OBJECTIVE: To develop an original-mirror alignment associated deep learning algorithm for intelligent registration of three-dimensional maxillofacial point cloud data, by utilizing a dynamic graph-based registration network model (maxillofacial dynamic graph registration network, MDGR-Net), and to provide a valuable reference for digital design and analysis in clinical dental applications. METHODS: Four hundred clinical patients without significant deformities were recruited from Peking University School of Stomatology from October 2018 to October 2022. Through data augmentation, a total of 2 000 three-dimensional maxillofacial datasets were generated for training and testing the MDGR-Net algorithm. These were divided into a training set (1 400 cases), a validation set (200 cases), and an internal test set (200 cases). The MDGR-Net model constructed feature vectors for key points in both original and mirror point clouds (X, Y), established correspondences between key points in the X and Y point clouds based on these feature vectors, and calculated rotation and translation matrices using singular value decomposition (SVD). Utilizing the MDGR-Net model, intelligent registration of the original and mirror point clouds were achieved, resulting in a combined point cloud. The principal component analysis (PCA) algorithm was applied to this combined point cloud to obtain the symmetry reference plane associated with the MDGR-Net methodology. Model evaluation for the translation and rotation matrices on the test set was performed using the coefficient of determination (R²). Angle error evaluations for the three-dimensional maxillofacial symmetry reference planes were constructed using the MDGR-Net-associated method and the "ground truth" iterative closest point (ICP)-associated method were conducted on 200 cases in the internal test set and 40 cases in an external test set. RESULTS: Based on testing with the three-dimensional maxillofacial data from the 200-case internal test set, the MDGR-Net model achieved an R² value of 0.91 for the rotation matrix and 0.98 for the translation matrix. The average angle error on the internal and external test sets were 0.84°±0.55° and 0.58°±0.43°, respectively. The construction of the three-dimensional maxillofacial symmetry reference plane for 40 clinical cases took only 3 seconds, with the model performing optimally in the patients with skeletal Class Ⅲ malocclusion, high angle cases, and Angle Class Ⅲ orthodontic patients. CONCLUSION This study proposed the MDGR-Net association method based on intelligent point cloud registration as a novel solution for constructing three-dimensional maxillofacial symmetry reference planes in clinical dental applications, which can significantly enhance diagnostic and therapeutic efficiency and outcomes, while reduce expert dependence.
Humans ; Deep Learning ; Algorithms ; Imaging, Three-Dimensional/methods* ; Male ; Female ; Maxilla/diagnostic imaging* ; Adult

Objective To construct myeloid-specific Spi1 gene knockout mice and analyze their genotypes,so as to provide animal model basis for the study of pathological mechanism of diseases and drug targets.Methods Ac-cording to the principle of CRISPR/Cas9 technology and Cre/LoxP system,sgRNA and Donor vectors were de-signed and constructed.The transcript of Exon 2(Exon 2)was used as the knockout region,and Loxp elements were placed on both sides of Exon 2.Cas9 protein,sgRNA and Donor vector were mixed and microinjected into the fertilized eggs of C57BL/6J mice,the fertilized eggs were transplanted into the uterus of C57BL/6J pregnant female mice,and F0 generation was obtained after 19～20 days.Positive F0 mice were mated with C57BL/6J mice to ob-tain stable F1 Spi1flox/+mice.Spi1flox/+mice of F1 generation were selfed to obtain Spi1flox/flox mice.Spi1flox/flox mated with Lyz2-Cre+mice to obtain Spi1flox/+/Lyz2-Cre+mice,and then mated with Spi1flox/flox,the Spi1flox/flox/Lyz2-Cre+mice were myeloid-specific Spi1 gene knockout(KO)mice.Spi1flox/flox/Lyz2-cre-mice were used as wild-type(WT)mice.DNA of WT and KO mice was extracted,and the genotypes were identified by agarose gel electro-phoresis after PCR amplification.Western blot was used to detect the expression of spleen focus forming virus provi-ral integration oncogene,Spi-1/purine rich box-1(PU.1)in immune cells of WT and KO mice.Results The results of PCR identification showed that the genotype of mice with only 220 bp amplified by flox primer was Spi1flox/flox homozygote,and the genotype of mice with 700 bp amplified by Lyz2-Cre primer was Lyz2-Cre+.Western blot showed that compared with WT group,the protein PU.1 was not expressed in bone marrow-derived macropha-ges(BMDMs)and peritoneal macrophages(PM)in KO group(P<0.01).There was no significant difference of statistics in the expression level of PU.1 in T cells between KO mice and WT mice.The results of PCR and West-ern blot showed that myeloid-specific Spi1 KO mice were successfully constructed.Conclusion The myeloid-spe-cific Spi1 gene KO mice are successfully constructed and identified,which provides animal model basis for further revealing the potential mechanism of PU.1 inimmune regulation.

