Objective To observe the expression levels of nuclear factor kappa B （NF-κB）， vascular endothelial growth factor （VEGF）， and CD31 in portal vein and surrounding tissues of rats during the formation process of cavernoustransformation of portal vein （CTPV）， and try to search the relationship between NF-κB， VEGF， and the angiogenesisof portal areas， as well as the significance and the role of NF-κB and VEGF in the formation process of CTPV. Methods One hundred and ten Sprague-Dawley （SD） rats were randomly （random number method） divided into sham operation group and model group. The partial constriction operations on portal vein were performed in model rats with a blunt 21Gcaliber to establish CTPV animal models （model group）， while the exploratory operations on portal vein， not constriction，were performed in rats of sham operation group. All specimens （portal vein and surrounding tissues） were fixed in formalinand made into paraffin blocks. Each specimen was tested by immunohistochemistry for the expressions of NF-κB， VEGF， and CD31， then optical density （OD） of NF-κB expression and the mean integral optical density （IOD） of VEGF expressionwere measured by using Image Pro Plus 6.0 software， and microvessel density （MVD） was calculated under microscope. Results Nucleoplasm ratio of OD value of NF-κB， mean IOD value of VEGF， and MVD value in 1， 2， 3， 4， and 6 weeks after operation didn’t significantly differed from that of before operation in sham operation group （P＞0.05）， but higher at all time points after operation in model group （P＜0.01）. Compared with sham operation group， nucleoplasm ratio of OD value of NF-κB， mean IOD value of VEGF， and MVD value were significantly higher in 1， 2， 3， 4， and 6 weeks after operation in model group （P＜0.01）. NF-κB and VEGF， NF-κB and MVD， VEGF and MVD were positively correlated with each other （r=0.654 6，P＜0.01；r=0.620 7， P＜0.01；r=0.636 9， P＜0.01） in model group. Conclusion NF-κB and VEGF may relate to the formation of CTPV， and may involve in the angiogenesis.
Traditional biomedical data analysis technology faces enormous challenges in the context of the big data era. The application of deep learning technology in the field of biomedical analysis has ushered in tremendous development opportunities. In this paper, we reviewed the latest research progress of deep learning in the field of biomedical data analysis. Firstly, we introduced the deep learning method and its common framework. Then, focusing on the proposal of biomedical problems, data preprocessing method, model building method and training algorithm, we summarized the specific application of deep learning in biomedical data analysis in the past five years according to the chronological order, and emphasized the application of deep learning in medical assistant diagnosis. Finally, we gave the possible development direction of deep learning in the field of biomedical data analysis in the future.