With the development of organ transplantation in clinical practice, allograft pathology has been constantly developing and advancing. The convening of Banff conference on allograft pathology and the establishment of Banff classification on allograft pathology (Banff classification) are pivotal milestones in the development of international allograft pathology. Since then, Banff classification on pathological diagnosis of various transplant organs have been continually updated and improved. Ultrastructural pathological observation by electron microscope plays an irreplaceable role in the early diagnosis of antibody-mediated rejection, recurrent disease and de novo disease of renal allograft. Early detection and rational treatment help to maintain the long-term survival of renal allograft and reduce the failure of renal allograft. In this article, the basic definition of electron microscope and the ultrastructural pathological diagnosis, the research history and main progress on electron microscope diagnosis on Banff classification for renal allograft pathology were introduced, and typical pathological changes, specific terminology and diagnostic criteria of electron microscope diagnosis on renal allograft biopsy were summarized, aiming to provide reference for clinical and basic research of organ transplantation.

Objective To predict microvascular invasion(MVI)in hepatocellular carcinoma(HCC)using a model based on multi-phase dynamic-enhanced CT(DCE-CT)radiomics feature and hierarchical fusion of multiple classifiers.Methods We retrospectively collected preoperative DCE-CT images from 111 patients with pathologically confirmed HCC in Guangzhou First People's Hospital between January,2016 and April,2020.The volume of interest was outlined in the early arterial phase,late arterial phase,portal venous phase and equilibrium phase,and radiomics features of these 4 phases were extracted.Seven classifiers based on different algorithms were trained using the filtered feature subsets to obtain multiple base classifiers under each phase.According to the hierarchical fusion strategy,a multi-criteria decision-making-based weight assignment algorithm was used for fusing each base classifier under the same phase with the model after extracting the phase information to obtain the prediction model.The proposed model was evaluated using a 5-fold cross-validation and assessed for area under the ROC curve(AUC),accuracy,sensitivity,and specificity.The prediction model was also compared with the fusion models using a single phase or multiple phases,models based on a single phase with a single classifier,models with different base classifier diversities,and 8 classifier models based on other ensemble methods.Results The experimental results showed that the performance of the proposed model for predicting HCCMVI was optimal after incorporating the 4 phases and 7 classifiers,with AUC,accuracy,sensitivity,and specificity of 0.828,0.766,0.877,and 0.648,respectively.Comparative experiments showed that this prediction model outperformed the models based on a single phase with a single classifier and other ensemble models.Conclusion The proposed prediction model is effective for predicting MVI in HCC with superior performance to other models.

Objective To predict microvascular invasion(MVI)in hepatocellular carcinoma(HCC)using a model based on multi-phase dynamic-enhanced CT(DCE-CT)radiomics feature and hierarchical fusion of multiple classifiers.Methods We retrospectively collected preoperative DCE-CT images from 111 patients with pathologically confirmed HCC in Guangzhou First People's Hospital between January,2016 and April,2020.The volume of interest was outlined in the early arterial phase,late arterial phase,portal venous phase and equilibrium phase,and radiomics features of these 4 phases were extracted.Seven classifiers based on different algorithms were trained using the filtered feature subsets to obtain multiple base classifiers under each phase.According to the hierarchical fusion strategy,a multi-criteria decision-making-based weight assignment algorithm was used for fusing each base classifier under the same phase with the model after extracting the phase information to obtain the prediction model.The proposed model was evaluated using a 5-fold cross-validation and assessed for area under the ROC curve(AUC),accuracy,sensitivity,and specificity.The prediction model was also compared with the fusion models using a single phase or multiple phases,models based on a single phase with a single classifier,models with different base classifier diversities,and 8 classifier models based on other ensemble methods.Results The experimental results showed that the performance of the proposed model for predicting HCCMVI was optimal after incorporating the 4 phases and 7 classifiers,with AUC,accuracy,sensitivity,and specificity of 0.828,0.766,0.877,and 0.648,respectively.Comparative experiments showed that this prediction model outperformed the models based on a single phase with a single classifier and other ensemble models.Conclusion The proposed prediction model is effective for predicting MVI in HCC with superior performance to other models.

