Pub Date : 2021-06-23DOI: 10.1109/MeMeA52024.2021.9478752
Ana Jiménez Martín, Ismael Miranda Gordo, David Gualda Gómez, S. G. D. Villa, Sergio Lluva Plaza, Juan Jesús García Domínguez
This work proposes a system to detect changes in daily routines in a controlled environment, such as a sensorized-home. Variations in routines can be indicative of physical or cognitive decline in elderly adults, which makes it very attractive to support independent living and healthy ageing. Our proposal is based on an indoor symbolic location system based on low-cost and easy-to-install Bluetooth Low Energy (BLE) transmitter beacons, together with a mobile receiver. The user's symbolic location is estimated from the Received Signal Strength Indicator (RSSI) and K-Nearest Neighbour (KNN) model, which is merged with the acceleration provided by the receiving mobile device. The location is used to estimate the time spent in each monitored room, to infer a time-based routine. The symbolic localization has an accuracy higher than 96%. The subsequent daily monitoring allows for the detection of variations with respect to a defined routine that can serve as an alarm for the user, family members or caregivers.
{"title":"BLE-based approach for detecting daily routine changes","authors":"Ana Jiménez Martín, Ismael Miranda Gordo, David Gualda Gómez, S. G. D. Villa, Sergio Lluva Plaza, Juan Jesús García Domínguez","doi":"10.1109/MeMeA52024.2021.9478752","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478752","url":null,"abstract":"This work proposes a system to detect changes in daily routines in a controlled environment, such as a sensorized-home. Variations in routines can be indicative of physical or cognitive decline in elderly adults, which makes it very attractive to support independent living and healthy ageing. Our proposal is based on an indoor symbolic location system based on low-cost and easy-to-install Bluetooth Low Energy (BLE) transmitter beacons, together with a mobile receiver. The user's symbolic location is estimated from the Received Signal Strength Indicator (RSSI) and K-Nearest Neighbour (KNN) model, which is merged with the acceleration provided by the receiving mobile device. The location is used to estimate the time spent in each monitored room, to infer a time-based routine. The symbolic localization has an accuracy higher than 96%. The subsequent daily monitoring allows for the detection of variations with respect to a defined routine that can serve as an alarm for the user, family members or caregivers.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"50 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":"132911743","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/MeMeA52024.2021.9478668
Michela Franzo', Simona Pascucci, M. Serrao, F. Marinozzi, F. Bini
The aim of this study is to evaluate the differences introduced by an update of implemented code between the two version of prototype for ataxic patients’ neurorehabilitation device. The rehabilitation consists in virtual exercise for the patient to improve his control of the upper arm during daily movement. The prototype is based on the Microsoft Kinect device to acquire subject’s position and on the Arduino board with accelerometer/gyroscope sensor to acquire kinematics quantities of the wrist during the task. Two subjects were analysed with 2.0 version of the prototype and they were compared to 2 of 20 subjects selected from the first control group to highlight the differences between the two versions.
