Pub Date : 2021-08-23DOI: 10.1109/SAS51076.2021.9530024
G. Olson, C. Davies, G. S. Gupta, Rose Davies, L. Fullard
The artificial muscles of a biomimetic model of the human stomach require positional control of the (linear track) sliders that the actuated muscles are attached to. A novel servomechanism for positional control of a slider on a linear track has been explored using a basic, low -cost stretch sensor as a means in determining the sliders' absolute position over time. The stretch sensor was constructed from a silicone (PDMS) tube filled with an ionic liquid (saline) and exhibited good characteristics of linearity and low hysteresis. A micro controller was used for conditioning the sensor feedback and software control over the slider positioning. Initial results indicate a coarse approximation is attainable of the slider position relative to its targeted position. However, further testing is required to determine operational life-time and other factors such as repeatability, drift and potential for improved accuracy.
{"title":"Positional feedback of a linear track slider using a low-cost stretch sensor","authors":"G. Olson, C. Davies, G. S. Gupta, Rose Davies, L. Fullard","doi":"10.1109/SAS51076.2021.9530024","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530024","url":null,"abstract":"The artificial muscles of a biomimetic model of the human stomach require positional control of the (linear track) sliders that the actuated muscles are attached to. A novel servomechanism for positional control of a slider on a linear track has been explored using a basic, low -cost stretch sensor as a means in determining the sliders' absolute position over time. The stretch sensor was constructed from a silicone (PDMS) tube filled with an ionic liquid (saline) and exhibited good characteristics of linearity and low hysteresis. A micro controller was used for conditioning the sensor feedback and software control over the slider positioning. Initial results indicate a coarse approximation is attainable of the slider position relative to its targeted position. However, further testing is required to determine operational life-time and other factors such as repeatability, drift and potential for improved accuracy.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129923626","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530117
Federico Basili, Stefano Parrino, G. Peruzzi, A. Pozzebon
This paper proposes a novel network architecture integrating a multi-hop Long Range (LoRa)-based thin linear network within a LoRa Wide Area Network (LoRaWAN) infrastructure, with the aim of proposing linear distributed measurement systems forwarding their collected data to a LoRaWAN server by means of a hybrid LoRa-LoRaWAN node. Such device is able to collect LoRa packets coming from the linear network and to encapsulate them in LoRaWAN packets transmitted to the remote server by means of standard LoRaWAN Gateways. The operation of the nodes is regulated by an ad-hoc routing protocol which aims at minimizing their active period, in order to reduce their power consumption increasing the overall system lifetime. Similarly, the synchronization of the nodes aims at increasing the robustness of the network reducing at minimum packet losses. The effectiveness of the proposed network architecture in terms of successful packet deliveries and reduction of active time is tested in different configurations, exploiting 2-node, 3-node and 4-node chains as well as adopting increasingly larger cycle periods. Results show that the proposed configuration ensures a noteworthy robustness in terms of packets delivery while maintaining the duty-cycling at levels that may guarantee long life times and autonomous operation to the overall infrastructure.
{"title":"IoT Multi-Hop Facilities via LoRa Modulation and LoRa WanProtocol within Thin Linear Networks","authors":"Federico Basili, Stefano Parrino, G. Peruzzi, A. Pozzebon","doi":"10.1109/SAS51076.2021.9530117","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530117","url":null,"abstract":"This paper proposes a novel network architecture integrating a multi-hop Long Range (LoRa)-based thin linear network within a LoRa Wide Area Network (LoRaWAN) infrastructure, with the aim of proposing linear distributed measurement systems forwarding their collected data to a LoRaWAN server by means of a hybrid LoRa-LoRaWAN node. Such device is able to collect LoRa packets coming from the linear network and to encapsulate them in LoRaWAN packets transmitted to the remote server by means of standard LoRaWAN Gateways. The operation of the nodes is regulated by an ad-hoc routing protocol which aims at minimizing their active period, in order to reduce their power consumption increasing the overall system lifetime. Similarly, the synchronization of the nodes aims at increasing the robustness of the network reducing at minimum packet losses. The effectiveness of the proposed network architecture in terms of successful packet deliveries and reduction of active time is tested in different configurations, exploiting 2-node, 3-node and 4-node chains as well as adopting increasingly larger cycle periods. Results show that the proposed configuration ensures a noteworthy robustness in terms of packets delivery while maintaining the duty-cycling at levels that may guarantee long life times and autonomous operation to the overall infrastructure.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128851502","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530008
M. Wohlschläger, M. Versen, C. Laforsch
The fluorescence decay time allows to identify and distinguish polymers from each other. Three differently treated biaxially-oriented polyethylene terephthalate films are examined with two excitation wavelengths of 445 and 488nm. The fluorescence decay time is dependent of the treatment method of the films and is a means for identification.
