Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences最新文献

{"title":"Intelligent Skin Cancer Detection System Based on Convolutional Neural Networks","authors":"Yurui Li, Du Wang, Zhaoyun Xu, Ziyu Zhao","doi":"10.1145/3500931.3500965","DOIUrl":"https://doi.org/10.1145/3500931.3500965","url":null,"abstract":"Skin cancer is one of the most threatening types of cancer and has been rising over the past decade. Traditional skin detection methods can be time-consuming and inefficient. Convolutional neural network (CNN) is a powerful autonomous feature extraction method with high accuracy in diagnosing skin cancer. However, most existing skin cancer detection approaches based on CNN only consider a single model and lack intelligent communication. To address this problem, this paper proposes a skin cancer detection system using three CNNs to provide fast, accurate, intelligent, and diversified detection and provide feedback. The three CNNs used in this paper are VGG16, MobileNet and Inception_resnet_v2. Our System consists of three main components, Skin Image Analysis Module, Medical Chatbot Module, and UI Web Module. In Skin Image Analysis Module, we implement the skin cancer detection function of two types: classifying malign moles and benign moles and classifying 7 classes of Skin lesions. In Medical Chatbot Module, the function of online consultation between users and virtual doctors is realized. In UI Web Module, we provide functionalities including uploading their image of moles for detection. VGG16, MobileNet, and Inception_resnet_v2's accuracies and transfer learning techniques are used on ISIC, and HAM1000 datasets are 0.88, 0.90, and 0.93, respectively. Our system can allow users to upload an image of their mole, chat with a virtual assistant, and receive timely and reliable test results, thereby improving the survival rate of potential patients.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"208 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131544410","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}

{"title":"Based on the network pharmacology to explore the micro-mechanism of Maziren Pill in the treatment of senile functional constipation","authors":"Yaoyao Shen, Xiuhong Yang, Yan-Hua Wu, Lili Nie","doi":"10.1145/3500931.3500984","DOIUrl":"https://doi.org/10.1145/3500931.3500984","url":null,"abstract":"Mazieren pill is a classic prescription for the treatment of senile functional constipation, but its molecular mechanism is not clear. This study aims to explore the micro-mechanism of Maziren Pill in the treatment of senile functional constipation by network pharmacology. First, the active components and targets of Dahuang, Maziren, Xingren, Zhishi, Baishao, and Houpu were searched by TCMSP; The disease targets of senile functional constipation were collected by the GeneCards database, and the main component targets of Maziren Pill and disease targets were crossed to obtain the efficacy target point. Then the Cytoscape 3.8 software was used to construct the drug-active component-target interaction network of Maziren pill in the treatment of senile functional constipation, and PPI protein interaction network was constructed and topological analysis was performed carried on. And then GO and KEGG enrichment analysis was performed using R software. As a result, we screened 48 active ingredients and 201 targets of the Maziren pill, including 46 active ingredients and 97 targets of the Maziren pill in the treatment of senile functional constipation. Proteins in the PPI protein interaction core network were MMP2, MAPK1, AKT1, VEGFA, MAPK8, MMP9, EGFR, MYC, TP53, BCL2L1, MAPK3, CASP3, EGF, PTGS2, JUN, MAPK14. GO and KEGG pathway enrichment analysis showed that they were mainly involved in the reaction to toxic substances, the reaction to oxygen level, the process of oxidative stress, the metabolic process of organic hydroxyl compounds, the reaction of cells to nitrogen compounds, and the circadian process. The MAPK signaling pathway, AGE-RAGE signaling pathway, p53 signaling pathway, NF-kB signaling pathway, JAK-STAT signaling pathway, and bile release pathway were regulated in the complications of diabetes. This study preliminarily identified the main pathways and targets related to Maziren Pill in the treatment of senile functional constipation, and laid the foundation for further exploration of its pharmacological effects in the future.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"8 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125655708","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}