{"title":"Kinect-based wearable prototype system for ataxic patients neurorehabilitation: software update for exergaming and rehabilitation","authors":"Michela Franzo', Simona Pascucci, M. Serrao, F. Marinozzi, F. Bini","doi":"10.1109/MeMeA52024.2021.9478668","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478668","url":null,"abstract":"The aim of this study is to evaluate the differences introduced by an update of implemented code between the two version of prototype for ataxic patients’ neurorehabilitation device. The rehabilitation consists in virtual exercise for the patient to improve his control of the upper arm during daily movement. The prototype is based on the Microsoft Kinect device to acquire subject’s position and on the Arduino board with accelerometer/gyroscope sensor to acquire kinematics quantities of the wrist during the task. Two subjects were analysed with 2.0 version of the prototype and they were compared to 2 of 20 subjects selected from the first control group to highlight the differences between the two versions.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"224 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":"134314530","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/MeMeA52024.2021.9478719
S. Behbahani, S. Rajan
Electroretinogram (ERG) is well-known for direct retinal function measurement. ERG responses to flicker stimulation can cause cyclic and oscillating changes in amplitude. Flicker response analyses are mostly based on amplitude and implicit time. However, non-linear analysis can also provide valuable information about the retinal function. In this paper, we investigate the flicker response using non-linear and chaotic features such as Approximate Entropy (ApEn), Hurst Exponent (HE), and Largest Lyapunov Exponent (LLE). Flicker responses were obtained from four groups with 16 subjects in each: one group with healthy subjects and three groups with central retinal vascular occlusion (CRVO), diabetic retinopathy (DR), and retinitis pigmentosa (RP) subjects, respectively. Statistical analysis shows that these non-linear and chaosbased features can distinguish the diseases and further indicate that the ERG has more complexity in healthy subjects than retinal disease subjects.
{"title":"Non-Linear and Chaos-based Analysis of Electroretinogram","authors":"S. Behbahani, S. Rajan","doi":"10.1109/MeMeA52024.2021.9478719","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478719","url":null,"abstract":"Electroretinogram (ERG) is well-known for direct retinal function measurement. ERG responses to flicker stimulation can cause cyclic and oscillating changes in amplitude. Flicker response analyses are mostly based on amplitude and implicit time. However, non-linear analysis can also provide valuable information about the retinal function. In this paper, we investigate the flicker response using non-linear and chaotic features such as Approximate Entropy (ApEn), Hurst Exponent (HE), and Largest Lyapunov Exponent (LLE). Flicker responses were obtained from four groups with 16 subjects in each: one group with healthy subjects and three groups with central retinal vascular occlusion (CRVO), diabetic retinopathy (DR), and retinitis pigmentosa (RP) subjects, respectively. Statistical analysis shows that these non-linear and chaosbased features can distinguish the diseases and further indicate that the ERG has more complexity in healthy subjects than retinal disease subjects.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"23 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":"116718017","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/MeMeA52024.2021.9478745
Mahsa Bahrami, M. Forouzanfar
Apnea is a prevalent sleep disorder which has detrimental impacts on human health and quality of life. Accurate automatic algorithms for the detection of sleep apnea are needed for analyzing long-term sleep data and monitoring and management of its side effects and consequences. Among different approaches for automatic detection of sleep apnea from biosignals, deep learning algorithms are of particular interest as, unlike conventional machine learning algorithms, they do not rely on expert crafted features. In this paper, we developed and evaluated a number of different deep learning models for the detection of sleep apnea from a single-lead electrocardiogram (ECG) signal. ECG R-peak amplitude and R-R intervals were extracted, and power spectral analysis was performed to align the R-peak amplitude and the R-R intervals in frequency domain. Convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM, gated recurrent unit, and deep hybrid models were implemented and analyzed. The performance of deep learning algorithms was evaluated on an apnea-ECG dataset of 70 recordings divided into a learning set of 35 records and a test of 35 records. The best accuracy, sensitivity, specificity, and F1-score on the test data were 80.67%, 75.04%, 84.13%, and 74.72%, respectively, with a hybrid CNN and LSTM network. The results show promise toward improved apnea detection using deep learning.
