BACKGROUND Colorectal cancer(CRC)is a prevalent global malignancy with complex prognostic factors.Tumor-associated macrophages(TAMs)have shown paradoxical associations with CRC survival,particularly concerning the M2 ...BACKGROUND Colorectal cancer(CRC)is a prevalent global malignancy with complex prognostic factors.Tumor-associated macrophages(TAMs)have shown paradoxical associations with CRC survival,particularly concerning the M2 subset.AIM We aimed to establish a simplified protocol for quantifying M2-like TAMs and explore their correlation with clinicopathological factors.METHODS A cross-sectional study included histopathological assessment of paraffinembedded tissue blocks obtained from 43 CRC patients.Using CD68 and CD163 immunohistochemistry,we quantified TAMs in tumor stroma and front,focusing on M2 proportion.Demographic,histopathological,and clinical parameters were collected.RESULTS TAM density was significantly higher at the tumor front,with the M2 proportion three times greater in both zones.The tumor front had a higher M2 proportion,which correlated significantly with advanced tumor stage(P=0.04),pathological nodal involvement(P=0.04),and lymphovascular invasion(LVI,P=0.01).However,no significant association was found between the M2 proportion in the tumor stroma and clinicopathological factors.CONCLUSION Our study introduces a simplified protocol for quantifying M2-like TAMs in CRC tissue samples.We demonstrated a significant correlation between an increased M2 proportion at the tumor front and advanced tumor stage,nodal involvement,and LVI.This suggests that M2-like TAMs might serve as potential indicators of disease progression in CRC,warranting further investigation and potential clinical application.展开更多
Many existing intelligent recognition technologies require huge datasets for model learning.However,it is not easy to collect rectal cancer images,so the performance is usually low with limited training samples.In add...Many existing intelligent recognition technologies require huge datasets for model learning.However,it is not easy to collect rectal cancer images,so the performance is usually low with limited training samples.In addition,traditional rectal cancer staging is time-consuming,error-prone,and susceptible to physicians’subjective awareness as well as professional expertise.To settle these deficiencies,we propose a novel deep-learning model to classify the rectal cancer stages of T2 and T3.First,a novel deep learning model(RectalNet)is constructed based on residual learning,which combines the squeeze-excitation with the asymptotic output layer and new cross-convolution layer links in the residual block group.Furthermore,a two-stage data augmentation is designed to increase the number of images and reduce deep learning’s dependence on the volume of data.The experiment results demonstrate that the proposed method is superior to many existing ones,with an overall accuracy of 0.8583.Oppositely,other traditional techniques,such as VGG16,DenseNet121,EL,and DERNet,have an average accuracy of 0.6981,0.7032,0.7500,and 0.7685,respectively.展开更多
文摘BACKGROUND Colorectal cancer(CRC)is a prevalent global malignancy with complex prognostic factors.Tumor-associated macrophages(TAMs)have shown paradoxical associations with CRC survival,particularly concerning the M2 subset.AIM We aimed to establish a simplified protocol for quantifying M2-like TAMs and explore their correlation with clinicopathological factors.METHODS A cross-sectional study included histopathological assessment of paraffinembedded tissue blocks obtained from 43 CRC patients.Using CD68 and CD163 immunohistochemistry,we quantified TAMs in tumor stroma and front,focusing on M2 proportion.Demographic,histopathological,and clinical parameters were collected.RESULTS TAM density was significantly higher at the tumor front,with the M2 proportion three times greater in both zones.The tumor front had a higher M2 proportion,which correlated significantly with advanced tumor stage(P=0.04),pathological nodal involvement(P=0.04),and lymphovascular invasion(LVI,P=0.01).However,no significant association was found between the M2 proportion in the tumor stroma and clinicopathological factors.CONCLUSION Our study introduces a simplified protocol for quantifying M2-like TAMs in CRC tissue samples.We demonstrated a significant correlation between an increased M2 proportion at the tumor front and advanced tumor stage,nodal involvement,and LVI.This suggests that M2-like TAMs might serve as potential indicators of disease progression in CRC,warranting further investigation and potential clinical application.
基金supported in part by the National Natural Science Foundation of China under Grants 62172192,U20A20228,and 62171203in part by the 2018 Six Talent Peaks Project of Jiangsu Province under Grant XYDXX-127in part by the Science and Technology Demonstration Project of Social Development of Jiangsu Province under Grant BE2019631.
文摘Many existing intelligent recognition technologies require huge datasets for model learning.However,it is not easy to collect rectal cancer images,so the performance is usually low with limited training samples.In addition,traditional rectal cancer staging is time-consuming,error-prone,and susceptible to physicians’subjective awareness as well as professional expertise.To settle these deficiencies,we propose a novel deep-learning model to classify the rectal cancer stages of T2 and T3.First,a novel deep learning model(RectalNet)is constructed based on residual learning,which combines the squeeze-excitation with the asymptotic output layer and new cross-convolution layer links in the residual block group.Furthermore,a two-stage data augmentation is designed to increase the number of images and reduce deep learning’s dependence on the volume of data.The experiment results demonstrate that the proposed method is superior to many existing ones,with an overall accuracy of 0.8583.Oppositely,other traditional techniques,such as VGG16,DenseNet121,EL,and DERNet,have an average accuracy of 0.6981,0.7032,0.7500,and 0.7685,respectively.
