Pub Date : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478757
R. Selzler, A. Chan, J. Green
The autonomic nervous system is known for the fight or flight response. Anxiety affects the autonomic nervous system, causing heightened heart rate and electrodermal activity. This paper explores machine learning methods to predict two- and three-level anxiety in spider fearful individuals watching spider video clips in a controlled trial. Features are extracted from electrocardiogram and electrodermal time-series signals. Specifically, this paper explores the performance of such models as the amount of data pertaining to the test subject increases in the training set. Standard K-fold cross-validation is here compared to leaky group-fold cross-validation with sample imputation, where we systematically vary the the number of samples from the test subject that are included in the training set. While it is possible to reach 78% and 60% k-fold accuracy for a two- and three-level anxiety prediction, respectively, excluding all test subject data from the training set causes the accuracy to drop to 73% and 45%. The results demonstrate that the features and models used here do not generalize for inter-subject classification tasks and that care should be taken when splitting subject data between training and test data. Furthermore, our results address the "cold start problem" by providing an indication of how much data would be required from a new subject before accurate prediction of anxiety is possible from physiologic data.
{"title":"Impact of Subject-specific Training Data in Anxiety Level Classification from Physiologic Data","authors":"R. Selzler, A. Chan, J. Green","doi":"10.1109/MeMeA52024.2021.9478757","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478757","url":null,"abstract":"The autonomic nervous system is known for the fight or flight response. Anxiety affects the autonomic nervous system, causing heightened heart rate and electrodermal activity. This paper explores machine learning methods to predict two- and three-level anxiety in spider fearful individuals watching spider video clips in a controlled trial. Features are extracted from electrocardiogram and electrodermal time-series signals. Specifically, this paper explores the performance of such models as the amount of data pertaining to the test subject increases in the training set. Standard K-fold cross-validation is here compared to leaky group-fold cross-validation with sample imputation, where we systematically vary the the number of samples from the test subject that are included in the training set. While it is possible to reach 78% and 60% k-fold accuracy for a two- and three-level anxiety prediction, respectively, excluding all test subject data from the training set causes the accuracy to drop to 73% and 45%. The results demonstrate that the features and models used here do not generalize for inter-subject classification tasks and that care should be taken when splitting subject data between training and test data. Furthermore, our results address the \"cold start problem\" by providing an indication of how much data would be required from a new subject before accurate prediction of anxiety is possible from physiologic data.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122911344","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478600
Rahul Manoj, V. RajKiran, P. Nabeel, M. Sivaprakasam, J. Joseph
Central Arteries’ elastic nature plays a fundamental role in maintaining cardiovascular health. Timely assessment of arterial stiffness helps in cardiovascular risk stratification. Various technological and methodological approaches exist to estimate arterial stiffness, through direct measurement of stiffness markers or surrogates. This work highlights a potential surrogate for arterial stiffness, based on the early onset of reflection waves. The significance comes with using low frame rate A-mode ultrasound scans for processing arterial diameter, modelled as a sum of three Gaussians. The novelty lies in the Gaussian modelled reflection onset time $left( {tau _R^{GM}} right)$, derived using the model parameters, a potential surrogate for early reflections and arterial stiffness. An observational cross-sectional study group of 34 subjects were recruited to validate this hypothesis. A statistically significant (p < 0.0001) correlation was obtained for $tau _R^{GM}$ against known stiffness markers. An R > 0.85 was obtained against Elastic modulus, specific stiffness index, and Pulse wave velocity. There exists an inverse correlation between the $tau _R^{GM}$ and popular stiffness markers. A statistically significant (p < 0.0001) correlation was obtained for $tau _R^{GM}$ against age, with R = 0.56. The early reflections were reliably detected by the $tau _R^{GM}$ and the evidenced strong correlation with stiffness markers make it a potential surrogate for arterial stiffness assessment. The advantage being that it can be obtained from a single pulse waveform like diameter.
