With recent advances in supervised machine learning for medical image analysis applications, the annotated medical image datasets of various domains are being shared extensively. Given that the annotation labelling requires medical expertise, such labels should be applied to as many learning tasks as possible. However, the multi-modal nature of each annotated image renders it difficult to share the annotation label among diverse tasks. In this work, we provide an inductive transfer learning (ITL) approach to adopt the annotation label of the source domain datasets to tasks of the target domain datasets using Cycle-GAN based unsupervised domain adaptation (UDA). To evaluate the applicability of the ITL approach, we adopted the brain tissue annotation label on the source domain dataset of Magnetic Resonance Imaging (MRI) images to the task of brain tumor segmentation on the target domain dataset of MRI. The results confirm that the segmentation accuracy of brain tumor segmentation improved significantly. The proposed ITL approach can make significant contribution to the field of medical image analysis, as we develop a fundamental tool to improve and promote various tasks using medical images.
{"title":"An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation","authors":"Y. Tokuoka, Shuji Suzuki, Yohei Sugawara","doi":"10.1145/3375923.3375948","DOIUrl":"https://doi.org/10.1145/3375923.3375948","url":null,"abstract":"With recent advances in supervised machine learning for medical image analysis applications, the annotated medical image datasets of various domains are being shared extensively. Given that the annotation labelling requires medical expertise, such labels should be applied to as many learning tasks as possible. However, the multi-modal nature of each annotated image renders it difficult to share the annotation label among diverse tasks. In this work, we provide an inductive transfer learning (ITL) approach to adopt the annotation label of the source domain datasets to tasks of the target domain datasets using Cycle-GAN based unsupervised domain adaptation (UDA). To evaluate the applicability of the ITL approach, we adopted the brain tissue annotation label on the source domain dataset of Magnetic Resonance Imaging (MRI) images to the task of brain tumor segmentation on the target domain dataset of MRI. The results confirm that the segmentation accuracy of brain tumor segmentation improved significantly. The proposed ITL approach can make significant contribution to the field of medical image analysis, as we develop a fundamental tool to improve and promote various tasks using medical images.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91098939","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}
Upper limb movements of human arms are natural behaviors which require both the spatial and temporal coordination of multiple muscles. We now investigate how the neural strategy control upper limb movements in the human movement control. These upper limb movements include abduction, adduction, shoulder flexion and shoulder extension. According to our research, we make a hypothesis that a few muscle synergies across different subjects may have similar properties. To validate this hypothesis, we collected and analyzed EMG data in six healthy subjects. Nine muscles were required to reproduce the movement of each subjects. We used a nonnegative factorization approaches to identify muscle synergies during the tasks and to examine the functional significance of such synergies for natural behaviors. Through this finding, the neuromuscular control strategies of upper limb in these movements could be explained clearly, which may also provide significant evidence to support the hypothesis of muscle synergies and a basis for rehabilitation.
{"title":"Muscle Synergy Analysis on Upper Limb Movements of Human Arms","authors":"Hanlin Chen, F. Qin, Jiankang Wu","doi":"10.1145/3375923.3375940","DOIUrl":"https://doi.org/10.1145/3375923.3375940","url":null,"abstract":"Upper limb movements of human arms are natural behaviors which require both the spatial and temporal coordination of multiple muscles. We now investigate how the neural strategy control upper limb movements in the human movement control. These upper limb movements include abduction, adduction, shoulder flexion and shoulder extension. According to our research, we make a hypothesis that a few muscle synergies across different subjects may have similar properties. To validate this hypothesis, we collected and analyzed EMG data in six healthy subjects. Nine muscles were required to reproduce the movement of each subjects. We used a nonnegative factorization approaches to identify muscle synergies during the tasks and to examine the functional significance of such synergies for natural behaviors. Through this finding, the neuromuscular control strategies of upper limb in these movements could be explained clearly, which may also provide significant evidence to support the hypothesis of muscle synergies and a basis for rehabilitation.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87687017","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}
The effect of a gene's activity can be affected by the existence of another gene, termed as genetic interaction, or intragenic epistasis. Understanding genetic interactions among tumor suppressor genes will undoubtedly facilitate our understanding of the tumorigenesis and metastasis. With the wide-application of the next-generation sequencing of patient tumor samples, we have gained unprecedented resolution on the occurrence of mutations in each patient. Many previous studies have used odds ratio and Fisher's exact test to quantify such genetic interactions among tumor suppressor genes. Here, using the TCGA breast cancer dataset as an example, we have showed a potential problem for previous approaches and propose an approach that corrects for these bias. This study serves as a reminder that the interpretation of such large scale studies of mutational frequency data should proceed with reasonable caution.
