Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences最新文献_第9页

An automatic COVID-19 CT segmentation based on Progressive encoder and decoder U-Net++ with attention mechanism 基于渐进式编码器和解码器U-Net++的COVID-19 CT自动分割

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570859

Xiaokang Ren, Jianwei Yang

{"title":"An automatic COVID-19 CT segmentation based on Progressive encoder and decoder U-Net++ with attention mechanism","authors":"Xiaokang Ren, Jianwei Yang","doi":"10.1145/3570773.3570859","DOIUrl":"https://doi.org/10.1145/3570773.3570859","url":null,"abstract":"The coronavirus disease (COVID-19) pandemic has contribute to a harsh effect on the global public health. Computed Tomography (CT) is an effective tool in the screening of COVID-19. It is greater important to rapidly and accurately segment COVID-19 from CT to help diagnostic and monitor patients. In this paper, we propose a Progressive encoder and decoder U-Net++ based segmentation network using attention mechanism. In terms of COVID-19 lesion segmentation problems with highly imbalanced dataset and small regions of interests (ROI), we will use a progressive encoder and decoder combined with dilated convolution to form a deeper network structure, which can extract more and lower level semantic features while ensuring spatial information features. We propose to incorporate an attention mechanism to a progressive encoder and decoder U-Net++ architecture to capture rich contextual relationships for better feature representations. Meanwhile, the focal tversky loss is enhanced to address the small lesion segmentation. In addition, after combining the advantages of multiple modules, the network parameters will increase abruptly. According to the performance of the model in the validation set, we cut the redundant branch of the network model to do the final segmentation test, which can not only reduce the segmentation accuracy, but also reduce the network parameters and calculation cost. The experiment results, evaluated on a small dataset where only 3520 CT images are available, prove the enhanced model can achieve an accurate result on COVID-19 segmentation. The obtained Dice Score, Sensitivity and Specificity are 70.1%, 82.1%, and 92.3%, respectively.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122057727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Discussions of Chemical, Biological, and Economic Features of two FDA Authorized Antivirals Against COVID-19: Molnupiravir and Paxlovid FDA批准的两种抗COVID-19抗病毒药物:莫努皮拉韦和Paxlovid的化学、生物学和经济特性的讨论

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570807

Jiaqi Dong

引用次数: 0

A Lightweight Lung Region Image Segmentation Model with Attention Mechanisms 基于注意机制的轻量级肺区域图像分割模型

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570809

Furong Cai, Yingguang Hao, Hongyu Wang

{"title":"A Lightweight Lung Region Image Segmentation Model with Attention Mechanisms","authors":"Furong Cai, Yingguang Hao, Hongyu Wang","doi":"10.1145/3570773.3570809","DOIUrl":"https://doi.org/10.1145/3570773.3570809","url":null,"abstract":"Image segmentation of lung regions is helpful for the diagnosis of lung diseases. The existing lung segmentation networks with high segmentation accuracy face difficulty in leveraging accuracy and speed in practical clinical application platforms due to high computational loads. To address this issue, we propose a lightweight lung segmentation network based on U-Net, which consists of a residual depth-separable module, an attention module, and a multi-receptive field feature fusion module. Depthwise separable convolutions are used to achieve lightweight. To prevent a drop in accuracy, we add a scSE attention module to the encoder to help the model effectively highlight the target area during feature extraction and pay more attention to the foreground pixels. In addition, a lightweight multi-receptive field feature fusion module is designed to alleviate the loss of spatial information caused by pooling and better adapt to the multi-size features of the lung region. The proposed network is evaluated on the Luna16 and the NSCLC-Radiomics datasets. Compared with the standard U-Net model, the proposed model maintains the original accuracy and reduces the number of parameters by 69.3%.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126266318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Convolutional neural network-based image recognition for animals 基于卷积神经网络的动物图像识别

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570832

He Huang

引用次数: 0

Universal CAR-T Generated Using the One-shot CRISPR/Cas9 System as a Replacement for Conventional Patient-specific CAR-T Therapy for B-Cell Acute Lymphoblastic Leukemia 使用一次性CRISPR/Cas9系统生成的通用CAR-T作为b细胞急性淋巴细胞白血病常规患者特异性CAR-T治疗的替代品