{"title":"Multi-Gaussian Model for Estimating Stiffness Surrogate using Arterial Diameter Waveform","authors":"Rahul Manoj, V. RajKiran, P. Nabeel, M. Sivaprakasam, J. Joseph","doi":"10.1109/MeMeA52024.2021.9478600","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478600","url":null,"abstract":"Central Arteries’ elastic nature plays a fundamental role in maintaining cardiovascular health. Timely assessment of arterial stiffness helps in cardiovascular risk stratification. Various technological and methodological approaches exist to estimate arterial stiffness, through direct measurement of stiffness markers or surrogates. This work highlights a potential surrogate for arterial stiffness, based on the early onset of reflection waves. The significance comes with using low frame rate A-mode ultrasound scans for processing arterial diameter, modelled as a sum of three Gaussians. The novelty lies in the Gaussian modelled reflection onset time $left( {tau _R^{GM}} right)$, derived using the model parameters, a potential surrogate for early reflections and arterial stiffness. An observational cross-sectional study group of 34 subjects were recruited to validate this hypothesis. A statistically significant (p < 0.0001) correlation was obtained for $tau _R^{GM}$ against known stiffness markers. An R > 0.85 was obtained against Elastic modulus, specific stiffness index, and Pulse wave velocity. There exists an inverse correlation between the $tau _R^{GM}$ and popular stiffness markers. A statistically significant (p < 0.0001) correlation was obtained for $tau _R^{GM}$ against age, with R = 0.56. The early reflections were reliably detected by the $tau _R^{GM}$ and the evidenced strong correlation with stiffness markers make it a potential surrogate for arterial stiffness assessment. The advantage being that it can be obtained from a single pulse waveform like diameter.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124722357","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478670
A. D. Leo, P. Russo, G. Cerri
In this paper a novel antenna for an electromagnetic assistance system for autonomous walking of blind or visually impaired people is presented. Its main aim is to detect obstacles that the white cane is not able to intercept, in particular those that can hurt the head or thorax zone. The proposed antenna has a fan beam radiation pattern, works at 24 GHz, in a frequency band reserved for ISM (Industrial, Scientific and Medical) applications. The antenna is designed using a numerical electromagnetic tool and its capability to detect a wide set of obstacles was investigated through numerical simulations and experimental measurements. Results confirm the good performances of the antenna and its capability to extend by a few meters the region usually explored by the white cane.
{"title":"Electronic Travel Aid for Visually Impaired People: Design and Experimental of a Special Antenna","authors":"A. D. Leo, P. Russo, G. Cerri","doi":"10.1109/MeMeA52024.2021.9478670","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478670","url":null,"abstract":"In this paper a novel antenna for an electromagnetic assistance system for autonomous walking of blind or visually impaired people is presented. Its main aim is to detect obstacles that the white cane is not able to intercept, in particular those that can hurt the head or thorax zone. The proposed antenna has a fan beam radiation pattern, works at 24 GHz, in a frequency band reserved for ISM (Industrial, Scientific and Medical) applications. The antenna is designed using a numerical electromagnetic tool and its capability to detect a wide set of obstacles was investigated through numerical simulations and experimental measurements. Results confirm the good performances of the antenna and its capability to extend by a few meters the region usually explored by the white cane.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125314544","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478674
Daniel Fehr, Renske Sassenburg, Jacqueline Blunschi, A. Lay-Ekuakille, A. Massaro, M. Bonmarin, F. Spano
Robots are slowly becoming part of our civilization, or at least one of the main evolutions of the third millennium. Nowadays their integration is based on their aspects by looking more and more human. Additionally, not only considering the psychological aspects, our society will have to improve their interaction. Systems integrating a full spectrum of sensors will have to be implemented. In this framework, as a preliminary step, the implementation of a tactile robotic skin can be an interesting upgrade. To guarantee safety between robots and humans, it can be interesting to implement such robots with human-like tactile perception. In this work, we focus on the realization of innovative tactile skin model. This model allows to sense and indicate where the pressures have been applied by using a combination of a flexible polymeric capacitive skin model combined with a LED matrix.
