RESUMO
Objective:To investigate the effects of deep learning-based AiContour ??versus atlas-based Raystation ?? automatic contouring methods on the contouring of organs-at-risk on CT images of patients with rectal cancer who undergo radiotherapy, providing evidence for clinical application. Methods:Fifty patients with rectal cancer who received treatment during January to June 2020 in Zhejiang Provincial People's Hospital (Affiliated Hospital of Hangzhou Medical College) were included in this study. The CT images from 20 patients with rectal cancer that had been contoured by experienced radiotherapist were selected as target images and automatically contoured using the data template library of AiContour ?? and Raystation ?? automatic contouring methods. Hausdorff distance, mean distance to agreement, dice similarity coefficient, Jaccard coefficient were used to quantitatively evaluate the accuracy of the volume of contour of organs-at-risk automatically sketched by the two methods. Results:There was no significant difference in Hausdorff distance in left femoral head [(6.81 ± 2.66) vs. (7.24 ± 2.10)], right femoral head [(7.38 ± 3.91) vs. (8.14 ± 3.71)], pelvis [(24.00 ± 9.01) vs. (24.66 ± 9.67)] between AiContour ?? and Raystation ?? automatic contouring methods ( tleft femoral head = -0.831, tright femoral head = -0.821, tpelvis = -0.357, all P > 0.05). Significant differences were observed in mean distance to agreement, dice similarity coefficient and Jaccard coefficient of organs-at-risk (all P < 0.05). The mean values of dice similarity coefficient automatically sketched by AiContour ?? method were > 0.7. The DSC of left kidney, right kidney, rectum and bladder automatically sketched by Raystation ?? method were < 0.7, and the dice similarity coefficient values of other organs-at-risk automatically sketched by Raystation ?? method were > 0.7. In addition, Hausdorff distance, mean distance to agreement and Jaccard coefficient values of organs-at-risk automatically sketched by AiContour ?? method were superior to those automatically sketched by Raystation ??. Conclusion:After slight modification, the organs-at-risk automatically sketched by AiContour ?? and Raystation ?? methods can meet clinical requirement. The contouring effects provided byAiContour ?? method were superior to those provided by Raystation ?? method.
RESUMO
This study investigated the changes of CD4(+) CD25(+) regulatory T cells (Tregs) in peripheral blood of patients with hepatocellular carcinoma before and after transcatheter arterial chemoembolization (TACE). The proportion of CD4(+) CD25(+) Tregs among CD4(+) T lymphocytes in peripheral blood of 33 patients with hepatocellular carcinoma was determined by flow cytometry before, 1 week and 1 month after TACE. And 25 healthy volunteers served as control. One month after TACE, the patients were divided into two groups: 22 in group A, who were in stable condition or getting better; and 10 in group B, who were deteriorating. One patient died and was excluded. The results showed that the percentage of CD4(+)CD25(+) Tregs among CD4(+) T lymphocytes did not significantly change in the 33 patients 1 week after TACE as compared with that before TACE, however, the difference was significant (P<0.01) between the patients with hepatocellular carcinoma and the healthy subjects. The percentage of CD4(+) CD25(+) Tregs among CD4(+) T lymphocytes in group A 1 month after TACE was decreased significantly in comparison with that before and 1 week after TACE (P<0.01), whereas, that in group B was increased significantly 1 month after TACE (P<0.01). It was concluded that patients with hepatocellular carcinoma had a higher proportion of CD4(+)CD25(+) Tregs in peripheral blood. TACE did not significantly affect the level of CD4(+) CD25(+) Tregs within short time (such as 1 week). The proportion of CD4(+)CD25(+) Tregs in peripheral blood 1 month after TACE was related to the prognosis of hepatocellular carcinoma.