{"title":"Non-destructive evaluation of treated polyethylene terephthalate films by fluorescence lifetime imaging","authors":"M. Wohlschläger, M. Versen, C. Laforsch","doi":"10.1109/SAS51076.2021.9530008","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530008","url":null,"abstract":"The fluorescence decay time allows to identify and distinguish polymers from each other. Three differently treated biaxially-oriented polyethylene terephthalate films are examined with two excitation wavelengths of 445 and 488nm. The fluorescence decay time is dependent of the treatment method of the films and is a means for identification.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134592158","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530184
J. Curry, N. Harris, N. White
This publication presents a novel actuator which makes use of temperature-dependent phase change to convert diurnal temperature variations into a variable force for energy harvesting. The developed actuator can be tuned in a variety of ways to maximise its energy output in any given environment, and paves the way towards a truly location-agnostic energy harvesting solution. Utilising this solution, initial testing indicates that up to 1.5 J of energy is available from a 20°C change in environmental temperature.
{"title":"A novel energy harvesting actuator for self-powered environmental sensors","authors":"J. Curry, N. Harris, N. White","doi":"10.1109/SAS51076.2021.9530184","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530184","url":null,"abstract":"This publication presents a novel actuator which makes use of temperature-dependent phase change to convert diurnal temperature variations into a variable force for energy harvesting. The developed actuator can be tuned in a variety of ways to maximise its energy output in any given environment, and paves the way towards a truly location-agnostic energy harvesting solution. Utilising this solution, initial testing indicates that up to 1.5 J of energy is available from a 20°C change in environmental temperature.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124562574","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530118
Laurie Kirkcaldy, P. Lewin, G. Lees, Rosalie Rogers
This paper investigates novel, initial experimentation in detecting and analysing Partial Discharge at the Oil-Pressboard interface using a continuous fibre-optic-based Distributed Acoustic Sensing (DAS) system. Discharge was successfully detected at a minimum of 223 pC despite the sample rate of DAS being lower than the spectra of acoustic emission. DAS presents multiple advantages over conventional Partial Discharge techniques including inherent localisation, immunity to electrical and magnetic noise, as well as much greater detection distances.
{"title":"Partial Discharge Detection Using Distributed Acoustic Sensing at the Oil-Pressboard Interface","authors":"Laurie Kirkcaldy, P. Lewin, G. Lees, Rosalie Rogers","doi":"10.1109/SAS51076.2021.9530118","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530118","url":null,"abstract":"This paper investigates novel, initial experimentation in detecting and analysing Partial Discharge at the Oil-Pressboard interface using a continuous fibre-optic-based Distributed Acoustic Sensing (DAS) system. Discharge was successfully detected at a minimum of 223 pC despite the sample rate of DAS being lower than the spectra of acoustic emission. DAS presents multiple advantages over conventional Partial Discharge techniques including inherent localisation, immunity to electrical and magnetic noise, as well as much greater detection distances.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123459150","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530013
Daniel G. Kyrollos, J. Tanner, K. Greenwood, J. Harrold, J. Green
Using video data of neonates admitted to the neonatal intensive care unit (NICU) we developed and compared the performance of various techniques for noncontact respiration rate (RR) estimation. Data were collected from an overhead colour and depth (RGB-D) camera, while gold standard physiologic data were captured from the hospital's patient monitor. We developed a deep learning algorithm for automatic detection of the face and chest area of the neonate. We then use this algorithm to identify time periods with low patient motion and to locate regions of interest for RR estimation. We produce a respiration signal by quantifying the chest movement using the raw RGB video, motion-magnified RGB video, and depth video. We compare this to a respiration signal derived from the changes in the green channel of the face. We were able to estimate RR from motion-magnified video and depth video, achieving a mean absolute error of less than 3.5 BPM for 69% and 67% of the time for each stream, respectively. We achieve this result without the need for skin segmentation and can apply our technique to fully clothed neonatal patients. We show that similar performance can be achieved using the depth and colour stream using this technique.