{"title":"A Capacitive Color-Changing Electronic Skin for Touch Sensing Applications","authors":"Daniel Fehr, Renske Sassenburg, Jacqueline Blunschi, A. Lay-Ekuakille, A. Massaro, M. Bonmarin, F. Spano","doi":"10.1109/MeMeA52024.2021.9478674","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478674","url":null,"abstract":"Robots are slowly becoming part of our civilization, or at least one of the main evolutions of the third millennium. Nowadays their integration is based on their aspects by looking more and more human. Additionally, not only considering the psychological aspects, our society will have to improve their interaction. Systems integrating a full spectrum of sensors will have to be implemented. In this framework, as a preliminary step, the implementation of a tactile robotic skin can be an interesting upgrade. To guarantee safety between robots and humans, it can be interesting to implement such robots with human-like tactile perception. In this work, we focus on the realization of innovative tactile skin model. This model allows to sense and indicate where the pressures have been applied by using a combination of a flexible polymeric capacitive skin model combined with a LED matrix.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124458886","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478671
A. Orrico, Leonard M. Bianchi, S. Korganbayev, M. Landrø, P. Saccomandi
Real-time monitoring and temperature-based control are beneficial for optimizing the outcomes of thermal ablation treatments. In this paper, simulations and experiments were performed to investigate the efficacy of the temperature-feedback control system in confining the thermal damaged area and in maintaining the setpoint temperature. The implemented control system adjusts the laser source power based on the maximum temperature values measured by fiber Bragg grating sensors. The theoretical model predicts the thermal response of the biological tissue under different control parameters and allows calculating the produced thermal damage. Different setpoint temperatures ranging from 43 °C to 60 °C were chosen to evaluate their effects on the irradiated tissue region, in terms of temperature trend and thermal damage. The numerical results are validated by the experimental temperature trends obtained applying the same control strategy. Finally, both the simulation results and experiment outcomes show the capability of the control system to confine the tissue thermal damaged area by performing a laser ablation procedure almost at the set temperature.
{"title":"Controlled photothermal therapy based on temperature monitoring: theoretical and experimental analysis","authors":"A. Orrico, Leonard M. Bianchi, S. Korganbayev, M. Landrø, P. Saccomandi","doi":"10.1109/MeMeA52024.2021.9478671","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478671","url":null,"abstract":"Real-time monitoring and temperature-based control are beneficial for optimizing the outcomes of thermal ablation treatments. In this paper, simulations and experiments were performed to investigate the efficacy of the temperature-feedback control system in confining the thermal damaged area and in maintaining the setpoint temperature. The implemented control system adjusts the laser source power based on the maximum temperature values measured by fiber Bragg grating sensors. The theoretical model predicts the thermal response of the biological tissue under different control parameters and allows calculating the produced thermal damage. Different setpoint temperatures ranging from 43 °C to 60 °C were chosen to evaluate their effects on the irradiated tissue region, in terms of temperature trend and thermal damage. The numerical results are validated by the experimental temperature trends obtained applying the same control strategy. Finally, both the simulation results and experiment outcomes show the capability of the control system to confine the tissue thermal damaged area by performing a laser ablation procedure almost at the set temperature.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122573325","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478605
Satyake Bakshi, S. Rajan
The threat of falling down is significantly higher for the geriatric population and can lead to serious injuries including death. In the past, classical Machine Learning/Deep Learning-based methods have been successfully investigated for the detection of falls. However, most of these methods require a lot of data in order to be successfully trained for accurate detection. In this work, we propose a shallow architecture using 1 × 1 filters for use in a few-shot Siamese network. The proposed architecture was used in a Siamese network-based fall detection system. The proposed detection system is shown to effectively learn feature representations for the detection of falls when trained with few signals acquired from wearables containing inertial motion unit (SisFall dataset). The proposed system achieved a performance of 93% ± 7% and 72.5% ± 10% in 15 and 1-shot scenarios respectively. Performance comparisons with Siamese convolutional autoencoders and transfer learning¬based approaches demonstrated the superiority of the proposed few shot fall detection system.
{"title":"Few-shot Fall Detection using Shallow Siamese Network","authors":"Satyake Bakshi, S. Rajan","doi":"10.1109/MeMeA52024.2021.9478605","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478605","url":null,"abstract":"The threat of falling down is significantly higher for the geriatric population and can lead to serious injuries including death. In the past, classical Machine Learning/Deep Learning-based methods have been successfully investigated for the detection of falls. However, most of these methods require a lot of data in order to be successfully trained for accurate detection. In this work, we propose a shallow architecture using 1 × 1 filters for use in a few-shot Siamese network. The proposed architecture was used in a Siamese network-based fall detection system. The proposed detection system is shown to effectively learn feature representations for the detection of falls when trained with few signals acquired from wearables containing inertial motion unit (SisFall dataset). The proposed system achieved a performance of 93% ± 7% and 72.5% ± 10% in 15 and 1-shot scenarios respectively. Performance comparisons with Siamese convolutional autoencoders and transfer learning¬based approaches demonstrated the superiority of the proposed few shot fall detection system.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126378011","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478753
J. Ahmadi-Farsani, Davide Caron, G. Panuccio, B. Linares-Barranco, T. Serrano-Gotarredona
This paper presents a biohybrid arrangement made of a commercial microelectrode array (MEA) system for seizure-like activity detection in brain slices. The set-up takes advantage of an embedded fixed-point digital signal processor (DSP) to implement a neuron model and a field-potential to spike converter (FP2SP). The neuron model is biologically plausible and capable of generating various firing modalities. Based on a three-step algorithm, FP2SP extracts spikes from the epileptiform activity generated by brain slices. The seizure detector system is developed by connecting the FP2SP to the model neuron and properly tuning the FP2SP parameters. The results show that all the blocks of this system can operate properly in real-time mode and recognize seizure-like activity.
