Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572273
Pradeep Balachandran, C. Carey
This paper asserts the importance of collaborative stakeholder participation and the need for a process measurement model to improve the performance of consensus building in standards development. A systems engineering based process behavior measurement model is proposed. The model is capable of detecting critical events and trends across the consensus building life cycle; thereby, improving the process performance in producing optimal outcomes. In this behavior model, the measures of specific attributes of the underlying consensus process are used to compute metrics that can be analyzed. They provide course and fine indicators process performance in terms of stability assessment, risk tracking and workflow evaluation. The proposed model may help guide an evidence-based metrics program for Standards Development Organizations (SDOs) to build equitable and accountable assessment platforms for stakeholder engagement in consesus standards development.
{"title":"Collaborative Model for Stakeholder Engagement in Consensus Standards Development","authors":"Pradeep Balachandran, C. Carey","doi":"10.1109/LSC.2018.8572273","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572273","url":null,"abstract":"This paper asserts the importance of collaborative stakeholder participation and the need for a process measurement model to improve the performance of consensus building in standards development. A systems engineering based process behavior measurement model is proposed. The model is capable of detecting critical events and trends across the consensus building life cycle; thereby, improving the process performance in producing optimal outcomes. In this behavior model, the measures of specific attributes of the underlying consensus process are used to compute metrics that can be analyzed. They provide course and fine indicators process performance in terms of stability assessment, risk tracking and workflow evaluation. The proposed model may help guide an evidence-based metrics program for Standards Development Organizations (SDOs) to build equitable and accountable assessment platforms for stakeholder engagement in consesus standards development.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121150893","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572239
A. Phinyomark, E. Scheme
In this work, we present a novel set of higher order time domain features for surface electromyographic (EMG) pattern recognition. The proposed methods employ simple measures of frequency information extracted from EMG time series when a sequence of differencing filters is applied. Multiple EMG datasets consisting of 48 able-bodied and transradial amputee subjects performing a large variety of hand and fingers movements are used to evaluate the performance and robustness of the proposed features. The results show that these novel higher order-based features provide significantly better performance than their traditional counterparts by 3–15 % $(p < 0.05)$. The best proposed feature, higher-order myopulse percentage rate, also significantly outperformed other frequency information-based EMG features in the time and frequency domains: histogram, mean frequency, and median frequency, by 8-14%, 8-25%, and 14-35% $(p < 0.05)$, respectively. With relatively less computational complexity, the proposed features could potentially be used as new features for extracting frequency information for EMG- based pattern recognition systems.
{"title":"Novel Features for EMG Pattern Recognition Based on Higher Order Crossings","authors":"A. Phinyomark, E. Scheme","doi":"10.1109/LSC.2018.8572239","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572239","url":null,"abstract":"In this work, we present a novel set of higher order time domain features for surface electromyographic (EMG) pattern recognition. The proposed methods employ simple measures of frequency information extracted from EMG time series when a sequence of differencing filters is applied. Multiple EMG datasets consisting of 48 able-bodied and transradial amputee subjects performing a large variety of hand and fingers movements are used to evaluate the performance and robustness of the proposed features. The results show that these novel higher order-based features provide significantly better performance than their traditional counterparts by 3–15 % $(p < 0.05)$. The best proposed feature, higher-order myopulse percentage rate, also significantly outperformed other frequency information-based EMG features in the time and frequency domains: histogram, mean frequency, and median frequency, by 8-14%, 8-25%, and 14-35% $(p < 0.05)$, respectively. With relatively less computational complexity, the proposed features could potentially be used as new features for extracting frequency information for EMG- based pattern recognition systems.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124085088","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572118
Gabriel Gagnon-Turcotte, C. Fall, Q. Mascret, M. Bielmann, L. Bouyer, B. Gosselin
This paper presents a wireless multichannel surface electromyography (sEMG) sensor which features a custom 0.13- $mu mathrm{m}$ CMOS mixed-signal system-on-chip (SoC) analog frontend circuit. The proposed sensor includes 10 sEMG recording channels with tunable bandwidth (BW) and analog-to-digital converter (ADC) resolution. The SoC includes 10x bioamplifiers, $10mathrm{x}3^{rd}$ order $Delta Sigma$ MASH 1-1-1 ADC, and 10x on-chip decimation filters (DF). This SoC provides the sEMG samples data through a serial peripheral interface (SPI) bus to a microcontroller unit (MCU) that then transfers the data to a wireless transceiver. We report sEMG waveforms acquired using a custom multichannel electrode module, and a comparison with a commercial grade system. Results show that the proposed integrated wireless SoC-based system compares well with the commercial grade sEMG recording system. The sensor has an input-referred noise of $2.5 mu mathbf{V}_{rms}$ (BW of 10–500 Hz), an input-dynamic range of 6 $mathbf{mV}_{pp}$, a programmable sampling rate of 2 ksps, for sEMG, while consuming only $7.1 mu mathrm{W}/mathrm{Ch}$ for the SoC (w/ ADC & DF) and 21.8 mW of power for the sensor (Transceiver, MCU, etc.). The system lies on a $1.5 mathrm{x} 2.0 mathrm{cm}^{2}$ printed circuit board and weights $< 1mathrm{g}$.
