Objective: People with blindness and low vision face substantial challenges when navigating both indoor and outdoor environments. While various solutions are available to facilitate travel to and from public transit hubs, there is a notable absence of solutions for navigating within transit hubs, often referred to as the “middle mile”. Although research pilots have explored the middle mile journey, no solutions exist at scale, leaving a critical gap for commuters with disabilities. In this paper, we proposed a novel mobile application, Commute Booster, that offers full trip planning and real-time guidance inside the station. Methods and procedures: Our system consists of two key components: the general transit feed specification (GTFS) and optical character recognition (OCR). The GTFS dataset generates a comprehensive list of wayfinding signage within subway stations that users will encounter during their intended journey. The OCR functionality enables users to identify relevant navigation signs in their immediate surroundings. By seamlessly integrating these two components, Commute Booster provides real-time feedback to users regarding the presence or absence of relevant navigation signs within the field of view of their phone camera during their journey. Results: As part of our technical validation process, we conducted tests at three subway stations in New York City. The sign detection achieved an impressive overall accuracy rate of 0.97. Additionally, the system exhibited a maximum detection range of 11 meters and supported an oblique angle of approximately 110 degrees for field of view detection. Conclusion: The Commute Booster mobile application relies on computer vision technology and does not require additional sensors or infrastructure. It holds tremendous promise in assisting individuals with blindness and low vision during their daily commutes. Clinical and Translational Impact Statement: Commute Booster translates the combination of OCR and GTFS into an assistive tool, which holds great promise for assisting people with blindness and low vision in their daily commute.
{"title":"Commute Booster: A Mobile Application for First/Last Mile and Middle Mile Navigation Support for People With Blindness and Low Vision","authors":"Junchi Feng;Mahya Beheshti;Mira Philipson;Yuvraj Ramsaywack;Maurizio Porfiri;John-Ross Rizzo","doi":"10.1109/JTEHM.2023.3293450","DOIUrl":"10.1109/JTEHM.2023.3293450","url":null,"abstract":"Objective: People with blindness and low vision face substantial challenges when navigating both indoor and outdoor environments. While various solutions are available to facilitate travel to and from public transit hubs, there is a notable absence of solutions for navigating within transit hubs, often referred to as the “middle mile”. Although research pilots have explored the middle mile journey, no solutions exist at scale, leaving a critical gap for commuters with disabilities. In this paper, we proposed a novel mobile application, Commute Booster, that offers full trip planning and real-time guidance inside the station. Methods and procedures: Our system consists of two key components: the general transit feed specification (GTFS) and optical character recognition (OCR). The GTFS dataset generates a comprehensive list of wayfinding signage within subway stations that users will encounter during their intended journey. The OCR functionality enables users to identify relevant navigation signs in their immediate surroundings. By seamlessly integrating these two components, Commute Booster provides real-time feedback to users regarding the presence or absence of relevant navigation signs within the field of view of their phone camera during their journey. Results: As part of our technical validation process, we conducted tests at three subway stations in New York City. The sign detection achieved an impressive overall accuracy rate of 0.97. Additionally, the system exhibited a maximum detection range of 11 meters and supported an oblique angle of approximately 110 degrees for field of view detection. Conclusion: The Commute Booster mobile application relies on computer vision technology and does not require additional sensors or infrastructure. It holds tremendous promise in assisting individuals with blindness and low vision during their daily commutes. Clinical and Translational Impact Statement: Commute Booster translates the combination of OCR and GTFS into an assistive tool, which holds great promise for assisting people with blindness and low vision in their daily commute.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"523-535"},"PeriodicalIF":3.4,"publicationDate":"2023-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10175612","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62231443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-07-03DOI: 10.1109/JTEHM.2023.3291925
Jan-Willem Klok;Roelf Postema;Asþor T. Steinþorsson;Jenny Dankelman;Tim Horeman