{"title":"Detection of Sleep Apnea from Single-Lead ECG: Comparison of Deep Learning Algorithms","authors":"Mahsa Bahrami, M. Forouzanfar","doi":"10.1109/MeMeA52024.2021.9478745","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478745","url":null,"abstract":"Apnea is a prevalent sleep disorder which has detrimental impacts on human health and quality of life. Accurate automatic algorithms for the detection of sleep apnea are needed for analyzing long-term sleep data and monitoring and management of its side effects and consequences. Among different approaches for automatic detection of sleep apnea from biosignals, deep learning algorithms are of particular interest as, unlike conventional machine learning algorithms, they do not rely on expert crafted features. In this paper, we developed and evaluated a number of different deep learning models for the detection of sleep apnea from a single-lead electrocardiogram (ECG) signal. ECG R-peak amplitude and R-R intervals were extracted, and power spectral analysis was performed to align the R-peak amplitude and the R-R intervals in frequency domain. Convolutional neural network (CNN), long short-term memory (LSTM), bidirectional LSTM, gated recurrent unit, and deep hybrid models were implemented and analyzed. The performance of deep learning algorithms was evaluated on an apnea-ECG dataset of 70 recordings divided into a learning set of 35 records and a test of 35 records. The best accuracy, sensitivity, specificity, and F1-score on the test data were 80.67%, 75.04%, 84.13%, and 74.72%, respectively, with a hybrid CNN and LSTM network. The results show promise toward improved apnea detection using deep learning.","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":"126398605","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/MeMeA52024.2021.9478688
Emanuele D'Angelantonio, Leandro Lucangeli, V. Camomilla, F. Mari, Guido Mascia, A. Pallotti
Telemedicine consists in the delivery of health care services, where patients and providers are separated by distance. Telemonitoring facilities play an important role in remote assistance programs, particularly in assisting patients suffering from chronic afflictions, such as phlebopathic diseases (e.g. chronic venous disease and diabetic foot). When these pathologies worsen, complications can be serious. In fact, foot deformities lead to variations of plantar load, formation of ulcers and, in the worst case, to amputation. Consequently, these pathologies cause huge expenses for the health care system. We propose a framework for screening and early detection of phlebopathic diseases insurgence, based on dynamic tests for functional assessment where patients wear sensorized socks. Socks used in this study integrate force and inertial sensors to provide information on plantar pressures and person’s movement. We show results of a feasibility study including 42 patients, with a balance of 21 healthy patients and 21 with phlebopathic diseases. Data gathered from wearables were automatically elaborated through machine learning techniques in order to obtain a binary classifier identifying whether or not a patient shows pathological gait. Results show that our best classifier has high positive predictive value and high sensitivity, with F1-score equal to 92.1%.
{"title":"Classification-Based Screening of Phlebopathic Patients using Smart Socks","authors":"Emanuele D'Angelantonio, Leandro Lucangeli, V. Camomilla, F. Mari, Guido Mascia, A. Pallotti","doi":"10.1109/MeMeA52024.2021.9478688","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478688","url":null,"abstract":"Telemedicine consists in the delivery of health care services, where patients and providers are separated by distance. Telemonitoring facilities play an important role in remote assistance programs, particularly in assisting patients suffering from chronic afflictions, such as phlebopathic diseases (e.g. chronic venous disease and diabetic foot). When these pathologies worsen, complications can be serious. In fact, foot deformities lead to variations of plantar load, formation of ulcers and, in the worst case, to amputation. Consequently, these pathologies cause huge expenses for the health care system. We propose a framework for screening and early detection of phlebopathic diseases insurgence, based on dynamic tests for functional assessment where patients wear sensorized socks. Socks used in this study integrate force and inertial sensors to provide information on plantar pressures and person’s movement. We show results of a feasibility study including 42 patients, with a balance of 21 healthy patients and 21 with phlebopathic diseases. Data gathered from wearables were automatically elaborated through machine learning techniques in order to obtain a binary classifier identifying whether or not a patient shows pathological gait. Results show that our best classifier has high positive predictive value and high sensitivity, with F1-score equal to 92.1%.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"82 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":"121122560","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/MeMeA52024.2021.9478735
E. Digo, E. Panero, V. Agostini, L. Gastaldi
The increasing average age of the population emphasizes the strong correlation between cognitive decline and gait disorders of elderly people. Wearable technologies such as magnetic inertial measurement units (MIMUs) have been ascertained as a suitable solution for gait analysis. However, the relationship between human motion and cognitive impairments should still be investigated, considering outcomes of different MIMU set-ups. Accordingly, the aim of the present study was to compare single-task and dual-task walking of an elderly population by using three different MIMU set-ups and correlated algorithms (trunk, shanks, and ankles). Gait sessions of sixteen healthy elderly subjects were registered and spatio-temporal parameters were selected as outcomes of interest. The analysis focused both on the comparison of walking conditions and on the evaluation of differences among MIMU set-ups. Results pointed out the significant effect of cognition on walking speed (p = 0.03) and temporal parameters (p ≤ 0.05), but not on the symmetry of gait. In addition, the comparison among MIMU configurations highlighted a significant difference in the detection of gait stance and swing phases (for shanks-ankles comparison p < 0.001 in both single and dual tasks, for trunk-ankles comparison p < 0.001 in single task and p < 0.01 in dual task). Overall, cognitive impact and MIMU set-ups revealed to be fundamental aspects in the analysis of gait spatio-temporal parameters in a healthy elderly population.