{"title":"Towards Quantifying Genetic Interactions Among Tumor Suppressor Genes in Breast Cancer","authors":"Wenhao Jiang, Qixuan Zhong","doi":"10.1145/3375923.3375935","DOIUrl":"https://doi.org/10.1145/3375923.3375935","url":null,"abstract":"The effect of a gene's activity can be affected by the existence of another gene, termed as genetic interaction, or intragenic epistasis. Understanding genetic interactions among tumor suppressor genes will undoubtedly facilitate our understanding of the tumorigenesis and metastasis. With the wide-application of the next-generation sequencing of patient tumor samples, we have gained unprecedented resolution on the occurrence of mutations in each patient. Many previous studies have used odds ratio and Fisher's exact test to quantify such genetic interactions among tumor suppressor genes. Here, using the TCGA breast cancer dataset as an example, we have showed a potential problem for previous approaches and propose an approach that corrects for these bias. This study serves as a reminder that the interpretation of such large scale studies of mutational frequency data should proceed with reasonable caution.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78607854","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}
Introduction: DMBA is carcinogenic-immunosuppressant. This study was conducted to investigate the immunosuppressant effect of dimethylbenzanthracene (DMBA) on H-Ras expression, hemogram, and CD8 count I Sprague Dawley (SD) rats. Methods: We divided the test animals into three groups. The normal group received standard food and drink. We induced the DMBA group with 10x20mg/kg BW DMBA for five weeks. The solvent group received standard feeding and corn oil solutions. We conducted dissection and data retrieval in week 27. The immunosuppressant effects of DMBA are measured by number leukocytes and CD8CTL. The number of CD8 is determined by the flow cytometer. The H-Ras gene expression is assessed using densitometry after PCR. The mean intergroup difference was calculated using ANOVA. Result: The results showed that DMBA administration increases H-Ras gene expression and decreases CD8 count (p<0.05). 10x20 mg/kg BW DMBA administration decrease leukocytes and platelet (p<0.05). Conclusion: A dose of 10x20 mg/kg BW DMBA decreased CD8, leukocytes, and platelet number, while it increased H-Ras gene expression in SD rats.
{"title":"DMBA Induction Increases H-Ras Gene Expression and Decreases CD8 Count in Sprague Dawley Rats","authors":"T. Hidayati, Indrayanti, Sagiran","doi":"10.1145/3375923.3375942","DOIUrl":"https://doi.org/10.1145/3375923.3375942","url":null,"abstract":"Introduction: DMBA is carcinogenic-immunosuppressant. This study was conducted to investigate the immunosuppressant effect of dimethylbenzanthracene (DMBA) on H-Ras expression, hemogram, and CD8 count I Sprague Dawley (SD) rats. Methods: We divided the test animals into three groups. The normal group received standard food and drink. We induced the DMBA group with 10x20mg/kg BW DMBA for five weeks. The solvent group received standard feeding and corn oil solutions. We conducted dissection and data retrieval in week 27. The immunosuppressant effects of DMBA are measured by number leukocytes and CD8CTL. The number of CD8 is determined by the flow cytometer. The H-Ras gene expression is assessed using densitometry after PCR. The mean intergroup difference was calculated using ANOVA. Result: The results showed that DMBA administration increases H-Ras gene expression and decreases CD8 count (p<0.05). 10x20 mg/kg BW DMBA administration decrease leukocytes and platelet (p<0.05). Conclusion: A dose of 10x20 mg/kg BW DMBA decreased CD8, leukocytes, and platelet number, while it increased H-Ras gene expression in SD rats.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73647029","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}
The purpose of this study was to examine the effects of trunk rotation and backrest activity on sitting discomfort, body pressure distribution and lumbar surface Electromyographic (sEMG) activities of lumbar erector spinae muscles (LES) and lumbar multifidus muscles (LMF), so as to provide a scientific basis on dynamic chair design and optimization and human-table-chair office system design. Ten healthy male subjects sat on two kinds of office chairs (one fixed dual-back chair and one movable dual-back chair), rotating 60° to the left and the right to simulate the common trunk activities of office work with the seatpan and backrest angle of 110°. Four tests were performed on each subject and sEMG activities of bilateral LES and LMF and body pressure distribution data of seatpan and backrest were statically measured. Meanwhile the Body Part Discomfort (BPD) Scale (Revised) was used to measure the subjective feelings of sitting discomfort. The results showed: (1) backrest activity did not affect marginally on LES and LMF myoelectric activities (P>.05) but trunk rotation had a significant effect on sEMG activities of left LMF (P<.01); (2) trunk rotation did not affect marginally on all the pressure variables (P>.05) but backrest activity affected marginally on average seatpan pressure (ASP), average backrest pressure (ABP) and peak backrest pressure (PBP) (P<.05); (3) low back discomfort (LBD) and total discomfort (OD) subjective ratings were significantly affected by backrest activity which had a large difference between fixed and movable dual-back chair and the latter gained a lower rating of discomfort. This study systematically utilized the combination of objective and subjective measurement to confirm that movable dual-back chairs were significantly better than fixed dual-back chairs which showed the superiority of dynamic chairs.