{"title":"Application and Innovation of Five Elements Music Therapy in the Era of Artificial Intelligence","authors":"M. Yuan, Zhibing Zhong, Yi He","doi":"10.1145/3500931.3500955","DOIUrl":"https://doi.org/10.1145/3500931.3500955","url":null,"abstract":"With the transformation of medical model and the promotion of the construction of healthy China, continuing to follow the traditional development model has been unable to meet the health needs of the new era. As early as the 1970s, traditional Chinese medicine tried to connect with artificial intelligence technology to seek a breakthrough in the development model of traditional Chinese medicine. In the new round of scientific and technological revolution and industrial reform, artificial intelligence, as an important driving force, presents new characteristics such as deep learning, cross-border integration and man-machine cooperation, which is more conducive to the organic combination with traditional Chinese medicine. As a traditional Chinese medicine therapy, the five elements music therapy, with its unique pertinence, can make the five tones and the five internal organs reach a harmonious resonance state when the patients listen, and make the body resonate, so as to smooth the spirit and express their feelings. Five elements music therapy has achieved great results in clinical psychotherapy, and through the combination with artificial intelligence, five elements music therapy can be presented to patients in a closer way. This paper aims to explore the development of this innovative way.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121315472","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}

{"title":"An Intelligent Question-Answering System for Myopia Prevention and Control based on Knowledge Graph","authors":"Yue Sun, Yuxuan Li, Bo Zheng, Shaojun Zhu, Maonian Wu","doi":"10.1145/3500931.3500947","DOIUrl":"https://doi.org/10.1145/3500931.3500947","url":null,"abstract":"China is facing a serious visual health crisis, especially the trend of high incidence of myopia and low age. The Chinese government pays special attention to the vision health of young people. The prevention and treatment of myopia in children and adolescents has become a public health issue of general concern. In order to further promote the prevention and control of myopia and the management of vision health, this research actively tracks social hot issues, expounding the construction process of the knowledge graph from the three aspects of knowledge acquisition, knowledge fusion, knowledge storage and visualization. Based on the knowledge graph, design intelligent question-answering robots, in-depth research on user intentions, and realize knowledge retrieval and utilization. The intelligent question answering application related to myopia prevention and control proposed in this article can provide references for researchers in related fields.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129921620","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}

{"title":"Optic Disc Segmentation Based on Phase-fusion PSPNet","authors":"Xinwen Fang, Yifan Shen, Bo Zheng, Shaojun Zhu, Maonian Wu","doi":"10.1145/3500931.3500959","DOIUrl":"https://doi.org/10.1145/3500931.3500959","url":null,"abstract":"In the analysis of fundus images, optic disc segmentation is vital to judge eye diseases such as diabetic retinopathy and glaucoma. Improving the accuracy of optic disc segmentation is of great significance to the diagnosis of the above diseases. Based on the PSPNet model, the Phase-Fusion PSPNet network structure is proposed. The network is connected to the phase upsampling module after the pyramid pooling module, which reduces information loss and makes the network suitable for segmentation tasks with fuzzy edges. The principle of phase upsampling module is to upsample the larger size span step by step and combine it with the corresponding size feature map. iChallenge-PM, iChallenge-AMD, and iChallenge-GON as the training and validation datasets in the paper. The IoU and PA of Phase-fusion PSPNet are 89.93% and 94.94%. Compared with PSPNet, the IoU and PA increased by 1.22% and 1.62% respectively. Experiments show that adding the phase upsampling module makes the model have a better segmentation performance.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"277 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114413697","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}

