ABSTRACT
Objective@#To evaluate the feasibility and accuracy of deep learning in CT image segmentation and further lesion-volume assessment of spontaneous intracerebral hemorrhage.@*Methods@#A total of 1 223 cases of spontaneous intracerebral hemorrhage including parenchymal hemorrhage, ventricular hemorrhage, subarachnoid hemorrhage and mixture hemorrhage, from April 2016 to April 2018 in Tianjin Medical University General Hospital, were retrospectively enrolled and analyzed. The patients were randomly divided into training set (905 cases), validation set (156 cases) and test set (162 cases), among each group, the number of parenchymal hemorrhage was 498, 107 and 100, respectively. The bleeding area manually outlined by physician was served as the reference standard to build the segmentation model and to evaluate the performance of the validation set. Patients were divided into 3 groups according to the volume calculated by reference standard. The volume of hematoma in group 1 was less than 5 ml, while group 2 was 5-25 ml, and group 3 was more than 25 ml. Comparison of the hematoma volume calculated by segmentation model and that calculated by ABC/2 formula was conducted in 97 simple intraparenchymal hemorrhage cases.@*Results@#In 162 cases of test set, the Dice coefficients of the segmentation model were 0.87, 0.85, 0.67 and 0.77 in parenchymal hemorrhage, intraventricular hemorrhage, subarachnoid hemorrhage and mixture hemorrhage, respectively. The estimated hematoma volume in the 97 intraparenchymal hemorrhage cases calculated by the segmentation model was (29.55±37.69) ml, and that calculated by the ABC/2 formula was (24.04±31.22) ml. Compared with reference standard, the absolute errors of three segmentation model were (0.52±0.54), (1.53±1.22) and (7.93±8.49) ml in group 1, 2 and 3 respectively. The absolute errors of the ABC/2 formula were (0.68±0.60), (3.16±2.90) and (19.31±17.23) ml in group 1, 2 and 3.@*Conclusion@#Deep learning based segmentation model improved detection of intraparenchymal hematoma volume, compared with ABC/2 formula.
ABSTRACT
Na +-K +-2Cl-cotransporter 1 (NKCC1) is highly expressed in malignant gliomas,which is closely related to the degree of malignancy.NKCC1 protein has a vital function in the volume regulation of glioma cells.NKCC1 allows glioma cells to transform its volume freely,migrating through the narrow extracellular space to achieve distant metastases.There is also close relationship between NKCC1 and tumor cytoskeleton regulation.In addition,NKCC1 is closely associated with cell cycle,nerve activity and other biological functions.In conclusion,NKCC1 plays an important role in gliomas.
ABSTRACT
Objective To investigate the inhibitory effect of a disintegrin and metalloprotease 12 silenced by shR?NA on self-renewal capacity of CD133 positive giloma cells. Methods The shRNA recombinant lentivirus aimed at si?lencing ADAM12 was prepared. Human glioma cells U87 were employed in this study and assigned into three groups:shRNA-ADAM12, shRNA-NCandshRNA-C. ADAM12 expression was detected at mRNA and protein level using Re?al-time quantitative-PCR and western bloting, respectively. U87 cells were cultured with stem cell culture medium, to obtain cell sphere formation in which CD133 positive glioma cells were enriched. Immunofluorescence was employed to detect the expression of ADAM12 and CD133 in cell spheres and U87 cells; Self-renewal was tested by using tumor sphere formation assay. Molecular markers for differentiated or undifferentiated cells (CD133,GFAP and Tuj1) were de?tected at protein using western blotting. Western blotting was employed to test protein expression of HES1. Results AD?AM12 shRNA significantly down-regulated the mRNA and protein expression levels of ADAM12. Compared with shRNA–C group, the relative expression levels of mRNA in shRNA-ADAM12 group and shRNA-NC group were 0.22 ± 0.03 and 0.98 ± 0.06 (F=425.37,P<0.01). The relative expression levels of protein in shRNA-ADAM12 group, shRNA-NC group and shRNA-C group were 28.72%±2.36%, 69.21%±3.92%and 69.04%±3.57%, respectively (F=145.42,P<0.01). Immunofluorescence staining showed that expression levels of ADAM12 and CD133 in cell spheres were significantly higher than those in normal cells. The number of spheres in three groups were 45.5±2.3、104.2±5.8 and 109.6±6.2, tumor sphere formation ability of shRNA-ADAM12 group was lower than that of shRNA-NC group and shRNA-C group (F=147.03,P<0.01). Compared with the shRNA-NC group and shRNA-C group, the protain expression of GFAP and Tuj1 were increased up to 166% and 146% (P<0.01) whereas the protein expression levels of CD133 and HES1 were down-regulated by 54% and 50% (P<0.01). Conclusion Knockdown of ADAM12 may suppress self-renewal ability of CD133 positive glioma cells by inhibiting the Notch pathway activity.
ABSTRACT
Objective To investigate the effects of siRNA-mediated knockdown of S100A4 expression on the inva?sion and migration of SNB19 glioma cells. Methods The S100A4 expression was knockdowned using S100A4 siRNA in SNB19 glioma cells. Glioma cells were assigned into control group,siRNA-negative control treated group (siRNA-NC) and siRNA-S100A4 group. RT-PCR and western blot were used to detect the mRNA and protein expression of S100A4, respectively. The wound-healing assay and transwell invasion assay were used to determine the ability of migration and invasion of SNB19 glioma cells, respectively. The expression of matrix metalloproteinase 9 (MMP-9), matrix metallopro?teinase 2 (MMP-2) and E-cadherin proteins were evaluated by using western blot. Moreover, the morphology of lamellipo?dia of glioma cells were examined by using inverted phase-contrast microscopy. Results The mRNA and protein expres?sion levels of S100A4 was obviously down-regulated after transfection of S100A4 siRNA. Compared with control group, the mRNA expression levels of S100A4 in siRNA-NC group and siRNA-S100A4 group were 0.97±0.07 and 0.21±0.04,respectively(P<0.01). The protein expression levels of S100A4 in control, siRNA-NC and siRNA-S100A4 groups were 78.12%±2.63%, 77.16%±3.00%and 37.95%±2.71%, respectively(P<0.01). The migration and invasiveness capability were decreased up to 46% and 55% in the siRNA-S100A4 group compared with the control group(P<0.01). The pro?tein expression levels of MMP-9 and MMP-2 were inhibited up to 62% and 68%(P<0.01)whereas the expression of E-cadherin was increased up to 154%(P<0.01)in the siRNA-S100A4 group. The lamellipodia became smaller or unex?tended in siRNA-S100A4-treated SNB19 glioma cells. Conclusion S100A4 plays an important role in the invasion and migration of glioma cells, suggesting that S100A4 might be a potential candidate for anti-glioma strategy to prevent the invasion and migration of glioma cells.