The novel coronavirus outbreak has spread worldwide, causing respiratory infections in humans, leading to a huge global pandemic COVID-19. According to World Health Organization, the only way to curb this spread is by increasing the testing and isolating the infected. Meanwhile, the clinical testing currently being followed is not easily accessible and requires much time to give the results. In this scenario, remote diagnostic systems could become a handy solution. Some existing studies leverage the deep learning approach to provide an effective alternative to clinical diagnostic techniques. However, it is difficult to use such complex networks in resource constraint environments. To address this problem, we developed a fine-tuned deep learning model inspired by the architecture of the MobileNet V2 model. Moreover, the developed model is further optimized in terms of its size and complexity to make it compatible with mobile and edge devices. The results of extensive experimentation performed on a real-world dataset consisting of 2482 chest Computerized Tomography scan images strongly suggest the superiority of the developed fine-tuned deep learning model in terms of high accuracy and faster diagnosis time. The proposed model achieved a classification accuracy of 96.40%, with approximately ten times shorter response time than prevailing deep learning models. Further, McNemar’s statistical test results also prove the efficacy of the proposed model.
Immunotherapies such as checkpoint blockade therapies are known to enhance anti-melanoma CD8+ T cell immunity, but only a fraction of patients treated with these therapies achieve durable immune response and disease control. It may be that CD8+ T cells need help from other immune cells to generate effective and long-lasting anti-tumor immunity or that CD8+ T cells alone are insufficient for complete tumor regression and cure. Melanoma contains significant numbers of B cells; however, the role of B cells in anti-melanoma immunity is controversial. In this study, B16 melanoma mouse models were used to determine the role of B cells in anti-melanoma immunity. C57BL/6 mice, B cell knockout (KO) C57BL/6 mice, anti-CD19, and anti-CXCL13 antibody-treated C57BL/6 mice were used to determine treatment efficacy and generation of tumor-specific CD8+ T cells in response to PD-L1 blockade alone or combination with TLR-7/8 activation. Whole transcriptome analysis was performed on the tumors from B cell depleted and WT mice, untreated or treated with anti-PD-L1. Both CD40-positive and CD40-negative B cells were isolated from tumors of TLR-7/8 agonist-treated wild-type mice and adoptively transferred into tumor-bearing B cell KO mice, which were treated with anti-PD-L1 and TLR-7/8 agonist. Therapeutic efficacy was determined in the presence of activated or inactivated B cells. Microarray analysis was performed on TLR-7/8-treated tumors to look for the B cell signatures. We found B cells were required to enhance the therapeutic efficacy of monotherapy with anti-PD-L1 antibody and combination therapy with anti-PD-L1 antibody plus TLR-7/8 agonist. However, B cells were not essential for anti-CTLA-4 antibody activity. Interestingly, CD40-positive but not CD40-negative B cells contributed to anti-melanoma immunity. In addition, melanoma patients’ TCGA data showed that the presence of B cell chemokine CXCL13 and B cells together with CD8+ T cells in tumors were strongly associated with improved overall survival. Our transcriptome data suggest that the absence of B cells enhances immune checkpoints expression in the tumors microenvironment. These results revealed the importance of B cells in the generation of effective anti-melanoma immunity in response to PD-1-PD-L1 blockade immunotherapy. Our findings may facilitate the design of more effective anti-melanoma immunotherapy.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.