{"title":"A Real-Time DSP-Based Biohybrid MEA System for Seizure Detection In Vitro","authors":"J. Ahmadi-Farsani, Davide Caron, G. Panuccio, B. Linares-Barranco, T. Serrano-Gotarredona","doi":"10.1109/MeMeA52024.2021.9478753","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478753","url":null,"abstract":"This paper presents a biohybrid arrangement made of a commercial microelectrode array (MEA) system for seizure-like activity detection in brain slices. The set-up takes advantage of an embedded fixed-point digital signal processor (DSP) to implement a neuron model and a field-potential to spike converter (FP2SP). The neuron model is biologically plausible and capable of generating various firing modalities. Based on a three-step algorithm, FP2SP extracts spikes from the epileptiform activity generated by brain slices. The seizure detector system is developed by connecting the FP2SP to the model neuron and properly tuning the FP2SP parameters. The results show that all the blocks of this system can operate properly in real-time mode and recognize seizure-like activity.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127020305","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478768
A. Tigrini, F. Verdini, S. Fioretti, R. Rabini, O. Mercante, A. Mengarelli
In this study Cross Teager-Kaiser (CTK) operator was employed to combine the two stabilogram components recorded during static posturography to generate a new time-series that describes the interaction among them. Then, such interaction was measured through a complexity index as Lemepel-Ziv. The method proposed would overcome some limitations that classical posturographic data analysis encounters in underlining differences among groups of subjects. This aspect is of great interest in the assessment of pathologies that affect the nervous system and its balance control strategies. The discriminative capability of the proposed method was evaluated through two assessments: the first aimed to highlight differences between young and elderly subjects; the second, more challenging, required to highlight differences between diabetic patients without neuropathy and diabetic patients with asymptomatic neuropathy. Wilcoxon-Mann-Whitney tests revealed that CTK combined with Lempel-Ziv index significantly differentiate the groups in the two assessments.
{"title":"Cross Teager-Kaiser operator and Lempel-Ziv Index for the assessment of human posturographic data","authors":"A. Tigrini, F. Verdini, S. Fioretti, R. Rabini, O. Mercante, A. Mengarelli","doi":"10.1109/MeMeA52024.2021.9478768","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478768","url":null,"abstract":"In this study Cross Teager-Kaiser (CTK) operator was employed to combine the two stabilogram components recorded during static posturography to generate a new time-series that describes the interaction among them. Then, such interaction was measured through a complexity index as Lemepel-Ziv. The method proposed would overcome some limitations that classical posturographic data analysis encounters in underlining differences among groups of subjects. This aspect is of great interest in the assessment of pathologies that affect the nervous system and its balance control strategies. The discriminative capability of the proposed method was evaluated through two assessments: the first aimed to highlight differences between young and elderly subjects; the second, more challenging, required to highlight differences between diabetic patients without neuropathy and diabetic patients with asymptomatic neuropathy. Wilcoxon-Mann-Whitney tests revealed that CTK combined with Lempel-Ziv index significantly differentiate the groups in the two assessments.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127989660","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478710
Pedram Fekri, Hamid Reza Nourani, M. Razban, J. Dargahi, Mehrdad Zadeh, A. Arshi
Having a real sense of the applied force in catheterization procedures can help surgeons with proper treatment for cardiovascular diseases. Using sensors is not common because of the limitations of catheters and complications related to the safety of patients. In this regard, a sensor free method can be deemed as a safe solution, in which it uses available equipment in the real operation room. In this work, we propose a deep learning method to estimate the contact forces directly from the catheters’ image tip without embedding further sensors. A convolutional neural network extracts the catheter’s deflections through input images and translates them into the corresponding forces. The architecture of the proposed model has been inspired by the ResNet graph so as to perform a regression. The model can make predictions based on the input images without utilizing any feature extraction or preprocessing steps. An experimental setup was designed and implemented to simulate catheter ablation therapy. Evaluation results show that the proposed method is able to elicit a robust model from the given dataset and approximate the force with proper accuracy. Opting RMSE as the preferred performance metric, the model reached 0.028 N and 0.023 N in estimation error in the x and y direction on the test data set, respectively.