Objective To explore the performance of a new multimodal feature fusion classification model based on distance matching and discriminative representation learning for differentiating high-grade glioma(HGG)from solitary brain metastasis(SBM).Methods We collected multi-parametric magnetic resonance imaging(MRI)data from 61 patients with HGG and 60 with SBM,and delineated regions of interest(ROI)on T1WI,T2WI,T2-weighted fluid attenuated inversion recovery(T2_FLAIR)and post-contrast enhancement T1WI(CE_T1WI)images.The radiomics features were extracted from each sequence using Pyradiomics and fused using a multimodal feature fusion classification model based on distance matching and discriminative representation learning to obtain a classification model.The discriminative performance of the classification model for differentiating HGG from SBM was evaluated using five-fold cross-validation with metrics of specificity,sensitivity,accuracy,and the area under the ROC curve(AUC)and quantitatively compared with other feature fusion models.Visual experiments were conducted to examine the fused features obtained by the proposed model to validate its feasibility and effectiveness.Results The five-fold cross-validation results showed that the proposed multimodal feature fusion classification model had a specificity of 0.871,a sensitivity of 0.817,an accuracy of 0.843,and an AUC of 0.930 for distinguishing HGG from SBM.This feature fusion method exhibited excellent discriminative performance in the visual experiments.Conclusion The proposed multimodal feature fusion classification model has an excellent ability for differentiating HGG from SBM with significant advantages over other feature fusion classification models in discrimination and classification tasks between HGG and SBM.

Objective To evaluate the performance of magnetic resonance imaging(MRI)multi-sequence feature imputation and fusion mutual model based on sequence deletion in differentiating high-grade glioma(HGG)from low-grade glioma(LGG).Methods We retrospectively collected multi-sequence MR images from 305 glioma patients,including 189 HGG patients and 116 LGG patients.The region of interest(ROI)of T1-weighted images(T1WI),T2-weighted images(T2WI),T2 fluid attenuated inversion recovery(T2_FLAIR)and post-contrast enhancement T1WI(CE_T1WI)were delineated to extract the radiomics features.A mutual-aid model of MRI multi-sequence feature imputation and fusion based on sequence deletion was used for imputation and fusion of the feature matrix with missing data.The discriminative ability of the model was evaluated using 5-fold cross-validation method and by assessing the accuracy,balanced accuracy,area under the ROC curve(AUC),specificity,and sensitivity.The proposed model was quantitatively compared with other non-holonomic multimodal classification models for discriminating HGG and LGG.Class separability experiments were performed on the latent features learned by the proposed feature imputation and fusion methods to observe the classification effect of the samples in two-dimensional plane.Convergence experiments were used to verify the feasibility of the model.Results For differentiation of HGG from LGG with a missing rate of 10%,the proposed model achieved accuracy,balanced accuracy,AUC,specificity,and sensitivity of 0.777,0.768,0.826,0.754 and 0.780,respectively.The fused latent features showed excellent performance in the class separability experiment,and the algorithm could be iterated to convergence with superior classification performance over other methods at the missing rates of 30%and 50%.Conclusion The proposed model has excellent performance in classification task of HGG and LGG and outperforms other non-holonomic multimodal classification models,demonstrating its potential for efficient processing of non-holonomic multimodal data.

Objective To explore the performance of a new multimodal feature fusion classification model based on distance matching and discriminative representation learning for differentiating high-grade glioma(HGG)from solitary brain metastasis(SBM).Methods We collected multi-parametric magnetic resonance imaging(MRI)data from 61 patients with HGG and 60 with SBM,and delineated regions of interest(ROI)on T1WI,T2WI,T2-weighted fluid attenuated inversion recovery(T2_FLAIR)and post-contrast enhancement T1WI(CE_T1WI)images.The radiomics features were extracted from each sequence using Pyradiomics and fused using a multimodal feature fusion classification model based on distance matching and discriminative representation learning to obtain a classification model.The discriminative performance of the classification model for differentiating HGG from SBM was evaluated using five-fold cross-validation with metrics of specificity,sensitivity,accuracy,and the area under the ROC curve(AUC)and quantitatively compared with other feature fusion models.Visual experiments were conducted to examine the fused features obtained by the proposed model to validate its feasibility and effectiveness.Results The five-fold cross-validation results showed that the proposed multimodal feature fusion classification model had a specificity of 0.871,a sensitivity of 0.817,an accuracy of 0.843,and an AUC of 0.930 for distinguishing HGG from SBM.This feature fusion method exhibited excellent discriminative performance in the visual experiments.Conclusion The proposed multimodal feature fusion classification model has an excellent ability for differentiating HGG from SBM with significant advantages over other feature fusion classification models in discrimination and classification tasks between HGG and SBM.