{"title":"Noncontact Neonatal Respiration Rate Estimation Using Machine Vision","authors":"Daniel G. Kyrollos, J. Tanner, K. Greenwood, J. Harrold, J. Green","doi":"10.1109/SAS51076.2021.9530013","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530013","url":null,"abstract":"Using video data of neonates admitted to the neonatal intensive care unit (NICU) we developed and compared the performance of various techniques for noncontact respiration rate (RR) estimation. Data were collected from an overhead colour and depth (RGB-D) camera, while gold standard physiologic data were captured from the hospital's patient monitor. We developed a deep learning algorithm for automatic detection of the face and chest area of the neonate. We then use this algorithm to identify time periods with low patient motion and to locate regions of interest for RR estimation. We produce a respiration signal by quantifying the chest movement using the raw RGB video, motion-magnified RGB video, and depth video. We compare this to a respiration signal derived from the changes in the green channel of the face. We were able to estimate RR from motion-magnified video and depth video, achieving a mean absolute error of less than 3.5 BPM for 69% and 67% of the time for each stream, respectively. We achieve this result without the need for skin segmentation and can apply our technique to fully clothed neonatal patients. We show that similar performance can be achieved using the depth and colour stream using this technique.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128117356","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530007
A. Burrello, Marcello Zanghieri, Cristian Sarti, Leonardo Ravaglia, Simone Benatt, L. Benini
Human-machine interaction is showing promising results for robotic prosthesis control and rehabilitation. In these fields, hand movement recognition via surface electromyographic (sEMG) signals is one of the most promising approaches. However, it still suffers from the issue of sEMG signal's variability over time, which negatively impacts classification robustness. In particular, the non-stationarity of input signals and the surface electrodes' shift can cause up to 30 % degradation in gesture recognition accuracy. This work addresses the temporal variability of the sEMG-based gesture recognition by proposing to train a Temporal Convolutional Network (TCN) incrementally over multiple gesture training sessions. Using incremental learning, we re-train our model on stored latent data spanning multiple sessions. We validate our approach on the UniBo-20-Session dataset, which includes 8 hand gestures from 3 subjects. Our incremental learning framework obtains 18.9% higher accuracy compared to a baseline with a standard single training session. Deploying our TCN on a Parallel, Ultra-Low Power (PULP) microcontroller unit (MCU), GAP8, we achieve an inference latency and energy of 12.9 ms and 0.66 mJ, respectively, with a weight memory footprint of 427 kB and a data memory footprint of 0.5-32 MB.
{"title":"Tackling Time-Variability in sEMG-based Gesture Recognition with On-Device Incremental Learning and Temporal Convolutional Networks","authors":"A. Burrello, Marcello Zanghieri, Cristian Sarti, Leonardo Ravaglia, Simone Benatt, L. Benini","doi":"10.1109/SAS51076.2021.9530007","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530007","url":null,"abstract":"Human-machine interaction is showing promising results for robotic prosthesis control and rehabilitation. In these fields, hand movement recognition via surface electromyographic (sEMG) signals is one of the most promising approaches. However, it still suffers from the issue of sEMG signal's variability over time, which negatively impacts classification robustness. In particular, the non-stationarity of input signals and the surface electrodes' shift can cause up to 30 % degradation in gesture recognition accuracy. This work addresses the temporal variability of the sEMG-based gesture recognition by proposing to train a Temporal Convolutional Network (TCN) incrementally over multiple gesture training sessions. Using incremental learning, we re-train our model on stored latent data spanning multiple sessions. We validate our approach on the UniBo-20-Session dataset, which includes 8 hand gestures from 3 subjects. Our incremental learning framework obtains 18.9% higher accuracy compared to a baseline with a standard single training session. Deploying our TCN on a Parallel, Ultra-Low Power (PULP) microcontroller unit (MCU), GAP8, we achieve an inference latency and energy of 12.9 ms and 0.66 mJ, respectively, with a weight memory footprint of 427 kB and a data memory footprint of 0.5-32 MB.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129677988","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 : 2021-08-23DOI: 10.1109/SAS51076.2021.9530099
Stefan Höltl, Matthias Kneißl, M. Versen
A parallel design concept of Delta-Sigma modulators that optimizes the resolution and the bandwidth for a highly dynamic position control in industrial applications. The idea is realized on a printed circuit board and tested by using a comprehensive measurement setup. The effective number of bits is increased by 2.5 bits at a fixed frequency. For a constant resolution, the design approach allows smaller filter lengths and a decrease of the delay by 25%.
{"title":"Parallel Delta-Sigma ADC modulation for performance increase of position sensors in industrial applications","authors":"Stefan Höltl, Matthias Kneißl, M. Versen","doi":"10.1109/SAS51076.2021.9530099","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530099","url":null,"abstract":"A parallel design concept of Delta-Sigma modulators that optimizes the resolution and the bandwidth for a highly dynamic position control in industrial applications. The idea is realized on a printed circuit board and tested by using a comprehensive measurement setup. The effective number of bits is increased by 2.5 bits at a fixed frequency. For a constant resolution, the design approach allows smaller filter lengths and a decrease of the delay by 25%.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121072505","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 : 2021-07-23DOI: 10.1109/SAS51076.2021.9530050
Xiaying Wang, Fabian Geiger, Vlad Niculescu, M. Magno, L. Benini
The sophisticated sense of touch of the human hand significantly contributes to our ability to safely, efficiently, and dexterously manipulate arbitrary objects in our environment. Robotic and prosthetic devices lack refined tactile feedback from their end-effectors, leading to counterintuitive and complex control strategies. To address this lack, tactile sensors have been designed and developed, but they are either expensive and not scalable or offer an insufficient spatial and temporal resolution. This paper focuses on overcoming these issues by designing a smart embedded system, called SmartHand, enabling the acquisition and real-time processing of high-resolution tactile information from a hand-shaped multi-sensor array for prosthetic and robotic applications. We acquire a new tactile dataset consisting of 340,000 frames while interacting with 16 objects from everyday life and the empty hand, i.e., a total of 17 classes. The design of the embedded system minimizes response latency in classification, by deploying a small yet accurate convolutional neural network on a high-performance ARM Cortex-M7 microcontroller. Compared to related work, our model requires one order of magnitude less memory and 15.6 x fewer computations while achieving similar inter-session accuracy and up to 98.86% and 99.83% top-1 and top-3 cross-validation accuracy, respectively. Experimental results of the designed prototype show a total power consumption of 505mW and a latency of only 100ms.