{"title":"A Multichannel Wireless sEMG Sensor Endowing a $0.13 mu mathrm{m}$ CMOS Mixed-Signal SoC","authors":"Gabriel Gagnon-Turcotte, C. Fall, Q. Mascret, M. Bielmann, L. Bouyer, B. Gosselin","doi":"10.1109/LSC.2018.8572118","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572118","url":null,"abstract":"This paper presents a wireless multichannel surface electromyography (sEMG) sensor which features a custom 0.13- $mu mathrm{m}$ CMOS mixed-signal system-on-chip (SoC) analog frontend circuit. The proposed sensor includes 10 sEMG recording channels with tunable bandwidth (BW) and analog-to-digital converter (ADC) resolution. The SoC includes 10x bioamplifiers, $10mathrm{x}3^{rd}$ order $Delta Sigma$ MASH 1-1-1 ADC, and 10x on-chip decimation filters (DF). This SoC provides the sEMG samples data through a serial peripheral interface (SPI) bus to a microcontroller unit (MCU) that then transfers the data to a wireless transceiver. We report sEMG waveforms acquired using a custom multichannel electrode module, and a comparison with a commercial grade system. Results show that the proposed integrated wireless SoC-based system compares well with the commercial grade sEMG recording system. The sensor has an input-referred noise of $2.5 mu mathbf{V}_{rms}$ (BW of 10–500 Hz), an input-dynamic range of 6 $mathbf{mV}_{pp}$, a programmable sampling rate of 2 ksps, for sEMG, while consuming only $7.1 mu mathrm{W}/mathrm{Ch}$ for the SoC (w/ ADC & DF) and 21.8 mW of power for the sensor (Transceiver, MCU, etc.). The system lies on a $1.5 mathrm{x} 2.0 mathrm{cm}^{2}$ printed circuit board and weights $< 1mathrm{g}$.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115246151","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572174
Junmin Wang, S. Isaacson, C. Belta
Transient transfection of cells can be highly stochastic, resulting in large variations in plasmid counts across a population. The resulting dynamics of the cells can then also be highly variable, so predicting the behaviors of transfected circuits can be a major challenge. In this work, we provide a precise definition of genetic modules, from which we then develop a method of composition that allows model-based design of circuits in transiently transfected mammalian cells. For validation, we apply our method to cascades consisting of two regulatory switches. Predictions of the mathematical models compare well with the experimental data. Our findings suggest reducing batch effects and selecting a proper model both contribute to improving model predictions.