Objective To evaluate the performance of magnetic resonance imaging(MRI)multi-sequence feature imputation and fusion mutual model based on sequence deletion in differentiating high-grade glioma(HGG)from low-grade glioma(LGG).Methods We retrospectively collected multi-sequence MR images from 305 glioma patients,including 189 HGG patients and 116 LGG patients.The region of interest(ROI)of T1-weighted images(T1WI),T2-weighted images(T2WI),T2 fluid attenuated inversion recovery(T2_FLAIR)and post-contrast enhancement T1WI(CE_T1WI)were delineated to extract the radiomics features.A mutual-aid model of MRI multi-sequence feature imputation and fusion based on sequence deletion was used for imputation and fusion of the feature matrix with missing data.The discriminative ability of the model was evaluated using 5-fold cross-validation method and by assessing the accuracy,balanced accuracy,area under the ROC curve(AUC),specificity,and sensitivity.The proposed model was quantitatively compared with other non-holonomic multimodal classification models for discriminating HGG and LGG.Class separability experiments were performed on the latent features learned by the proposed feature imputation and fusion methods to observe the classification effect of the samples in two-dimensional plane.Convergence experiments were used to verify the feasibility of the model.Results For differentiation of HGG from LGG with a missing rate of 10%,the proposed model achieved accuracy,balanced accuracy,AUC,specificity,and sensitivity of 0.777,0.768,0.826,0.754 and 0.780,respectively.The fused latent features showed excellent performance in the class separability experiment,and the algorithm could be iterated to convergence with superior classification performance over other methods at the missing rates of 30%and 50%.Conclusion The proposed model has excellent performance in classification task of HGG and LGG and outperforms other non-holonomic multimodal classification models,demonstrating its potential for efficient processing of non-holonomic multimodal data.

Objective To investigate the relationships of pre-radiotherapy body weight,gender,age,EBVDNA,hemoglobin,plasma albumin,and induction chemotherapy regimen with the changes of target area and lymph node volume in adaptive radiotherapy,so as to provide a reference for the timing and population selection of adaptive radiotherapy.Methods A retrospective analysis was conducted on 34 patients who received the first course of radiotherapy at Sun Yat-sen University Cancer Center from January 2022 to November 2022.All patients underwent CT scans again after 20 sessions of radiotherapy for developing the secondary radiotherapy plans.The body weight,gender,age,tumor stage,hemoglobin,plasma albumin,induction chemotherapy regimen,and EBVDNA were collected.Results The tumor volume reduction in the primary focus was more evident in patients with pre-treatment plasma albumin≥40 g/L than in those with pre-treatment plasma albumin<40 g/L(t=3.971,P=0.001),and in patients with pretreatment EBVDNA≤4000 copies/mL than in those with pretreatment EBVDNA>4000 copies/mL(t=4.080,P=0.001).Pearson analysis showed that GTVnx volume difference was positively correlated with pre-radiotherapy GTVnx volume(r=0.444,P=0.009),right parotid gland volume difference(r=0.737,P<0.001),left parotid gland volume difference(r=0.435,P=0.010),and hemoglobin(r=0.722,P<0.001).Conclusion The reduction in tumor volume during radiotherapy is more pronounced in nasopharyngeal cancer patients with normal plasma albumin level and those with pretreatment EBVDNA≤4000 copies/mL.The pre-radiotherapy treatment volume of primary focus,parotid gland volume change before and after radiotherapy,and pre-radiotherapy EBVDNA,hemoglobin and plasma albumin levels can be used to predict the degree of tumor volume shrinkage during radiotherapy,providing a reference for the selection of the timing of adaptive radiotherapy for nasopharyngeal carcinoma.

As an emerging discipline that combines traditional diagnostic methods with modern scientific technology,micro syndrome differentiation has good prospects for development,but there are some controversies in the research process.Based on ancient and modern literature,this article reviewed the origin and flow of research on micro syndrome differentiation,and summarized the problems to be improved in the process of research on micro syndrome differentiation from three aspects:application of disease type,guiding ideology and micro indicators.Based on this,the article further expounded the new thinking on"near-micro"syndrome differentiation from three aspects:connotation,scope of application,and links to traditional identification and micro-identification,and pointed out that the modern medical detection basis should be incorporated into the field of TCM syndrome differentiation,and at the same time,it should be based on the overall thinking mode of TCM,which would provide a new idea for the development of modern TCM diagnosis technology.

Objective: To investigate the effect of silencing the endoplasmic reticulum stress-related protein calnexin on the proliferation, invasion, and migration of tongue squamous cell carcinoma cells. Methods : Calnexin siRNA was transfected into SCC-9 and SCC-25 tongue squamous cell carcinoma cells, and the expression of calnexin was detected by qRT-PCR. The silencing effect of calnexin siRNA was further verified by Western blotting. CCK-8 assay was applied to detect the effect of silencing calnexin on the proliferation of tongue squamous cell carcinoma cells; Transwell assay was used to detect the effect of silencing calnexin on the invasion and migration of tongue squamous cell carcinoma cells. Results : qRT-PCR showed that calnexin siRNA could effectively downregulate the expression of calnexin. Western blot analysis further confirmed the silencing effect of calnexin siRNA on calnexin. The CCK-8 assay showed that silencing calnexin expression on the 4th and 5th days could inhibit the proliferation of tongue squamous cell carcinoma cells, and the difference was statistically significant (P < 0.01). The Transwell assay showed that knockdown of calnexin could inhibit the invasion and migration of tongue squamous cell carcinoma cells (P < 0.001). Conclusion Knockdown of calnexin can inhibit the proliferation, invasion, and migration of tongue squamous cell carcinoma cells.