In laparoscopic surgery, quality of haptic feedback is reduced compared to conventional surgery, leading to unintentional tissue damage during grasping. From the perspective of haptics, poor mechanical design of laparoscopic instrument joints induces friction and a nonlinear actuation-tip force relation. In this study, a novel laparoscopic grasper using compliant joints and a magnetic balancer is presented, and the reduction in hysteresis and friction is evaluated. The hysteresis loop of the novel compliant grasper and two conventional laparoscopic graspers (high quality leading commercial brand and low quality unbranded grasper) were measured. In order to assess quality of haptic feedback, the lowest grasper tip load perceivable by instrument users was measured with the novel and the conventional laparoscopic graspers. The hysteresis loop measurement yielded a mechanical efficiency of 43% for the novel grasper, compared to- 25% and 23% for the Aesculap and the unbranded grasper, respectively. The forces perceivable by the user through the novel grasper were significantly lower (mean 1.37N, SD 0.44N) than those of conventional graspers (mean 2.15N, SD 0.71N and mean 2.65N, SD 1.20N, respectively). The balanced compliant grasper technology has the ability to improve the quality of haptic feedback compared to conventional laparoscopic graspers. Research is needed to relate these results to soft and delicate tissue grasping in a clinical setting, for which this instrument is intended.
{"title":"Design and Evaluation of a Balanced Compliant Laparoscopic Grasper","authors":"Jan-Willem Klok;Roelf Postema;Asþor T. Steinþorsson;Jenny Dankelman;Tim Horeman","doi":"10.1109/JTEHM.2023.3291925","DOIUrl":"10.1109/JTEHM.2023.3291925","url":null,"abstract":"In laparoscopic surgery, quality of haptic feedback is reduced compared to conventional surgery, leading to unintentional tissue damage during grasping. From the perspective of haptics, poor mechanical design of laparoscopic instrument joints induces friction and a nonlinear actuation-tip force relation. In this study, a novel laparoscopic grasper using compliant joints and a magnetic balancer is presented, and the reduction in hysteresis and friction is evaluated. The hysteresis loop of the novel compliant grasper and two conventional laparoscopic graspers (high quality leading commercial brand and low quality unbranded grasper) were measured. In order to assess quality of haptic feedback, the lowest grasper tip load perceivable by instrument users was measured with the novel and the conventional laparoscopic graspers. The hysteresis loop measurement yielded a mechanical efficiency of 43% for the novel grasper, compared to- 25% and 23% for the Aesculap and the unbranded grasper, respectively. The forces perceivable by the user through the novel grasper were significantly lower (mean 1.37N, SD 0.44N) than those of conventional graspers (mean 2.15N, SD 0.71N and mean 2.65N, SD 1.20N, respectively). The balanced compliant grasper technology has the ability to improve the quality of haptic feedback compared to conventional laparoscopic graspers. Research is needed to relate these results to soft and delicate tissue grasping in a clinical setting, for which this instrument is intended.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"451-459"},"PeriodicalIF":3.4,"publicationDate":"2023-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10172011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41220007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Cardiopulmonary bypass (CPB) is an indispensable technique in cardiac surgery, providing the ability to temporarily replace cardiopulmonary function and create a bloodless surgical field. Traditionally, the operation of CPB systems has depended on the expertise and experience of skilled perfusionists. In particular, simultaneously controlling the arterial and venous occluders is difficult because the blood flow rate and reservoir level both change, and failure may put the patient’s life at risk. This study proposes an automatic control system with a two-degree-of-freedom model matching controller nested in an I-PD feedback controller to simultaneously regulate the blood flow rate and reservoir level. CPB operations were performed using glycerin and bovine blood as perfusate to simulate flow-up and flow-down phases. The results confirmed that the arterial blood flow rate followed the manually adjusted target venous blood flow rate, with an error of less than 5.32%, and the reservoir level was maintained, with an error of less than 3.44% from the target reservoir level. Then, we assessed the robustness of the control system against disturbances caused by venting/suction of blood. The resulting flow rate error was 5.95%, and the reservoir level error 2.02%. The accuracy of the proposed system is clinically satisfactory and within the allowable error range of 10% or less, meeting the standards set for perfusionists. Moreover, because of the system’s simple configuration, consisting of a camera and notebook PC, the system can easily be integrated with general CPB equipment. This practical design enables seamless adoption in clinical settings. With these advancements, the proposed system represents a significant step towards the automation of CPB.