{"title":"Predictions of Genetic Circuit Behaviors Based on Modular Composition in Transiently Transfected Mammalian Cells","authors":"Junmin Wang, S. Isaacson, C. Belta","doi":"10.1109/LSC.2018.8572174","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572174","url":null,"abstract":"Transient transfection of cells can be highly stochastic, resulting in large variations in plasmid counts across a population. The resulting dynamics of the cells can then also be highly variable, so predicting the behaviors of transfected circuits can be a major challenge. In this work, we provide a precise definition of genetic modules, from which we then develop a method of composition that allows model-based design of circuits in transiently transfected mammalian cells. For validation, we apply our method to cascades consisting of two regulatory switches. Predictions of the mathematical models compare well with the experimental data. Our findings suggest reducing batch effects and selecting a proper model both contribute to improving model predictions.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"76 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116290217","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}
Pub Date : 2018-10-01DOI: 10.1109/lsc.2018.8572282
T. AbdelFatah, M. Jalali, S. Mahshid
Here we report on design, fabrication and implementation of a nanosurfac microfluidic device for efficient bacteria capture and optical detection. The device features simple design and ease of implementation. The principal of operation depends on the self-assembly of microparticles (polystyrene particles) at a pillar array region to form a Nano-filter for subsequent bacteria capture on gold nano/micro islands. The design was optimized using 2D COMSOL simulation. The device was fabricated using a single UV lithography step followed by electrodeposition of the gold structures and a subsequent step of polydimethylsiloxane (PDMS) bonding for device sealing. Lastly, the device was experimentally implemented using Escherichia coli (E.coli) bacteria showing efficient bacteria capturing performance.
{"title":"A Nanosurface Microfluidic Device for Capture and Detection of Bacteria","authors":"T. AbdelFatah, M. Jalali, S. Mahshid","doi":"10.1109/lsc.2018.8572282","DOIUrl":"https://doi.org/10.1109/lsc.2018.8572282","url":null,"abstract":"Here we report on design, fabrication and implementation of a nanosurfac microfluidic device for efficient bacteria capture and optical detection. The device features simple design and ease of implementation. The principal of operation depends on the self-assembly of microparticles (polystyrene particles) at a pillar array region to form a Nano-filter for subsequent bacteria capture on gold nano/micro islands. The design was optimized using 2D COMSOL simulation. The device was fabricated using a single UV lithography step followed by electrodeposition of the gold structures and a subsequent step of polydimethylsiloxane (PDMS) bonding for device sealing. Lastly, the device was experimentally implemented using Escherichia coli (E.coli) bacteria showing efficient bacteria capturing performance.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114197596","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572252
Vahid Khojasteh Lazarjan, M. N. Khiarak, A. B. Gashti, A. Garnier, B. Gosselin
In this paper, a new miniaturized wireless cell spectrophotometer is presented. This system can scan a sample, detect incoming light power and transmit corresponding data to a base station for further analysis in the range of 340 nm to 850 nm. In vitro measurement results with VERO E6 cells tagged with DAPI and Alexa Fluor488 are presented to demonstrate its performance. The proposed system uses two small Lithium-ion batteries that provide a 7.4 V supply voltage. The system's low power consumption (88 mW), its minimal use of hardware resources, and its total weight of 17 g incorporated into a small wireless platform make the proposed device suitable for real-time implementation in most common low-power cell spectrophotometer applications.
{"title":"Miniaturized Wireless Cell Spectrophotometer Platform in Visible and Near-IR Range","authors":"Vahid Khojasteh Lazarjan, M. N. Khiarak, A. B. Gashti, A. Garnier, B. Gosselin","doi":"10.1109/LSC.2018.8572252","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572252","url":null,"abstract":"In this paper, a new miniaturized wireless cell spectrophotometer is presented. This system can scan a sample, detect incoming light power and transmit corresponding data to a base station for further analysis in the range of 340 nm to 850 nm. In vitro measurement results with VERO E6 cells tagged with DAPI and Alexa Fluor488 are presented to demonstrate its performance. The proposed system uses two small Lithium-ion batteries that provide a 7.4 V supply voltage. The system's low power consumption (88 mW), its minimal use of hardware resources, and its total weight of 17 g incorporated into a small wireless platform make the proposed device suitable for real-time implementation in most common low-power cell spectrophotometer applications.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128154586","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572089
Tayyyebeh Azita Saberbgahi, E. Ghafar-Zadeh, Chun Peng
This study presents a new approach for delivery of molecules into the cell Layers of Zebrafish Follicle which can be crucial for understanding of ovarian development and the treatment of ovarian diseases. Zebrafish follicles are used as a model of ovarian development. These follicles consists of an oocyte surrounded by two thin layers of cells called theca and granulosa cell. Electroporation is a non-invasive method widely used for transferring molecules into cells for various applications including stem cell based tissue construction and gene therapy. Despite broad advantages of electroporation, no reports have been released for application of drug delivery into Zebrafish follicle and Follicle cells. This paper is the first to discuss the advantage of electroporation for the delivery of biomolecules into the follicle and follicle cells. Herein we demonstrate and discuss the advantage of electroporation for the molecule delivery into follicle and follicle cells using Propidium Iodide (PI) and green fluorescence protein (GFP).