{"title":"Gait Parameters of Elderly Subjects in Single-task and Dual-task with three different MIMU set-ups","authors":"E. Digo, E. Panero, V. Agostini, L. Gastaldi","doi":"10.1109/MeMeA52024.2021.9478735","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478735","url":null,"abstract":"The increasing average age of the population emphasizes the strong correlation between cognitive decline and gait disorders of elderly people. Wearable technologies such as magnetic inertial measurement units (MIMUs) have been ascertained as a suitable solution for gait analysis. However, the relationship between human motion and cognitive impairments should still be investigated, considering outcomes of different MIMU set-ups. Accordingly, the aim of the present study was to compare single-task and dual-task walking of an elderly population by using three different MIMU set-ups and correlated algorithms (trunk, shanks, and ankles). Gait sessions of sixteen healthy elderly subjects were registered and spatio-temporal parameters were selected as outcomes of interest. The analysis focused both on the comparison of walking conditions and on the evaluation of differences among MIMU set-ups. Results pointed out the significant effect of cognition on walking speed (p = 0.03) and temporal parameters (p ≤ 0.05), but not on the symmetry of gait. In addition, the comparison among MIMU configurations highlighted a significant difference in the detection of gait stance and swing phases (for shanks-ankles comparison p < 0.001 in both single and dual tasks, for trunk-ankles comparison p < 0.001 in single task and p < 0.01 in dual task). Overall, cognitive impact and MIMU set-ups revealed to be fundamental aspects in the analysis of gait spatio-temporal parameters in a healthy elderly population.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"53 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":"114278748","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/MeMeA52024.2021.9478769
L. Svobodová, R. Janca, P. Jiruška
An ischemic stroke is a local lesion that disrupts the large-scale structural and functional connectivity of the brain. Although local, the ischemic stroke often leads to deficits in cognitive functions which can’t be explained by local brain damage. It is believed that stroke-induced large-scale network alteration represents the mechanisms responsible for a decline in cognitive functions which are dependent on large-scale integration. To gain insight into the pathophysiological principles of how a local lesion results in a global cognitive decline requires a reliable and robust algorithm that can quantify the relationship between cognitive functions and network properties. In this study, we have developed, optimized, and tested a processing pipeline to parameterize complex neuropsychological evaluation and determine the functional connectivity from high-density EEG recordings. The developed algorithm was applied on a cohort of 27 patients who suffered a stroke and who were underwent cognitive examinations and high-density EEG monitoring one and two years after the stroke. The developed automatic algorithm demonstrated that it can reliably estimate functional connectivity and that it is robust against the physiological and technical artifacts. The proposed processing pipeline allows an unbiased and quantitative characterization of cognitive performance and its comparison with functional connectivity alterations.