{"title":"Effects of Trunk Rotation and Backrest Activity on Lumbar sEMG Activities, Body Pressure Distribution and Sitting Discomfort during Sitting","authors":"Zhiping Liu","doi":"10.1145/3375923.3375941","DOIUrl":"https://doi.org/10.1145/3375923.3375941","url":null,"abstract":"The purpose of this study was to examine the effects of trunk rotation and backrest activity on sitting discomfort, body pressure distribution and lumbar surface Electromyographic (sEMG) activities of lumbar erector spinae muscles (LES) and lumbar multifidus muscles (LMF), so as to provide a scientific basis on dynamic chair design and optimization and human-table-chair office system design. Ten healthy male subjects sat on two kinds of office chairs (one fixed dual-back chair and one movable dual-back chair), rotating 60° to the left and the right to simulate the common trunk activities of office work with the seatpan and backrest angle of 110°. Four tests were performed on each subject and sEMG activities of bilateral LES and LMF and body pressure distribution data of seatpan and backrest were statically measured. Meanwhile the Body Part Discomfort (BPD) Scale (Revised) was used to measure the subjective feelings of sitting discomfort. The results showed: (1) backrest activity did not affect marginally on LES and LMF myoelectric activities (P>.05) but trunk rotation had a significant effect on sEMG activities of left LMF (P<.01); (2) trunk rotation did not affect marginally on all the pressure variables (P>.05) but backrest activity affected marginally on average seatpan pressure (ASP), average backrest pressure (ABP) and peak backrest pressure (PBP) (P<.05); (3) low back discomfort (LBD) and total discomfort (OD) subjective ratings were significantly affected by backrest activity which had a large difference between fixed and movable dual-back chair and the latter gained a lower rating of discomfort. This study systematically utilized the combination of objective and subjective measurement to confirm that movable dual-back chairs were significantly better than fixed dual-back chairs which showed the superiority of dynamic chairs.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78886844","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}
The measurement of autonomic nerve activity plays an important role in the diagnosis and treatment of various cardiovascular diseases. This paper presents a model-based method for measuring autonomic nerve activity and sensitivity. By non-invasively recording heart rate and blood pressure data of the subjects during the sit-to-stand experiment, we modeled the blood pressure-heart rate regulation system and solved personalized parameters. These personalized parameters were used to obtain the autonomic nerve activity and sensitivity of the subjects. We conducted experiments on 9 patients with refractory hypertension and 20 healthy people, and the results showed that there were significant differences in the sensitivity and activity of autonomic nerves.
{"title":"A Model-based Method for Measuring Autonomic Nerve Activity and Sensitivity","authors":"Xiang'ao Meng, Zhipei Huang, Jiankang Wu","doi":"10.1145/3375923.3375944","DOIUrl":"https://doi.org/10.1145/3375923.3375944","url":null,"abstract":"The measurement of autonomic nerve activity plays an important role in the diagnosis and treatment of various cardiovascular diseases. This paper presents a model-based method for measuring autonomic nerve activity and sensitivity. By non-invasively recording heart rate and blood pressure data of the subjects during the sit-to-stand experiment, we modeled the blood pressure-heart rate regulation system and solved personalized parameters. These personalized parameters were used to obtain the autonomic nerve activity and sensitivity of the subjects. We conducted experiments on 9 patients with refractory hypertension and 20 healthy people, and the results showed that there were significant differences in the sensitivity and activity of autonomic nerves.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77134002","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}
Recently, a type of genetic interaction, termed synthetic lethality, is emerging as a potential promising anticancer strategy. Synthetic lethality indicates that simultaneous silencing of two complementary signaling pathways can cause cell death, while deficiency of any single gene will not show phenotype. In this study, we aimed to analyze and predict synthetic lethal genetic interactions based on decision tree in breast cancer using TCGA data. First, candidate gene pairs were collected using mutation data based on Misl algorithm, and involved genes were found in more than 2.5% total samples. Based on this method, we obtained 51,040 candidate gene pairs containing 320 genes. Second, 281 experimentally validated gene pairs were used to classify and optimize two features of mutation coverage and copy number variations (CNV) gain/loss, and the final integrated scores were used to predict synthetic lethal genetic interactions based on decision tree. Finally, candidate gene pairs were performed multi-level integrative analysis to search potential interactions, and 11,758 pairs were primarily identified. Some key gene pairs could be further screened based on drug responses and amplification features for experimentally identification, and we finally screened 5 gene pairs to perform further analysis. These results may contribute to screening and identifying synthetic lethal genetic interactions to uncover potential therapeutic target.
