Histopathological image analysis is the gold standard for pathologists to grade colorectal cancers of different differentiation types. However, the diagnosis by pathologists is highly subjective and prone to misdiagnosis. In this study, we constructed a new attention mechanism named MCCBAM based on channel attention mechanism and spatial attention mechanism, and developed a computer-aided diagnosis (CAD) method based on CNN and MCCBAM, called HCCANet. In this study, 630 histopathology images processed with Gaussian filtering denoising were included and gradient-weighted class activation map (Grad-CAM) was used to visualize regions of interest in HCCANet to improve its interpretability. The experimental results show that the proposed HCCANet model outperforms four advanced deep learning (ResNet50, MobileNetV2, Xception, and DenseNet121) and four classical machine learning (KNN, NB, RF, and SVM) techniques, achieved 90.2%, 85%, and 86.7% classification accuracy for colorectal cancers with high, medium, and low differentiation levels, respectively, with an overall accuracy of 87.3% and an average AUC value of 0.9.In addition, the MCCBAM constructed in this study outperforms several commonly used attention mechanisms SAM, SENet, SKNet, Non_Local, CBAM, and BAM on the backbone network. In conclusion, the HCCANet model proposed in this study is feasible for postoperative adjuvant diagnosis and grading of colorectal cancer.
Objective. To study the expression and clinical importance of CD4+T, CD8+T cells, and CD4+T/CD8+T cell percentage in gastric cancer (GC) patients. Methods. The blood count of CD4+T and CD8+T lymphocytes was ascertained via flow cytometry before surgery in 93 GC patients undergoing gastrectomy. The CD4+T, CD8+T, and Foxp3+T lymphocytes in cancerous and normal adjacent tissues and the presence of PD-L1 in cancerous tissues were detected via immunohistochemistry. The link between the permeation of CD4+T, CD8+T lymphocytes in venous blood, and cancer and normal adjacent tissues was analyzed. Results. Lauren histotype, TNM stage, lymphatic/nervous invasion, and NLR level were all considerably associated with peripheral CD4+T and CD8+T cell levels, whereas CD8+T lymphocytes were also associated with vascular invasion ( p < 0.05 ). The CD4+T lymphocyte counts, CD4+T, and CD8+T cell percentage in GC tissues were found to have been decreased when compared to normal adjacent tissues, whereas the CD8+T and Foxp3+T lymphocyte count was higher in GC tissues ( p < 0.05 ). According to a Spearman analysis, the CD4+T and CD8+T cell counts in tumor tissues were positively related to the Foxp3+T lymphocyte count ( p < 0.05 ). Greater peripheral CD4+T lymphocyte counts and increased level of CD4+T/CD8+T percentage corresponded with greater CD4+T cell levels and increased CD4+T/CD8+T quantity in normal adjacent tissues. Higher levels of peripheral CD8+T cells corresponded with higher quantities of CD8+T cells in cancer tissues. A reduced CD4+T lymphocyte count, together with a reduced CD4+T/CD8+T percentage in venous blood, was consistent with a diminished CD4+T cell count along with a reduced CD4+T/CD8+T lymphocyte ratio in cancer and normal adjacent tissues. Conclusion. The peripheral quantity of CD4+T and CD8+T lymphocytes in GC patients can partly reflect the infiltrating state of these lymphocytes in cancer and normal adjacent tissues and can preliminarily predict immunotherapy response to a certain extent.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.