{"title":"Automatic processing protocol to evaluate the impact of functional network damage and reorganization on cognitive functions after stroke","authors":"L. Svobodová, R. Janca, P. Jiruška","doi":"10.1109/MeMeA52024.2021.9478769","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478769","url":null,"abstract":"An ischemic stroke is a local lesion that disrupts the large-scale structural and functional connectivity of the brain. Although local, the ischemic stroke often leads to deficits in cognitive functions which can’t be explained by local brain damage. It is believed that stroke-induced large-scale network alteration represents the mechanisms responsible for a decline in cognitive functions which are dependent on large-scale integration. To gain insight into the pathophysiological principles of how a local lesion results in a global cognitive decline requires a reliable and robust algorithm that can quantify the relationship between cognitive functions and network properties. In this study, we have developed, optimized, and tested a processing pipeline to parameterize complex neuropsychological evaluation and determine the functional connectivity from high-density EEG recordings. The developed algorithm was applied on a cohort of 27 patients who suffered a stroke and who were underwent cognitive examinations and high-density EEG monitoring one and two years after the stroke. The developed automatic algorithm demonstrated that it can reliably estimate functional connectivity and that it is robust against the physiological and technical artifacts. The proposed processing pipeline allows an unbiased and quantitative characterization of cognitive performance and its comparison with functional connectivity alterations.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"40 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":"122565716","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/MeMeA52024.2021.9478770
S. Casaccia, G. M. Revel, L. Scalise, Giacomo Cucchieri, L. Rossi
This paper is focused on identifying the accuracy of smartwatches (SWs) on the measurement of number of steps. Five SWs have been identified based on technical characteristics and costs from a list of 32 SWs available on the market. A metrological characterization on the selected SWs has been made on six subjects wearing all the SWs and doing walking activity with natural, slow and fast pace. R, R2 and statistical confidence, with coverage factor equal to 2, are computed considering videos as reference system to identify the number of steps. The overall statistical confidence is 4.2% for natural pace, 7.5% for the slow pace and 7.1% for the fast pace.
{"title":"Smartwatches selection: market analysis and metrological characterization on the measurement of number of steps","authors":"S. Casaccia, G. M. Revel, L. Scalise, Giacomo Cucchieri, L. Rossi","doi":"10.1109/MeMeA52024.2021.9478770","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478770","url":null,"abstract":"This paper is focused on identifying the accuracy of smartwatches (SWs) on the measurement of number of steps. Five SWs have been identified based on technical characteristics and costs from a list of 32 SWs available on the market. A metrological characterization on the selected SWs has been made on six subjects wearing all the SWs and doing walking activity with natural, slow and fast pace. R, R2 and statistical confidence, with coverage factor equal to 2, are computed considering videos as reference system to identify the number of steps. The overall statistical confidence is 4.2% for natural pace, 7.5% for the slow pace and 7.1% for the fast pace.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"104 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":"124192657","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/MeMeA52024.2021.9478607
Xingxing Liu, Tri Quang, Wenxiang Deng, Yang Liu
Fluorescence imaging has been widely utilized in various clinical applications. As a functional imaging modality, NIR fluorescence imaging often does not offer sufficient structural details. Therefore, structural imaging such as color reflectance overlaid with fluorescence imaging represents a superior approach for surgical visualization. Image registration of color reflectance and NIR fluorescence is needed for accurate overlay. In this study, we have implemented a deep convolutional algorithm for feature-based fluorescence-to-color image registration. Software-hardware codesign was conducted. Several sets of experiments were performed on biological tissues to compare the performance of our algorithm and traditional methods. We have demonstrated the feasibility of deep convolutional feature-based fluorescence-to-color image registration. To our best knowledge, this is the first demonstration of deep learning-based image registration between fluorescence and color imageries.