Objective To breed and identify the T lymphocyte-conditional Spi1 knockout mice for the further in-vestgation of the specific role of Spi1-encoded protein PU.1.Methods The Lck-Cre mice were mated with Spi1flox/flox mice to obtain Lck-Cre×Spi1flox/flox mice(T lymphocyte-specific Spi1 knockout mice),and the genotype was determined by polymerase chain reaction(PCR)and agarose gel electrophoresis.Magnetic beads were used to sort out the splenic T lymphocytes,and the knockdown efficiency of PU.1 in T cells was detected by Western blot,quantitative real-time PCR(qPCR)and flow cytometry.Results The Lck-Cre×Spi1flox/flox mouse genotype was stably inherited.Compared with Spi1flox/flox mice,the expression level of PU.1 was significantly reduced in splenic T cells of Lck-Cre×Spi1flox/flox mice.Conclusion In this study,the T lymphocyte-specific Spi1 knockout mice was successfully constructed by applying Cre/LoxP system and CRISPR/Cas9 technology,which provided a reliable an-imal model for the subsequent experiments of the specific role of PU.1 in T cell-related diseases.

Objective To construct Csf1r-CreERT2 R26REYFP reporter gene mice and assess the efficacy of Csf1r-CreERT2-mediated enhancement of CSF1R in CD45+cells labeled with yellow fluorescein protein EYFP.Methods Csf1r-CreERT2 mice were crossbred with R26REYFP homozygous mice,and Csf1r-CreERT2R26REYFP mice were identified through PCR and Western Blot analyses.Flow cytometry was employed to evaluate CSF1R tag-efficiency in CD45+cells across different mouse tissues following tamoxifen induction.Results Csf1r-CreERT2 R26REYFP reporter gene mice were acquired.In addition,it was found that Csf1r-CreERT2-mediated EYFP could effectively mark CSF1R in various tissues of mice and CD45+cells in different locations.Compared to the R26REYF P group,the highest labeling efficiency was observed in the brain tissue(P＜0.001),the lowest in the thymus tissue(P＜0.05),and no sig-nificant difference was observed in the spleen tissue.Conclusion Adult Csf1r-CreERT2 mice and R26REYFP mice are effective ways to obtain Csf1r-CreERT2 R26REYFP induced conditional fluorescence mice.Csf1r-CreERT2 can mediate EYFP to effectively trace CSF1R in CD45+cells in different parts of mice.