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570788

U. H. Chan

{"title":"Universal CAR-T Generated Using the One-shot CRISPR/Cas9 System as a Replacement for Conventional Patient-specific CAR-T Therapy for B-Cell Acute Lymphoblastic Leukemia","authors":"U. H. Chan","doi":"10.1145/3570773.3570788","DOIUrl":"https://doi.org/10.1145/3570773.3570788","url":null,"abstract":"Since the traditional patient-specific CAR-T has an obvious disadvantage of long wait time while universal CAR-T has a risk of graft rejection. This experiment will investigate the safety and efficacy of the enhanced universal CAR-T generated using the one-hit CRISPR/Cas9 system and the traditional CAR-T in humanized-leukemic mice. Mice are first humanized by transplantation of human fetal thymus CD34+ liver cells of two origins. B-ALL cells are extracted from mice transduced with MLL-AF9 fusion gene/GFP-carrying retroviruses. T cells are extracted from mice and anti-CD19 CAR-T are generated by lentiviral transduction. They are transplanted into autologous mice. Other T cells extracted undergo TCR/HLA-I/Fas-triple gene ablation using one-shot CRISPR protocols and transplanted into allogenic mice. Three measurements are taken at day 1, 3, 7, 14, 21, and 28 post-transplantation: anti-CD19 CAR-T serum level by flow cytometry; CD19+GFP+ PBMC serum level by FACS, and acute GVHD-related biomarker expression (IL-2Rα, TNFR-1, IL- 8, HGF) by ELISA assay. There are 8 possible results but only when the universal CAR-grafted mice express a significantly higher serum level of CAR-T and a significant increase in the killing of leukemic cells while showing no indication of graft rejection risk, then would the result support the hypothesis. The experimental design of this study can be used as a reference for future research on universal CAR-T in mice. The results of this experiment provide important insight into the safety and efficacy of universal CAR-T; and aids in the clinical translation of this technology.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134554364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

High Exogenous Cholesterol Level Suppress the HMGCR Expression in MVA Pathway and it's Relationship with Ferroptosis in Colorectal Cancer cell 高外源性胆固醇抑制结直肠癌细胞MVA通路HMGCR表达及其与铁凋亡的关系

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570806

Yang Chen, Minqi Chen, Yijun Chen, Wenjun Mao, Yijing Wang

{"title":"High Exogenous Cholesterol Level Suppress the HMGCR Expression in MVA Pathway and it's Relationship with Ferroptosis in Colorectal Cancer cell","authors":"Yang Chen, Minqi Chen, Yijun Chen, Wenjun Mao, Yijing Wang","doi":"10.1145/3570773.3570806","DOIUrl":"https://doi.org/10.1145/3570773.3570806","url":null,"abstract":"Ferroptosis is a type of programmed cell death that can be regulated in many pathways to interfere with the development of many diseases such as tumors. Based on the recent years study, the mevalonate (MVA) pathway has been discovered to be one of the significant regulatory factors of ferroptosis. In addition, hydroxymethylglutaryl coenzyme A reductase (HMGCR), a crucial regulatory enzyme manipulating the biosynthesis of endogenous cholesterol, found out to be the rate-limiting enzyme of MVA pathway by previous studies. However, despite HMGCR being known to be highly contributing to cholesterol biosynthesis, interplay of MVA pathway and HMGCR expression affected by the cholesterol level remains unexplored. In this research, we focused on colorectal cancer by using HT29 cell line as the target of study and we hypothesize that by increasing the concentration of exogenous cholesterol inhibit HMGCR will lead to the production of inhibitory effect on MVA Pathway. Isopentenyl Pyrophosphate (IPP) is an important product of the MVA Pathway, which the inhibition of MVA Pathway will result in the decrease of IPP production. The decrease of IPP production is impeding Selenocysteine tRNA maturation and downregulating the synthesis of Selenocysteine tRNA, which in turn is affecting Glutathione Peroxidase 4 (GPX4) activity. The GPX4 and Ferroptosis are also closely connected, so if GPX4 is inhibited, Ferroptosis is likely to occur and thus affect the progression of Colorectal cancer. With a more in depth understanding of the mevalonate pathway and its relationship with ferroptosis, it could propose a new target for antitumor treatment development in the future.","PeriodicalId":153475,"journal":{"name":"Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133217496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Construction and Application of Whole Assembly Operating Room in Medical Construction 整体装配手术室在医疗建设中的建设与应用

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570874

Xiwei Li

引用次数: 0

Scheduling with periodic due date to minimize the maximum tardiness in lean production of medical equipment 在医疗设备精益生产中，定期安排交货期，最大限度地减少延误

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570812

Zhouli He, Xiaolong Cui, Hongyu Huang, Long Wan

引用次数: 0

Does OTC inhibited glutamate uptake by GLAST and GLT-1? OTC是否抑制GLAST和GLT-1对谷氨酸的摄取?

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570811

J. Yuan

引用次数: 0

Preparation and evaluation of ginseng whitening and nourishing mask 人参美白滋养面膜的制备与评价

Proceedings of the 3rd International Symposium on Artificial Intelligence for Medicine Sciences Pub Date : 2022-10-13 DOI: 10.1145/3570773.3570785

Rikang Huang, Lingyi Xin, Yan Yang, Zelong Wang, Long Ma, Ying He

引用次数: 0