication after clipping.Especially for the PCoA aneurysms,it is very important to protect the PCoA.Further research should be done for the treatment in the case with mother artery arteriosclerosis and thrombosis within the aneurysms.

OBJECTIVETo evaluate the restoration of function after spinal cord injury (SCI) in patients of different ages who have underwent intraspinal transplantation of olfactory ensheathing cells (OECs).

METHODSOne hundred and seventy-one SCI patients were included in this study. Of them, 139 were male and 32 were female, with age ranging from 2 to 64 years (mean, 34.9 years). In all SCI patients the lesions were injected at the time of operation with OECs. According to their ages, the patients were divided into 5 groups: 51 years group (n = 14). The spinal cord function was assessed based on the American Spinal Injury Association (ASIA) Classification System before and 2 - 8 weeks after OECs transplantation. One-way ANOVA and q test were used for statistical analysis, and the data were expressed as mean +/- SD.

RESULTSAfter surgery, the motor scores increased by 5.2 +/- 4.8, 8.6 +/- 8.0, 8.3 +/- 8.8, 5.7 +/- 7.3 and 8.2 +/- 7.6 in 5 age groups respectively (F = 1.009, P = 0.404); light touch scores increased by 13.9 +/- 8.1, 15.5 +/- 14.3, 12.0 +/- 14.4, 14.1 +/- 18.5 and 24.8 +/- 25.3 respectively (F = 1.837, P = 0.124); and pin prick scores increased by 11.1 +/- 7.9, 17.2 +/- 14.3, 13.2 +/- 11.8, 13.6 +/- 13.9 and 25.4 +/- 24.3 respectively (F = 2.651, P = 0.035). Restoration of pin prick in > 51 years group was better than other age groups except 21 - 30 years group.

CONCLUSIONOECs transplantation can improve the neurological function of spinal cord of SCI patients regardless of their ages. Further research into the long-term outcomes of the treatment will be required.

Adolescent ; Adult ; Age Factors ; Child ; Child, Preschool ; Female ; Humans ; Male ; Middle Aged ; Olfactory Bulb ; cytology ; transplantation ; Spinal Cord ; physiology ; Spinal Cord Injuries ; surgery ; Treatment Outcome