ABSTRACT
OBJECTIVE@#To establish a deep learning algorithm that can accurately determine three-dimensional facial anatomical landmarks, multi-view stacked hourglass convolutional neural networks (MSH-CNN) and to construct three-dimensional facial midsagittal plane automatically based on MSH-CNN and weighted Procrustes analysis algorithm.@*METHODS@#One hundred subjects with no obvious facial deformity were collected in our oral clinic. Three-dimensional facial data were scanned by three-dimensional facial scanner. Experts annotated twenty-one facial landmarks and midsagittal plane of each data. Eighty three-dimensional facial data were used as training set, to train the MSH-CNN in this study. The overview of MSH-CNN network architecture contained multi-view rendering and training the MSH-CNN network. The three-dimensional facial data were rendered from ninety-six views that were fed to MSH-CNN and the output was one heatmap per landmark. The result of the twenty-one landmarks was accurately placed on the three-dimensional facial data after a three-dimensional view ray voting process. The remaining twenty three-dimensional facial data were used as test set. The trained MSH-CNN automatically determined twenty-one three-dimensional facial anatomical landmarks of each case of data, and calculated the distance between each MSH-CNN landmark and the expert landmark, which was defined as position error. The midsagittal plane of the twenty subjects' could be automatically constructed, using the MSH-CNN and Procrustes analysis algorithm. To evaluate the effect of midsagittal plane by automatic method, the angle between the midsagittal plane constructed by the automatic method and the expert annotated plane was calculated, which was defined as angle error.@*RESULTS@#For twenty subjects with no obvious facial deformity, the average angle error of the midsagittal plane constructed by MSH-CNN and weighted Procrustes analysis algorithm was 0.73°±0.50°, in which the average position error of the twenty-one facial landmarks automatically determined by MSH-CNN was (1.13±0.24) mm, the maximum position error of the orbital area was (1.31±0.54) mm, and the minimum position error of the nasal area was (0.79±0.36) mm.@*CONCLUSION@#This research combines deep learning algorithms and Procrustes analysis algorithms to realize the fully automated construction of the three-dimensional midsagittal plane, which initially achieves the construction effect of clinical experts. The obtained results constituted the basis for the independent intellectual property software development.
Subject(s)
Humans , Algorithms , Deep Learning , Face , Neural Networks, Computer , SoftwareABSTRACT
Objective: To investigate the association between the genetic polymorphism of ABCB1 C3435T and plasma concentration and adverse reactions of high-dose methotrexate(HD-MTX) chemotherapy in children with acute lymphoblastic leukemia(ALL).Methods: A total of 70 peripheral blood samples were obtained from the children with acute lymphoblastic leukemia for extracting genome DNA.The genetic polymorphism of ABCB1 C3435T locus was examined by using PCR technology and direct sequencing;enzyme-amplified immunoassay (EMIT) was employed to determine the plasma concentration of MTX in 48 h;the clinical data of patients were collected during the HD-MTX chemotherapy, the adverse reactions were statistically analyzed.The association between ABCB1 C3435T genotypes and MTX plasma concentration and adverse reactions were investigated.Results: Genetic polymorphism existed at the SNP of ABCB1 C3435T.At the SNP of ABCB1 C3435T, the percentage of CC, CT and TT genotype in the children with ALL was 31.43%, 47.14% and 21.43%, respectively.The order of C/D ratio of MTX from low to high was CC, CT and TT genotypes, there was a significant association between the gene polymorphism and the C/D ratio of MTX (P<0.05);the order of incidence of oral mucosa damage from low to high was CC, CT and TT genotypes, there was a significant association between the gene polymorphism and oral mucosa damage (P<0.05);the order of incidence of hepatotoxicity from low to high were CC, CT and TT genotypes, the gene polymorphism and hepatotoxicity had a significant association (P<0.05).Conclusion: ABCB1 C3435T genetic polymorphism and C/D ratio of MTX, gastrointestinal side effects and hepatotoxicity after HD-MTX chemotherapy in the children with ALL exhibit significant association.
ABSTRACT
Objective:To study the antihypertensive effect of the extract from compound Prunella vulgaris L. in spontaneous hy-pertension(SH)rats. Methods:Forty SH rats were randomly divided into the model group,high,middle and low dose groups of ex-tract from vompound Prunella vulgaris L. ,the compound kendir leaves tablets Ⅰ group with 8 ones in each. Non-invasive blood pres-sure measurement was used to detect the SBP and DBP of the SHR rats. Then the serum NO,AngⅡ ,ET-1 and ANP content were measured after the eight-week treatment. The pathological changes were observed after kidney HE staining in the SH rats. Results:Compared with that in the model group,the blood pressure in high-dose treatment group,middle-dose treatment group and the positive model group was significantly decreased(P < 0. 05). The AngⅡ and ET-1 levels in high-dose treatment group,middle-dose treatment group and the positive model group were decreased(P < 0. 01),and NO and ANP contents in serum were significantly increased when compared with those in the model group(P < 0. 01). The pathological examination showed that the pathological changes in the model group were faster than those in all the drug-treatment groups,the pathological changes included glomerular and renal tubular atrophy, glomerular vascular wall thickening and renal tubular epithelial cell degeneration or necrosis. Conclusion:The extract from compound Prunella vulgaris L. can reduce blood pressure of SH rats. The mechanism may be associated with the level reduction of AngII and ET-1 and content elevation of NO and ANP.
ABSTRACT
@# Objective To study the personality characteristics of the stagnation of liver-qi syndrome cases with Minnesota Multiphasic Personality Inventory (MMPI).Methods 20 liver-qi stagnation syndrome cases and 20 normal persons whose paired by sex and age were tested by MMPI. The scores of 13 clinical scales and the section plane of MMPI were acquired and analyzed. Results There was a significant difference in 9 clinical scales (F, Pa, D, Pt, Si, Sc, Hs, Hy, Pd) between the liver-qi stagnation syndrome cases and normal persons ( P<0.05～0.001). The scores of Hs, D, Hy, Pd in the liver-qi stagnation syndrome group were higher than the Chinese normal model. The MMPI section plane of liver-qi stagnation group presented the type of 3/1. Conclusion The patients with liver-qi stagnation have some special personality characteristics such as depression, anxiety, loneliness, indifferent and attention.
ABSTRACT
@#The adhesion molecules expressed by brain microvascular endothelial cell maintain the structure and function of brain, ensure the continuity of endothelium cell and penetrate blood-brain barrier in physiology. They also intervene inflammation cells that remove or orientate regular or inflammation organism in pathology. The adhesion molecules of Immunoglobulin supperfamily and Selectin family are expressed by brain microvascular endothelial cell and have affinity with the ischemic brain damage. The advance in research on relationship between the expression of adhesion molecules by brain microvascular endothelial cell and ischemic brain damage is reviewed in this article.