{"title":"Simultaneous Control of Venous Reservoir Level and Arterial Flow Rate in Cardiopulmonary Bypass With a Centrifugal Pump","authors":"Hidenobu Takahashi;Takuya Kinoshita;Zu Soh;Shigeyuki Okahara;Satoshi Miyamoto;Shinji Ninomiya;Toshio Tsuji","doi":"10.1109/JTEHM.2023.3290951","DOIUrl":"10.1109/JTEHM.2023.3290951","url":null,"abstract":"Cardiopulmonary bypass (CPB) is an indispensable technique in cardiac surgery, providing the ability to temporarily replace cardiopulmonary function and create a bloodless surgical field. Traditionally, the operation of CPB systems has depended on the expertise and experience of skilled perfusionists. In particular, simultaneously controlling the arterial and venous occluders is difficult because the blood flow rate and reservoir level both change, and failure may put the patient’s life at risk. This study proposes an automatic control system with a two-degree-of-freedom model matching controller nested in an I-PD feedback controller to simultaneously regulate the blood flow rate and reservoir level. CPB operations were performed using glycerin and bovine blood as perfusate to simulate flow-up and flow-down phases. The results confirmed that the arterial blood flow rate followed the manually adjusted target venous blood flow rate, with an error of less than 5.32%, and the reservoir level was maintained, with an error of less than 3.44% from the target reservoir level. Then, we assessed the robustness of the control system against disturbances caused by venting/suction of blood. The resulting flow rate error was 5.95%, and the reservoir level error 2.02%. The accuracy of the proposed system is clinically satisfactory and within the allowable error range of 10% or less, meeting the standards set for perfusionists. Moreover, because of the system’s simple configuration, consisting of a camera and notebook PC, the system can easily be integrated with general CPB equipment. This practical design enables seamless adoption in clinical settings. With these advancements, the proposed system represents a significant step towards the automation of CPB.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"435-440"},"PeriodicalIF":3.4,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10168928","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9945552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Epilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures is the result of temporal and spatial evolution, Existing deep learning methods often ignore its spatial features, in order to make better use of the temporal and spatial characteristics of epileptic EEG signals. We propose a CBAM-3D CNN-LSTM model to predict epilepsy seizures. First, we apply short-time Fourier transform(STFT) to preprocess EEG signals. Secondly, the 3D CNN model was used to extract the features of preictal stage and interictal stage from the preprocessed signals. Thirdly, Bi-LSTM is connected to 3D CNN for classification. Finally CBAM is introduced into the model. Different attention is given to the data channel and space to extract key information, so that the model can accurately extract interictal and pre-ictal features. Our proposed approach achieved an accuracy of 97.95%, a sensitivity of 98.40%, and a false alarm rate of 0.017 h −1 on 11 patients from the public CHB-MIT scalp EEG dataset. Clinical and Translational Impact Statement —Timely prediction of epileptic seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients.