{"title":"UoL-XJTLU students' Knowledge, Attitude and Practice for the anti-COVID-19 policies of UK and China","authors":"Heyi Zhang, Siqi Li, Yu-Yao He, You-Sin Liang","doi":"10.1145/3500931.3500946","DOIUrl":"https://doi.org/10.1145/3500931.3500946","url":null,"abstract":"COVID-19 was the most serious health emergency in 2020, and now it has become a global public health problem. The high infectivity of COVID-19 makes controlling its prevalence an important measure to contain its further development. In view of the fact that both China and the UK have taken measures to curb the prevalence of the COVID-19, we prepared a questionnaire entitled \"UoL-XJTLU students' Knowledge, Attitude and Practice for the anti-COVID-19 policies of the UK and China\" based on the KAP model, and the UOL-XJTlU students who experienced the epidemic policies of China and Britain at the same time, was interviewed by this online questionnaire to understand their views on different policies and measures between China and the UK.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114934230","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}

{"title":"Dependence of neurons mortality on synaptogenesis in conditional mutant mice models","authors":"Shu Yang","doi":"10.1145/3500931.3501028","DOIUrl":"https://doi.org/10.1145/3500931.3501028","url":null,"abstract":"Neurons originate from stem cells. Adult neurogenesis continuously occurs in specific areas of the rostral lateral ventricles and the hippocampus. Microglia is an essential components of the normal hippocampus as it can remove and kill damaged cells and infections through phagocytosis to help hippocampal neurons to stay homeostasis. Internal and external stimuli can trigger different responses from microglia. Inhibition of neuron firing would disrupt neuron function like synapse formation and synaptic function, which would increase microglia activity, and cause more neurons to be removed. In this work, hM4Di conditional mutant mice models were used to study the dependence of neuron mortality on synaptogenesis. CNO was injected to the mice to activate the hM4Di G protein-coupled receptor to trigger inhibition of neuron firing. This work made a contribution to discover the relationship of neuron mortality and synaptogenesis, which may provide a new strategy to find a therapy to cure Alzheimer's disease and depression.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134130302","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}

{"title":"Entity Pair Recognition using Semantic Enrichment and Adversarial Training for Chinese Drug Knowledge Extraction","authors":"Feng Gao, Lunsheng Zhou, J. Gu","doi":"10.1145/3500931.3500939","DOIUrl":"https://doi.org/10.1145/3500931.3500939","url":null,"abstract":"Existing knowledge extraction methods in pharmacy often use natural language processing tools and deep learning model to identify drug entities and extract their relationships from drug instructions, thus obtaining drug-drug or drug-disease knowledge. However, sentences in drug instructions may contain multiple drug-related entities, and existing methods lack the capability of identifying valid the \"drug-drug\" or \"drug-disease\" entity pairs. This will introduce significant noise data in the subsequent tasks such as entity relationship extraction and knowledge graph construction. Meanwhile, some mentions in the sentence can have hierarchical relations even if they do not form valid entity pairs, such information is also crucial to knowledge extraction. To solve these two problems, this paper proposes an entity pair verification model based on entity semantic enhancement and adversarial training. Through the experiment on more than 2000 kinds of drug instructions data, the experimental results show that the F1 value of the model for entity pair verification is up to 98.65%, which is up to 9.37% compared with the existing methods.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134602333","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}

{"title":"How the Medicine Works for Treat the Depression: Prozac and Ketamine","authors":"Xiangke Zhang","doi":"10.1145/3500931.3500989","DOIUrl":"https://doi.org/10.1145/3500931.3500989","url":null,"abstract":"This article focuses on depression and its medication. It contains the history of depression as defined. Serotonin (5-HT), norepinephrine (NE), and dopamine are noted to cause depression. The impact of depression on society, a large number of patients with depression make depression have to be taken seriously. The number of drugs available to treat depression and the history of prozac, ketamine. The chemical mechanism and drug mechanism of prozac and ketamine were investigated. Since ketamine is a new drug defined to treat depression, much of its mechanism is unclear. At the end of the article, the economics of the two drugs are explained.","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123488514","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}

{"title":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","authors":"","doi":"10.1145/3500931","DOIUrl":"https://doi.org/10.1145/3500931","url":null,"abstract":"","PeriodicalId":364880,"journal":{"name":"Proceedings of the 2nd International Symposium on Artificial Intelligence for Medicine Sciences","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126134269","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}