OBJECTIVE Taking Professor Zhou Zhongying's clinical cases of treating hyperthyroidism as the research object,this article explored the use of the TabNet model based on neural networks to discover the diagnosis and treatment rules of hyperthyroid-ism,providing a method reference for inheriting the academic thoughts of famous veteran traditional Chinese medicine practitioners and assisting clinical diagnosis and treatment.METHODS Based on the clinical diagnosis and treatment cases of hyperthyroidism of Pro-fessor Zhou Zhongying and his team,standardized and structured training data were constructed;algorithms based on attention mecha-nism and sparse feature selection mechanism were studied;a pathogenesis prediction model was constructed by inputting standardized clinical manifestations,standardized tongue and pulse conditions;core symptoms,pathogenesis and medication were analyzed,as well as the relationship between the three.RESULTS The trained prediction model was used to predict the 6 pathogenesis of liver stagna-tion,liver fire,phlegm fluid,kidney deficiency,yin deficiency,and blood stasis.Compared with multi-label classification models constructed by classic algorithms such as decision trees and random forests,this model had better classification and prediction indica-tors.Mining was carried out through the decision tree algorithm,and 6 core pathogenesis corresponding Chinese medicine groups were summarized:vinegar-baked Bupleurum chinense,prunella vulgaris,oyster,processed Carapax trionycis,Scrophularia ningpoensis,Asparagus cochinchinensis,Ophiopogon japonicus,etc.CONCLUSION Using the TabNet algorithm on clinical medical record data to build a pathogenesis prediction model based on clinical manifestations,tongue and pulse conditions can effectively predict the core pathogenesis,and then discover the connection between symptoms,pathogenesis and medication,providing methodological references for the inheritance of academic ideas of famous veteran traditional Chinese medicine practitioners and clinical auxiliary diagnosis and treatment decision-making.

Purpose: The risk stratification of pediatric anaplastic large cell lymphoma (ALCL) has not been standardized. In this study, new risk factors were included to establish a new risk stratification system for ALCL, and its feasibility in clinical practice was explored. Materials and Methods: On the basis of the non-Hodgkin’s lymphoma Berlin–Frankfurt–Munster 95 (NHL-BFM-95) protocol, patients with minimal disseminated disease (MDD), high-risk tumor site (multiple bone, skin, liver, and lung involvement), and small cell/lymphohistiocytic (SC/LH) pathological subtype were enrolled in risk stratification. Patients were treated with a modified NHL-BFM-95 protocol combined with an anaplastic lymphoma kinase inhibitor or vinblastine (VBL). Results: A total of 136 patients were enrolled in this study. The median age was 8.8 years. The 3-year event-free survival (EFS) and overall survival of the entire cohort were 77.7% (95% confidence interval [CI], 69.0% to 83.9%) and 92.3% (95% CI, 86.1% to 95.8%), respectively. The 3-year EFS rates of low-risk group (R1), intermediate-risk group (R2), and high-risk group (R3) patients were 100%, 89.5% (95% CI, 76.5% to 95.5%), and 67.9% (95% CI, 55.4% to 77.6%), respectively. The prognosis of patients with MDD (+), stage IV cancer, SC/LH lymphoma, and high-risk sites was poor, and the 3-year EFS rates were 45.3% (95% CI, 68.6% to 19.0%), 65.7% (95% CI, 47.6% to 78.9%), 55.7% (95% CI, 26.2% to 77.5%), and 70.7% (95% CI, 48.6% to 84.6%), respectively. At the end of follow-up, one of the five patients who received maintenance therapy with VBL relapsed, and seven patients receiving anaplastic lymphoma kinase inhibitor maintenance therapy did not experience relapse. Conclusion This study has confirmed the poor prognostic of MDD (+), high-risk site and SC/LH, but patients with SC/LH lymphoma and MDD (+) at diagnosis still need to receive better treatment (ClinicalTrials.gov number, NCT03971305).

Objective:To establish an intelligent registration algorithm under the framework of original-mirror alignment algorithm to construct three-dimensional (3D) facial midsagittal plane automatically. Dynamic Graph Registration Network (DGRNet) was established to realize the intelligent registration, in order to provide a reference for clinical digital design and analysis.Methods:Two hundred clinical patients without significant facial deformities were collected from October 2020 to October 2022 at Peking University School and Hospital of Stomatology. The DGRNet consists of constructing the feature vectors of key points in point original and mirror point clouds (X, Y), obtaining the correspondence of key points, and calculating the rotation and translation by singular value decomposition. Original and mirror point clouds were registrated and united. The principal component analysis (PCA) algorithm was used to obtain the DGRNet alignment midsagittal plane. The model was evaluated based on the coefficient of determination (R 2) index for the translation and rotation matrix of test set. The angle error was evaluated on the 3D facial midsagittal plane constructed by the DGRNet alignment midsagittal plane and the iterative closet point (ICP) alignment midsagittal plane for 50 cases of clinical facial data. Results:The average angle error of the DGRNet alignment midsagittal plane and ICP alignment midsagittal plane was 1.05°±0.56°, and the minimum angle error was only 0.13°. The successful detection rate was 78% (39/50) within 1.50° and 90% (45/50) within 2.00°.Conclusions:This study proposes a new solution for the construction of 3D facial midsagittal plane based on the DGRNet alignment method with intelligent registration, which can improve the efficiency and effectiveness of treatment to some extent.