{"title":"A Deep Learning Force Estimator System for Intracardiac Catheters","authors":"Pedram Fekri, Hamid Reza Nourani, M. Razban, J. Dargahi, Mehrdad Zadeh, A. Arshi","doi":"10.1109/MeMeA52024.2021.9478710","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478710","url":null,"abstract":"Having a real sense of the applied force in catheterization procedures can help surgeons with proper treatment for cardiovascular diseases. Using sensors is not common because of the limitations of catheters and complications related to the safety of patients. In this regard, a sensor free method can be deemed as a safe solution, in which it uses available equipment in the real operation room. In this work, we propose a deep learning method to estimate the contact forces directly from the catheters’ image tip without embedding further sensors. A convolutional neural network extracts the catheter’s deflections through input images and translates them into the corresponding forces. The architecture of the proposed model has been inspired by the ResNet graph so as to perform a regression. The model can make predictions based on the input images without utilizing any feature extraction or preprocessing steps. An experimental setup was designed and implemented to simulate catheter ablation therapy. Evaluation results show that the proposed method is able to elicit a robust model from the given dataset and approximate the force with proper accuracy. Opting RMSE as the preferred performance metric, the model reached 0.028 N and 0.023 N in estimation error in the x and y direction on the test data set, respectively.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133799501","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 : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478675
S. Korganbayev, S. Asadi, Inbal Maor, E. Schena, H. Azhari, I. Weitz, P. Saccomandi
Copper oxide nanoparticles (CuO-NPs) have the potential of serving as an anticancer theranostic agent with photothermal capabilities. In order to control their toxicity and release, the CuO NPs were encapsulated within polymeric nanospheres composed of poly(lactic-co-glycolic acid) (PLGA) core and polydopamine (PDA)/polyethylene glycol (PEG) shell. After the characterization of synthesized nanospheres, their photothermal response to different near-infrared laser sources (808 nm, 940 nm and 1064 nm) was assessed in terms of the measured temperature. Arrays of sub-millimetric fiber Bragg grating sensors were employed to achieve an optimal spatial resolution for resolving the temperature increase in samples embedding the nanospheres. The results have shown that the designed structure of CuO@PLGA/PDA/PEG nanospheres substantially augments the temperature elevation. A maximum of 30 °C temperature increase, in comparison with the control solution, was achieved for the 808 nm laser source. These results indicate that the designed structure of CuO@PLGA/PDA/PEG nanospheres is suitable for further applications towards chemo-photothermal therapy combined with diagnostic imaging for the treatment of cancer.
{"title":"Measurement of Enhanced Photothermal Effects of CuO-encapsulated Polymeric Nanospheres","authors":"S. Korganbayev, S. Asadi, Inbal Maor, E. Schena, H. Azhari, I. Weitz, P. Saccomandi","doi":"10.1109/MeMeA52024.2021.9478675","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478675","url":null,"abstract":"Copper oxide nanoparticles (CuO-NPs) have the potential of serving as an anticancer theranostic agent with photothermal capabilities. In order to control their toxicity and release, the CuO NPs were encapsulated within polymeric nanospheres composed of poly(lactic-co-glycolic acid) (PLGA) core and polydopamine (PDA)/polyethylene glycol (PEG) shell. After the characterization of synthesized nanospheres, their photothermal response to different near-infrared laser sources (808 nm, 940 nm and 1064 nm) was assessed in terms of the measured temperature. Arrays of sub-millimetric fiber Bragg grating sensors were employed to achieve an optimal spatial resolution for resolving the temperature increase in samples embedding the nanospheres. The results have shown that the designed structure of CuO@PLGA/PDA/PEG nanospheres substantially augments the temperature elevation. A maximum of 30 °C temperature increase, in comparison with the control solution, was achieved for the 808 nm laser source. These results indicate that the designed structure of CuO@PLGA/PDA/PEG nanospheres is suitable for further applications towards chemo-photothermal therapy combined with diagnostic imaging for the treatment of cancer.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131742572","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：