{"title":"Predicting Synthetic Lethal Genetic Interactions in Breast Cancer using Decision Tree","authors":"Zibo Yin, Bowen Qian, Guowei Yang, Li Guo","doi":"10.1145/3375923.3375933","DOIUrl":"https://doi.org/10.1145/3375923.3375933","url":null,"abstract":"Recently, a type of genetic interaction, termed synthetic lethality, is emerging as a potential promising anticancer strategy. Synthetic lethality indicates that simultaneous silencing of two complementary signaling pathways can cause cell death, while deficiency of any single gene will not show phenotype. In this study, we aimed to analyze and predict synthetic lethal genetic interactions based on decision tree in breast cancer using TCGA data. First, candidate gene pairs were collected using mutation data based on Misl algorithm, and involved genes were found in more than 2.5% total samples. Based on this method, we obtained 51,040 candidate gene pairs containing 320 genes. Second, 281 experimentally validated gene pairs were used to classify and optimize two features of mutation coverage and copy number variations (CNV) gain/loss, and the final integrated scores were used to predict synthetic lethal genetic interactions based on decision tree. Finally, candidate gene pairs were performed multi-level integrative analysis to search potential interactions, and 11,758 pairs were primarily identified. Some key gene pairs could be further screened based on drug responses and amplification features for experimentally identification, and we finally screened 5 gene pairs to perform further analysis. These results may contribute to screening and identifying synthetic lethal genetic interactions to uncover potential therapeutic target.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88701143","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}
Yudong Zhong, Xiaodong Zhou, Yiping P. Du, Qun Chen
The aim of this study is to develop a technique for rapid multislice chemical exchange saturation transfer (CEST) imaging with dual-channel radiofrequency (RF) irradiation to reduce scan time and enhance CEST contrast. Conventional CEST MRI is implemented with a long RF irradiation module, followed by fast image acquisition to obtain a steady state CEST contrast. However, it typically requires a long preparation time while producing relatively small CEST contrast. A dual-channel RF irradiation scheme is proposed including a long dual-channel RF irradiation module that establishes a steady state CEST contrast and repetitive short dual-channel secondary RF irradiation modules to maintain the contrast. The proposed method is designed to reduce the preparation time to reach steady state CEST contrast and efficiently maintain the contrast throughout signal averages and multislice acquisition. The proposed method was validated on a creatine phantom, and exhibited 31.96% higher CEST contrast than the conventional method. The proposed method, a fast multislice CEST MRI sequence with dual-channel RF irradiation module, is a promising technique with significantly improved CEST contrast and reduced scan time.
{"title":"Fast Multislice Chemical Exchange Saturation Transfer (CEST) MRI with Dual-channel RF Irradiation","authors":"Yudong Zhong, Xiaodong Zhou, Yiping P. Du, Qun Chen","doi":"10.1145/3375923.3375925","DOIUrl":"https://doi.org/10.1145/3375923.3375925","url":null,"abstract":"The aim of this study is to develop a technique for rapid multislice chemical exchange saturation transfer (CEST) imaging with dual-channel radiofrequency (RF) irradiation to reduce scan time and enhance CEST contrast. Conventional CEST MRI is implemented with a long RF irradiation module, followed by fast image acquisition to obtain a steady state CEST contrast. However, it typically requires a long preparation time while producing relatively small CEST contrast. A dual-channel RF irradiation scheme is proposed including a long dual-channel RF irradiation module that establishes a steady state CEST contrast and repetitive short dual-channel secondary RF irradiation modules to maintain the contrast. The proposed method is designed to reduce the preparation time to reach steady state CEST contrast and efficiently maintain the contrast throughout signal averages and multislice acquisition. The proposed method was validated on a creatine phantom, and exhibited 31.96% higher CEST contrast than the conventional method. The proposed method, a fast multislice CEST MRI sequence with dual-channel RF irradiation module, is a promising technique with significantly improved CEST contrast and reduced scan time.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88782210","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}
Rising medical costs and aging populations are major concerns for most countries, including developed countries. Some studies are now mining Health Social Networks (HSNs) as a way of dealing with these concerns. HSN provides a scalable, cost-effective, and fast method for collecting a large amount of user-generated data. However, patients usually have difficulty finding relevant information from social networks. This study aims to develop an Internet of Things (IoT) approach to find keywords to describe medical conditions using patients' biosignals. This study uses the Convolutional Neural Network (CNN) to encode ECG signals into word embedding vectors. Word embedding is a vector projection of words' sentimental features from a context. Similar keywords can be extracted given a vector. Therefore, keywords can be used to search for information from HSN. The average number of keywords correctly predicted is 2 to 3 out of 5. This approach improves the efficiency and effectiveness of information searching in HSNs using biosignal. This study is the first time that index biosignal in HSN.