Objective: To obtain chimeric antigen receptor macrophages ( CAR-M) targeting HER2 stably transfected． Methods : CAR lentivirus vector targeting HER2 was constructed and infected with human monocytic leukemia cell line (THP-1) ．CAR THP-1 cells with green fluorescent labeling were selected by sorting flow cytometry and continued to be cultured in vitro．The CAR THP-1 cells targeting HER2 were co-cultured with the endometrial cancer cell line Ishikawa with negative and positive HER2 expression，and their targeted phagocytosis of CAR-M to HER2 positive tumor cells was detected by imaging flow cytometry ，and the targeted phagocytosis efficiency of CAR-M to HER2 positive tumor cells was detected by flow cytometry. Results : CAR lentivirus infection with THP- 1 cells was less efficient ; After co-culture with cancer cells，flow cytometry and imaging flow cytometry showed that CAR THP-1 cells had enhanced phagocytosis of HER2 positive Ishikawa cells compared with the empty body group (P＜0. 01) ． Conclusion In this experiment，CAR THP-1 cell line targeting HER2 was established by constructing CAR lentivirus vector and transfecting THP-1 cells ，and it was proved that CAR THP-1 could phagocytize HER2 positive Ishikawa cells through specific targeting.

Objective:To evaluate the clinical efficacy of multi-disciplinary single center's CCCG-HB-2016 regimen in the treatment of hepatoblastoma (HB) in children.Methods:Clinical data of 36 HB patients treated with CCCG-HB-2016 program from Aug 2016 to March 2020 were analyzed.Results:These 36 patients included 20 boys and 16 girls. The serum AFP was all higher than 2 792 ng/ml,there was a correlation between AFP and tumor risk stratification ( H=14.973, P<0.05). Twenty eight cases (77.78%) were epithelial type and 8 cases (22.22%) were mixed epithelial mesenchymal type.All children were treated by tumor resection combined with chemotherapy, and there was a correlation between tumor risk stratification and surgical resection of liver lobe ( H=8.847, P<0.05). The probability of bone marrow suppression in the low-risk group was 58.33% (35/60),that in the intermediate-risk group was 73.49% (61/83) and in the high-risk group was 80.23% (69/86).All 36 cases were followed up to March 31, 2020,with an average follow-up of 21.9 months and the median survival was 22.5 months.The overall survival rate (OS) and event-free survival rate (EFS) were 97.2% and 83.3% respectively. Conclusions:The multidisciplinary CCCG-HB-2016 regimen was with a high success rate and along with a high incidence of bone marrow suppression.

Objective To investigate the effects of controlled hypotension (CH) combined with tranexamic acid (TA) on peri-operative blood loss and coagulation function in patients undergoing brain tumor surgery. Methods Forty patients undergoing brain tumor surgery were randomly allocated into group A and group B with 20 patients in each group. Patients in group A received CH alone, while patients in group B received CH combined with TA. Coagulation factors and d-dimer levels were measured 24 hours before and after surgery. Amount of blood loss, intravenous fluid transfused, urine output and postoperative drainage were recorded. Results D-dimer levels of 24 hours after surgery increased compared with that of 24 hours before surgery. In group B, the d-dimer level increased more than that of group A (P < 0.05). No significant difference was found in coagulation factor levels between group A and group B. Amount of blood loss, intravenous fluid transfused and postoperative drainage flows of patients in group B were lower than that in group A (P < 0.05). There were no significant changes in urine output and fluid infusion volume between two groups. Conclusion CH compared with TA can reduce perioperative blood loss in patients undergoing brain tumor surgery , with no obvious coagulant function abnormality. Collectively, it should be a safe and reliable method for clinical application.