{"title":"An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model","authors":"Xiang Lu;Anhao Wen;Lei Sun;Hao Wang;Yinjing Guo;Yande Ren","doi":"10.1109/JTEHM.2023.3290036","DOIUrl":"10.1109/JTEHM.2023.3290036","url":null,"abstract":"Epilepsy as a common disease of the nervous system, with high incidence, sudden and recurrent characteristics. Therefore, timely prediction of seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients. Epilepsy seizures is the result of temporal and spatial evolution, Existing deep learning methods often ignore its spatial features, in order to make better use of the temporal and spatial characteristics of epileptic EEG signals. We propose a CBAM-3D CNN-LSTM model to predict epilepsy seizures. First, we apply short-time Fourier transform(STFT) to preprocess EEG signals. Secondly, the 3D CNN model was used to extract the features of preictal stage and interictal stage from the preprocessed signals. Thirdly, Bi-LSTM is connected to 3D CNN for classification. Finally CBAM is introduced into the model. Different attention is given to the data channel and space to extract key information, so that the model can accurately extract interictal and pre-ictal features. Our proposed approach achieved an accuracy of 97.95%, a sensitivity of 98.40%, and a false alarm rate of 0.017 h\u0000<sup>−1</sup>\u0000 on 11 patients from the public CHB-MIT scalp EEG dataset. \u0000<italic><b>Clinical and Translational Impact Statement</b></i>\u0000—Timely prediction of epileptic seizures and intervention treatment can significantly reduce the accidental injury of patients and protect the life and health of patients.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"417-423"},"PeriodicalIF":3.4,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10164022","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9814105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Background: In the past few years, U-Net based U-shaped architecture and skip-connections have made incredible progress in the field of medical image segmentation. U 2 -Net achieves good performance in computer vision. However, in the medical image segmentation task, U 2 -Net with over nesting is easy to overfit. Purpose: A 2D network structure TransU 2 -Net combining transformer and a lighter weight U 2 -Net is proposed for automatic segmentation of brain tumor magnetic resonance image (MRI). Methods: The light-weight U 2 -Net architecture not only obtains multi-scale information but also reduces redundant feature extraction. Meanwhile, the transformer block embedded in the stacked convolutional layer obtains more global information; the transformer with skip-connection enhances spatial domain information representation. A new multi-scale feature map fusion strategy as a postprocessing method was proposed for better fusing high and low-dimensional spatial information. Results: Our proposed model TransU 2 -Net achieves better segmentation results, on the BraTS2021 dataset, our method achieves an average dice coefficient of 88.17%; Evaluation on the publicly available MSD dataset, we perform tumor evaluation, we achieve a dice coefficient of 74.69%; in addition to comparing the TransU 2 -Net results are compared with previously proposed 2D segmentation methods. Conclusions: We propose an automatic medical image segmentation method combining transformers and U 2 -Net, which has good performance and is of clinical importance. The experimental results show that the proposed method outperforms other 2D medical image segmentation methods. Clinical Translation Statement : We use the BarTS2021 dataset and the MSD dataset which are publicly available databases. All experiments in this paper are in accordance with medical ethics.
{"title":"TransU²-Net: An Effective Medical Image Segmentation Framework Based on Transformer and U²-Net","authors":"Xiang Li;Xianjin Fang;Gaoming Yang;Shuzhi Su;Li Zhu;Zekuan Yu","doi":"10.1109/JTEHM.2023.3289990","DOIUrl":"10.1109/JTEHM.2023.3289990","url":null,"abstract":"Background: In the past few years, U-Net based U-shaped architecture and skip-connections have made incredible progress in the field of medical image segmentation. U\u0000<sup>2</sup>\u0000-Net achieves good performance in computer vision. However, in the medical image segmentation task, U\u0000<sup>2</sup>\u0000-Net with over nesting is easy to overfit. Purpose: A 2D network structure TransU\u0000<sup>2</sup>\u0000-Net combining transformer and a lighter weight U\u0000<sup>2</sup>\u0000-Net is proposed for automatic segmentation of brain tumor magnetic resonance image (MRI). Methods: The light-weight U\u0000<sup>2</sup>\u0000-Net architecture not only obtains multi-scale information but also reduces redundant feature