{"title":"Towards High Throughput Electroporation of Zebrafish Folicles","authors":"Tayyyebeh Azita Saberbgahi, E. Ghafar-Zadeh, Chun Peng","doi":"10.1109/LSC.2018.8572089","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572089","url":null,"abstract":"This study presents a new approach for delivery of molecules into the cell Layers of Zebrafish Follicle which can be crucial for understanding of ovarian development and the treatment of ovarian diseases. Zebrafish follicles are used as a model of ovarian development. These follicles consists of an oocyte surrounded by two thin layers of cells called theca and granulosa cell. Electroporation is a non-invasive method widely used for transferring molecules into cells for various applications including stem cell based tissue construction and gene therapy. Despite broad advantages of electroporation, no reports have been released for application of drug delivery into Zebrafish follicle and Follicle cells. This paper is the first to discuss the advantage of electroporation for the delivery of biomolecules into the follicle and follicle cells. Herein we demonstrate and discuss the advantage of electroporation for the molecule delivery into follicle and follicle cells using Propidium Iodide (PI) and green fluorescence protein (GFP).","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127252160","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572105
John B. Oommen, David Bews, M. S. Hassani, Y. Ono, J. Green
This project aims to enable a visually impaired swimmer to train with more independence than currently allowed by other solutions. The final device prototype consists of a smartphone application that leverages various hardware components within a smartphone, such as the video camera and the gyroscope. These hardware components are used to track the visually impaired swimmer in a reliable manner and notify the swimmer if they have deviated to a side or if they are approaching the end of their lane. The final prototype uses machine vision to track a swimmer's position relative to the black “T” shaped line on the bottom of a standard competitive swimming pool. A device prototype is created and tested to demonstrate the proof of concept for the device design and algorithm. The in-water device testing demonstrates the success of the prototype in real-world scenarios and highlights opportunities for further device improvements.
{"title":"A Wearable Electronic Swim Coach for Blind Athletes","authors":"John B. Oommen, David Bews, M. S. Hassani, Y. Ono, J. Green","doi":"10.1109/LSC.2018.8572105","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572105","url":null,"abstract":"This project aims to enable a visually impaired swimmer to train with more independence than currently allowed by other solutions. The final device prototype consists of a smartphone application that leverages various hardware components within a smartphone, such as the video camera and the gyroscope. These hardware components are used to track the visually impaired swimmer in a reliable manner and notify the swimmer if they have deviated to a side or if they are approaching the end of their lane. The final prototype uses machine vision to track a swimmer's position relative to the black “T” shaped line on the bottom of a standard competitive swimming pool. A device prototype is created and tested to demonstrate the proof of concept for the device design and algorithm. The in-water device testing demonstrates the success of the prototype in real-world scenarios and highlights opportunities for further device improvements.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123723815","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572264
A. Chaddad, T. Niazi
Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and cognitive functions of patients. However, whether imaging features can be utilised as biomarkers for this disease has not been explored. To address this, we encoded subcortical regions of the brain using 45 radiomic features to identify features specific for AD patients. We comprehensively evaluated the proposed approach using the OASIS dataset, assessing significance via the Wilcoxon test and Random Forest (RF) classifier models to identify the subcortical regions best able to identify AD patients. Our results show that features (i.e., correlation and volume) derived from several subcortical regions (i.e., cerebral, thalamus, caudate Putamen, Pallidum, hippocampus, amygdala, and stem-and-cerebrospinal-fluid) are able to identify AD from healthy control (HC) subjects with the hippocampus and amygdala reaching $mathrm{p} < 0.01$ following Holm-Bonferroni correction. Consistent with this, hippocampus ($mathbf{AUC}=mathbf{81.19-84.09}%$) and amygdala ($mathbf{AUC}=mathbf{79.70-80.27}%$) regions showed a higher AUC value compared to other subcortical regions. Combining radiomic features derived from all subcortical regions produced an AUC value of 91.54% for classifying AD from HC subjects. RF analysis revealed that from the 45 radiomic features, correlation and volume are the most important features for the classifier model. These results demonstrate that radiomic features extracted from hippocampus and amygdala regions are relevant biomarkers for AD patients and that correlation and volume features are the most important features to build this model.