{"title":"Deep Convolutional Feature-Based Fluorescence-to-Color Image Registration","authors":"Xingxing Liu, Tri Quang, Wenxiang Deng, Yang Liu","doi":"10.1109/MeMeA52024.2021.9478607","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478607","url":null,"abstract":"Fluorescence imaging has been widely utilized in various clinical applications. As a functional imaging modality, NIR fluorescence imaging often does not offer sufficient structural details. Therefore, structural imaging such as color reflectance overlaid with fluorescence imaging represents a superior approach for surgical visualization. Image registration of color reflectance and NIR fluorescence is needed for accurate overlay. In this study, we have implemented a deep convolutional algorithm for feature-based fluorescence-to-color image registration. Software-hardware codesign was conducted. Several sets of experiments were performed on biological tissues to compare the performance of our algorithm and traditional methods. We have demonstrated the feasibility of deep convolutional feature-based fluorescence-to-color image registration. To our best knowledge, this is the first demonstration of deep learning-based image registration between fluorescence and color imageries.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"58 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":"114615649","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/MeMeA52024.2021.9478724
A. Inuggi, Alessia Tonelli, M. Gori
We present PsySuite, an Android App designed to perform multimodal behavioral tests in the temporal domain. This class of tests consists in delivering either unimodal or multimodal visual, acoustic and tactile stimuli and asking participants to evaluate their temporal features: duration, temporal distance between stimuli and simultaneity across different modalities. The accuracy and reproducibility of our stimuli production mechanism was evaluated with an oscilloscope on two different smartphones models. Then, we validated the App running two versions of the double-flash illusion (DFI) test in seven healthy adults. DFI was selected as it induces a perceptual illusion only when stimuli are precisely delivered within few milliseconds. We found the App could reliably produce stimuli with a minimum duration of 7 ms, 17 ms and 35 ms respectively for acoustic, visual and tactile stimuli. Oboe library outclassed AudioTrack solution in playing pairs of sounds, whilst visual and tactile performance was highly dependent on the smartphone’s model used. In the DFI test using "long" stimuli (35 ms) we did not find the flash illusion effect. We could run the "short" (audio: 7 ms, visual: 17 ms) stimuli version only with audio-visual stimuli and we found a strong effect consistent with the literature using classical experimental, PC-based, setups. These results suggest that our PsySuite App can be used to run highly demanding audio-visual psychophysics experiments obtaining the same effect found with classical setups.
{"title":"PsySuite, an Android App for behavioural tests in the temporal domain","authors":"A. Inuggi, Alessia Tonelli, M. Gori","doi":"10.1109/MeMeA52024.2021.9478724","DOIUrl":"https://doi.org/10.1109/MeMeA52024.2021.9478724","url":null,"abstract":"We present PsySuite, an Android App designed to perform multimodal behavioral tests in the temporal domain. This class of tests consists in delivering either unimodal or multimodal visual, acoustic and tactile stimuli and asking participants to evaluate their temporal features: duration, temporal distance between stimuli and simultaneity across different modalities. The accuracy and reproducibility of our stimuli production mechanism was evaluated with an oscilloscope on two different smartphones models. Then, we validated the App running two versions of the double-flash illusion (DFI) test in seven healthy adults. DFI was selected as it induces a perceptual illusion only when stimuli are precisely delivered within few milliseconds. We found the App could reliably produce stimuli with a minimum duration of 7 ms, 17 ms and 35 ms respectively for acoustic, visual and tactile stimuli. Oboe library outclassed AudioTrack solution in playing pairs of sounds, whilst visual and tactile performance was highly dependent on the smartphone’s model used. In the DFI test using \"long\" stimuli (35 ms) we did not find the flash illusion effect. We could run the \"short\" (audio: 7 ms, visual: 17 ms) stimuli version only with audio-visual stimuli and we found a strong effect consistent with the literature using classical experimental, PC-based, setups. These results suggest that our PsySuite App can be used to run highly demanding audio-visual psychophysics experiments obtaining the same effect found with classical setups.","PeriodicalId":429222,"journal":{"name":"2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"18 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":"115153927","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：