extraction. Meanwhile, the transformer block embedded in the stacked convolutional layer obtains more global information; the transformer with skip-connection enhances spatial domain information representation. A new multi-scale feature map fusion strategy as a postprocessing method was proposed for better fusing high and low-dimensional spatial information. Results: Our proposed model TransU\u0000<sup>2</sup>\u0000-Net achieves better segmentation results, on the BraTS2021 dataset, our method achieves an average dice coefficient of 88.17%; Evaluation on the publicly available MSD dataset, we perform tumor evaluation, we achieve a dice coefficient of 74.69%; in addition to comparing the TransU\u0000<sup>2</sup>\u0000-Net results are compared with previously proposed 2D segmentation methods. Conclusions: We propose an automatic medical image segmentation method combining transformers and U\u0000<sup>2</sup>\u0000-Net, which has good performance and is of clinical importance. The experimental results show that the proposed method outperforms other 2D medical image segmentation methods. \u0000<bold>Clinical Translation Statement</b>\u0000: We use the BarTS2021 dataset and the MSD dataset which are publicly available databases. All experiments in this paper are in accordance with medical ethics.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"441-450"},"PeriodicalIF":3.4,"publicationDate":"2023-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/75/25/jtehm-fang-3289990.PMC10561737.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41220010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: Common bile duct (CBD) stones caused diseases are life-threatening. Because CBD stones locate in the distal part of the CBD and have relatively small sizes, detecting CBD stones from CT scans is a challenging issue in the medical domain. Methods and procedures: We propose a deep learning based weakly-supervised method called multiple field-of-view based attention driven network (MFADNet) to detect CBD stones from CT scans based on image-level labels. Three dominant modules including a multiple field-of-view encoder, an attention driven decoder and a classification network are collaborated in the network. The encoder learns the feature of multi-scale contextual information while the decoder with the classification network is applied to locate the CBD stones based on spatial-channel attentions. To drive the learning of the whole network in a weakly-supervised and end-to-end trainable manner, four losses including the foreground loss, background loss, consistency loss and classification loss are proposed. Results: Compared with state-of-the-art weakly-supervised methods in the experiments, the proposed method can accurately classify and locate CBD stones based on the quantitative and qualitative results. Conclusion: We propose a novel multiple field-of-view based attention driven network for a new medical application of CBD stone detection from CT scans while only image-levels are required to reduce the burdens of labeling and help physicians automatically diagnose CBD stones. The source code is available at https://github.com/nchucvml/MFADNet after acceptance. Clinical impact: Our deep learning method can help physicians localize relatively small CBD stones for effectively diagnosing CBD stone caused diseases.
{"title":"Multiple Field-of-View Based Attention Driven Network for Weakly Supervised Common Bile Duct Stone Detection","authors":"Ya-Han Chang;Meng-Ying Lin;Ming-Tsung Hsieh;Ming-Ching Ou;Chun-Rong Huang;Bor-Shyang Sheu","doi":"10.1109/JTEHM.2023.3286423","DOIUrl":"10.1109/JTEHM.2023.3286423","url":null,"abstract":"Objective: Common bile duct (CBD) stones caused diseases are life-threatening. Because CBD stones locate in the distal part of the CBD and have relatively small sizes, detecting CBD stones from CT scans is a challenging issue in the medical domain. Methods and procedures: We propose a deep learning based weakly-supervised method called multiple field-of-view based attention driven network (MFADNet) to detect CBD stones from CT scans based on image-level labels. Three dominant modules including a multiple field-of-view encoder, an attention driven decoder and a classification network are collaborated in the network. The encoder learns the feature of multi-scale contextual information while the decoder with the classification network is applied to locate the CBD stones based on spatial-channel attentions. To drive the learning of the whole network in a weakly-supervised and end-to-end trainable manner, four losses including the foreground loss, background loss, consistency loss and classification loss are proposed. Results: Compared with state-of-the-art weakly-supervised methods in the experiments, the proposed method can accurately classify and locate CBD stones based on the quantitative and qualitative results. Conclusion: We propose a novel multiple field-of-view based attention driven network for a new medical application of CBD stone detection from CT scans while only image-levels are required to reduce the burdens of labeling and help physicians automatically diagnose CBD stones. The source code is available at \u0000<uri>https://github.com/nchucvml/MFADNet</uri>\u0000 after acceptance. Clinical impact: Our deep learning method can help physicians localize relatively small CBD stones for effectively diagnosing CBD stone caused diseases.