{"title":"Indexing Biosignal for Integrated Health Social Networks","authors":"Yi Huang, Insu Song","doi":"10.1145/3375923.3375936","DOIUrl":"https://doi.org/10.1145/3375923.3375936","url":null,"abstract":"Rising medical costs and aging populations are major concerns for most countries, including developed countries. Some studies are now mining Health Social Networks (HSNs) as a way of dealing with these concerns. HSN provides a scalable, cost-effective, and fast method for collecting a large amount of user-generated data. However, patients usually have difficulty finding relevant information from social networks. This study aims to develop an Internet of Things (IoT) approach to find keywords to describe medical conditions using patients' biosignals. This study uses the Convolutional Neural Network (CNN) to encode ECG signals into word embedding vectors. Word embedding is a vector projection of words' sentimental features from a context. Similar keywords can be extracted given a vector. Therefore, keywords can be used to search for information from HSN. The average number of keywords correctly predicted is 2 to 3 out of 5. This approach improves the efficiency and effectiveness of information searching in HSNs using biosignal. This study is the first time that index biosignal in HSN.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90201807","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}
Junwei Zhao, Zhenliang Lin, Xiaodong Zhou, Guobin Li, Jie Luo
Acoustic noise during MR scans, generated by the gradient coil vibration, has been compromising for patient comfort and even poses risk for sensitive populations such as fetuses and infants. Although recommended noise level for neonatal MRI with hearing protection such as earplugs is 65 dBA, noise level of an MRI scan could be as high as 125-130 dB(A) at 3T. Further, hearing protection compliance for neonates using earplug could be unreliable. Single-shot echo planar imaging (EPI) has a rapid switching readout gradient waveform that is very efficient for data acquisition but also very loud. Given that EPI is widely used diffusion MRI techniques, modifications in the EPI sequence design could offer a solution that is ubiquitous across scanner platforms. In this work, we investigated the acoustic noise reduction effects of gradient waveform adjustments, echo spacing adjustments, in combination with parallel imaging. Through gradient waveform and echo spacing (ESP) adjustment, the acoustic noise was reduced by 7.5 dBA while keeping high image SNR. Besides, we validated the image consistency and ADC value accuracy quantitatively between traditional EPI-DWI sequence and the modified versions of EPI-DWI sequences in both phantom and human studies.
{"title":"Acoustic Noise Reduction of Echo Planar Imaging in Diffusion MRI","authors":"Junwei Zhao, Zhenliang Lin, Xiaodong Zhou, Guobin Li, Jie Luo","doi":"10.1145/3375923.3375937","DOIUrl":"https://doi.org/10.1145/3375923.3375937","url":null,"abstract":"Acoustic noise during MR scans, generated by the gradient coil vibration, has been compromising for patient comfort and even poses risk for sensitive populations such as fetuses and infants. Although recommended noise level for neonatal MRI with hearing protection such as earplugs is 65 dBA, noise level of an MRI scan could be as high as 125-130 dB(A) at 3T. Further, hearing protection compliance for neonates using earplug could be unreliable. Single-shot echo planar imaging (EPI) has a rapid switching readout gradient waveform that is very efficient for data acquisition but also very loud. Given that EPI is widely used diffusion MRI techniques, modifications in the EPI sequence design could offer a solution that is ubiquitous across scanner platforms. In this work, we investigated the acoustic noise reduction effects of gradient waveform adjustments, echo spacing adjustments, in combination with parallel imaging. Through gradient waveform and echo spacing (ESP) adjustment, the acoustic noise was reduced by 7.5 dBA while keeping high image SNR. Besides, we validated the image consistency and ADC value accuracy quantitatively between traditional EPI-DWI sequence and the modified versions of EPI-DWI sequences in both phantom and human studies.","PeriodicalId":20457,"journal":{"name":"Proceedings of the 2019 6th International Conference on Biomedical and Bioinformatics Engineering","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89492889","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：