{"title":"SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications","authors":"Xiaying Wang, Fabian Geiger, Vlad Niculescu, M. Magno, L. Benini","doi":"10.1109/SAS51076.2021.9530050","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530050","url":null,"abstract":"The sophisticated sense of touch of the human hand significantly contributes to our ability to safely, efficiently, and dexterously manipulate arbitrary objects in our environment. Robotic and prosthetic devices lack refined tactile feedback from their end-effectors, leading to counterintuitive and complex control strategies. To address this lack, tactile sensors have been designed and developed, but they are either expensive and not scalable or offer an insufficient spatial and temporal resolution. This paper focuses on overcoming these issues by designing a smart embedded system, called SmartHand, enabling the acquisition and real-time processing of high-resolution tactile information from a hand-shaped multi-sensor array for prosthetic and robotic applications. We acquire a new tactile dataset consisting of 340,000 frames while interacting with 16 objects from everyday life and the empty hand, i.e., a total of 17 classes. The design of the embedded system minimizes response latency in classification, by deploying a small yet accurate convolutional neural network on a high-performance ARM Cortex-M7 microcontroller. Compared to related work, our model requires one order of magnitude less memory and 15.6 x fewer computations while achieving similar inter-session accuracy and up to 98.86% and 99.83% top-1 and top-3 cross-validation accuracy, respectively. Experimental results of the designed prototype show a total power consumption of 505mW and a latency of only 100ms.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124337379","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 : 2020-11-01DOI: 10.1109/SAS51076.2021.9530155
Taimur Hassan, Bilal Hassan, A. El-Baz, N. Werghi
Prostate cancer (PCa) is the second deadliest form of cancer in males, and it can be clinically graded by examining the structural representations of Gleason tissues. This paper proposes a new method for segmenting the Gleason tissues (patch-wise) in order to grade PCa from the whole slide images (WSI). Also, the proposed approach encompasses two main contributions: 1) A synergy of hybrid dilation factors and hierarchical decomposition of latent space representation for effective Gleason tissues extraction, and 2) A three-tiered loss function which can penalize different semantic segmentation models for accurately extracting the highly correlated patterns. In addition to this, the proposed framework has been extensively evaluated on a large-scale PCa dataset containing 10,516 whole slide scans (with around 71.7M patches), where it outperforms state-of-the-art schemes by 3.22% (in terms of mean intersection-over-union) for extracting the Gleason tissues and 6.91 % (in terms of F1 score) for grading the progression of PCa.
{"title":"A Dilated Residual Hierarchically Fashioned Segmentation Framework for Extracting Gleason Tissues and Grading Prostate Cancer from Whole Slide Images","authors":"Taimur Hassan, Bilal Hassan, A. El-Baz, N. Werghi","doi":"10.1109/SAS51076.2021.9530155","DOIUrl":"https://doi.org/10.1109/SAS51076.2021.9530155","url":null,"abstract":"Prostate cancer (PCa) is the second deadliest form of cancer in males, and it can be clinically graded by examining the structural representations of Gleason tissues. This paper proposes a new method for segmenting the Gleason tissues (patch-wise) in order to grade PCa from the whole slide images (WSI). Also, the proposed approach encompasses two main contributions: 1) A synergy of hybrid dilation factors and hierarchical decomposition of latent space representation for effective Gleason tissues extraction, and 2) A three-tiered loss function which can penalize different semantic segmentation models for accurately extracting the highly correlated patterns. In addition to this, the proposed framework has been extensively evaluated on a large-scale PCa dataset containing 10,516 whole slide scans (with around 71.7M patches), where it outperforms state-of-the-art schemes by 3.22% (in terms of mean intersection-over-union) for extracting the Gleason tissues and 6.91 % (in terms of F1 score) for grading the progression of PCa.","PeriodicalId":224327,"journal":{"name":"2021 IEEE Sensors Applications Symposium (SAS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127699286","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：