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"394-404"},"PeriodicalIF":3.4,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10153581","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9854605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-13DOI: 10.1109/JTEHM.2023.3285723
Zongshuai Qu;Tao Yao;Xinghui Liu;Gang Wang
Objective: Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative disease that is not easily detectable in the early stage. This study proposed an efficient method of applying a graph convolutional network (GCN) on the early prediction of AD. Methods: We proposed a univariate neurodegeneration biomarker (UNB) based GCN semi-supervised classification framework. We generated UNB by comparing the similarity of individual morphological atrophy pattern and the atrophy pattern of $text{A}beta +$ AD group according to the brain morphological abnormalities induced by AD. For the GCN semi-supervised classification model, we took the UNBs of individuals as the features of nodes and constructed the weight of edges according to the similarity of phenotypic information between individuals, which explored the essential features of individuals through spectral graph convolution. The attention module was constructed and embedded into the GCN framework, which may refine the input morphological features to highlight the main impact of AD on the cerebral cortex and weaken the instability caused by individual diversities, thereby identifying the significant ROIs affected by AD and improving the classification accuracy. Results: We tested the UNB-GCN framework on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The estimated minimum sample sizes were 156, 349 and 423 for the longitudinal $text{A}beta +$ AD, $text{A}beta +$ mild cognitive impairment (MCI) and $text{A}beta +$ cognitively unimpaired (CU) groups, respectively. And the proposed UNB-GCN framework combined with the attention module can effectively improve the classification performance with 93.90% classification accuracy for AD vs. CU and 82.05% for AD vs. MCI on the validation set. Conclusion: The proposed UNB measures were superior to the conventional volume measures in describing the AD-induced cerebral cortex morphological changes. And the UNB-GCN framework combined with attention module may effectively improve the classification performance between MCI subjects and AD patients. Clinical and Translational Impact Statement: This study aims to predict the early AD patients, so as to help clinicians develop effective interventions to delay the deterioration of AD symptoms.
{"title":"A Graph Convolutional Network Based on Univariate Neurodegeneration Biomarker for Alzheimer’s Disease Diagnosis","authors":"Zongshuai Qu;Tao Yao;Xinghui Liu;Gang Wang","doi":"10.1109/JTEHM.2023.3285723","DOIUrl":"10.1109/JTEHM.2023.3285723","url":null,"abstract":"Objective: Alzheimer’s disease (AD) is a progressive and irreversible neurodegenerative disease that is not easily detectable in the early stage. This study proposed an efficient method of applying a graph convolutional network (GCN) on the early prediction of AD. Methods: We proposed a univariate neurodegeneration biomarker (UNB) based GCN semi-supervised classification framework. We generated UNB by comparing the similarity of individual morphological atrophy pattern and the atrophy pattern of \u0000<inline-formula> <tex-math>$text{A}beta +$ </tex-math></inline-formula>\u0000 AD group according to the brain morphological abnormalities induced by AD. For the GCN semi-supervised classification model, we took the UNBs of individuals as the features of nodes and constructed the weight of edges according to the similarity of phenotypic information between individuals, which explored the essential features of individuals through spectral graph convolution. The attention module was constructed and embedded into the GCN framework, which may refine the input morphological features to highlight the main impact of AD on the cerebral cortex and weaken the instability caused by individual diversities, thereby identifying the significant