{"title":"Radiomics Analysis of Subcortical Brain Regions Related to Alzheimer Disease","authors":"A. Chaddad, T. Niazi","doi":"10.1109/LSC.2018.8572264","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572264","url":null,"abstract":"Alzheimer's disease (AD) is the most common form of dementia that causes progressive impairment of memory and cognitive functions of patients. However, whether imaging features can be utilised as biomarkers for this disease has not been explored. To address this, we encoded subcortical regions of the brain using 45 radiomic features to identify features specific for AD patients. We comprehensively evaluated the proposed approach using the OASIS dataset, assessing significance via the Wilcoxon test and Random Forest (RF) classifier models to identify the subcortical regions best able to identify AD patients. Our results show that features (i.e., correlation and volume) derived from several subcortical regions (i.e., cerebral, thalamus, caudate Putamen, Pallidum, hippocampus, amygdala, and stem-and-cerebrospinal-fluid) are able to identify AD from healthy control (HC) subjects with the hippocampus and amygdala reaching $mathrm{p} < 0.01$ following Holm-Bonferroni correction. Consistent with this, hippocampus ($mathbf{AUC}=mathbf{81.19-84.09}%$) and amygdala ($mathbf{AUC}=mathbf{79.70-80.27}%$) regions showed a higher AUC value compared to other subcortical regions. Combining radiomic features derived from all subcortical regions produced an AUC value of 91.54% for classifying AD from HC subjects. RF analysis revealed that from the 45 radiomic features, correlation and volume are the most important features for the classifier model. These results demonstrate that radiomic features extracted from hippocampus and amygdala regions are relevant biomarkers for AD patients and that correlation and volume features are the most important features to build this model.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122653445","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}
Pub Date : 2018-10-01DOI: 10.1109/LSC.2018.8572248
Roger Booto Tokime, Hassan Elassady, M. Akhloufi
The development time of new drugs is a long and complex process with different stages of analysis and screening. In most of the analysis stage, the first step is the detection of cells' nuclei. This allows researchers to identify the individual cells in a sample because most of the cells contain a nucleus filled with DNA (Deoxyribonucleic acid). Identification of cell nuclei help measure the reactions of cells when exposed to various treatments and lead to understanding the biological process underlying the work. This process is laborious and slow because it requires the identification and analysis of thousands of images at a time. Thus, automating this step would speed up the analytical process. Therefore, the time to market for a new drug can be significantly reduced. This work proposes three deep learning techniques to segment the images and to identify the cells' nuclei. Modified architectures based on semantic segmentation networks such as UNet, SegNet, and FCN were developed. The obtained results are very interesting with F1-Scores ranging from 94% for FCN to 96% for UNet. SegNet follows closely UNet with an F1-Score of 95%.
{"title":"Identifying the Cells' Nuclei Using Deep Learning","authors":"Roger Booto Tokime, Hassan Elassady, M. Akhloufi","doi":"10.1109/LSC.2018.8572248","DOIUrl":"https://doi.org/10.1109/LSC.2018.8572248","url":null,"abstract":"The development time of new drugs is a long and complex process with different stages of analysis and screening. In most of the analysis stage, the first step is the detection of cells' nuclei. This allows researchers to identify the individual cells in a sample because most of the cells contain a nucleus filled with DNA (Deoxyribonucleic acid). Identification of cell nuclei help measure the reactions of cells when exposed to various treatments and lead to understanding the biological process underlying the work. This process is laborious and slow because it requires the identification and analysis of thousands of images at a time. Thus, automating this step would speed up the analytical process. Therefore, the time to market for a new drug can be significantly reduced. This work proposes three deep learning techniques to segment the images and to identify the cells' nuclei. Modified architectures based on semantic segmentation networks such as UNet, SegNet, and FCN were developed. The obtained results are very interesting with F1-Scores ranging from 94% for FCN to 96% for UNet. SegNet follows closely UNet with an F1-Score of 95%.","PeriodicalId":254835,"journal":{"name":"2018 IEEE Life Sciences Conference (LSC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122120937","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：