ROIs affected by AD and improving the classification accuracy. Results: We tested the UNB-GCN framework on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. The estimated minimum sample sizes were 156, 349 and 423 for the longitudinal \u0000<inline-formula> <tex-math>$text{A}beta +$ </tex-math></inline-formula>\u0000 AD, \u0000<inline-formula> <tex-math>$text{A}beta +$ </tex-math></inline-formula>\u0000 mild cognitive impairment (MCI) and \u0000<inline-formula> <tex-math>$text{A}beta +$ </tex-math></inline-formula>\u0000 cognitively unimpaired (CU) groups, respectively. And the proposed UNB-GCN framework combined with the attention module can effectively improve the classification performance with 93.90% classification accuracy for AD vs. CU and 82.05% for AD vs. MCI on the validation set. Conclusion: The proposed UNB measures were superior to the conventional volume measures in describing the AD-induced cerebral cortex morphological changes. And the UNB-GCN framework combined with attention module may effectively improve the classification performance between MCI subjects and AD patients. Clinical and Translational Impact Statement: This study aims to predict the early AD patients, so as to help clinicians develop effective interventions to delay the deterioration of AD symptoms.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"405-416"},"PeriodicalIF":3.4,"publicationDate":"2023-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10149537","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9892878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-07DOI: 10.1109/JTEHM.2023.3283519
Yuhu Shi;Lili Zhou;Weiming Zeng;Boyang Wei;Jin Deng
Objective: Long non-coding RNAs (lncRNAs) have been shown to be associated with the pathogenesis of different kinds of diseases and play important roles in various biological processes. Although numerous lncRNAs have been found, the functions of most lncRNAs and physiological/pathological significance are still in its infancy. Meanwhile, their expression patterns and regulation mechanisms are also far from being fully understood. Methods: In order to reveal functional lncRNAs and identify the key lncRNAs, we develop a new sparse independence component analysis (ICA) method to identify lncRNA-mRNA-miRNA expression co-modules based on the competitive endogenous RNA (ceRNA) theory using the sample-matched lncRNA, mRNA and miRNA expression profiles. The expression data of the three RNA combined together is approximated sparsely to obtain the corresponding sparsity coefficient, and then it is decomposed by using ICA constraint optimization to obtain the common basis and modules. Subsequently, affine propagation clustering is used to perform cluster analysis on the common basis under multiple running conditions to obtain the co-modules for the selection of different RNA elements. Results: We applied sparse ICA to Liver Hepatocellular Carcinoma (LIHC) dataset and the experiment results demonstrate that the proposed sparse ICA method can effectively discover biologically functional expression common modules. Conclusion: It may provide insights into the function of lncRNAs and molecular mechanism of LIHC. Clinical and Translational Impact Statement–The results on LIHC dataset demonstrate that the proposed sparse ICA method can effectively discover biologically functional expression common modules, which may provide insights into the function of IncRNAs and molecular mechanism of LIHC.
{"title":"Sparse Independence Component Analysis for Competitive Endogenous RNA Co-Module Identification in Liver Hepatocellular Carcinoma","authors":"Yuhu Shi;Lili Zhou;Weiming Zeng;Boyang Wei;Jin Deng","doi":"10.1109/JTEHM.2023.3283519","DOIUrl":"10.1109/JTEHM.2023.3283519","url":null,"abstract":"Objective: Long non-coding RNAs (lncRNAs) have been shown to be associated with the pathogenesis of different kinds of diseases and play important roles in various biological processes. Although numerous lncRNAs have been found, the functions of most lncRNAs and physiological/pathological significance are still in its infancy. Meanwhile, their expression patterns and regulation mechanisms are also far from being fully understood. Methods: In order to reveal functional lncRNAs and identify the key lncRNAs, we develop a new sparse independence component analysis (ICA) method to identify lncRNA-mRNA-miRNA expression co-modules based on the competitive endogenous RNA (ceRNA) theory using the sample-matched lncRNA, mRNA and miRNA expression profiles. The expression data of the three RNA combined together is approximated sparsely to obtain the corresponding sparsity coefficient, and then it is decomposed by using ICA constraint optimization to obtain the common basis and modules. Subsequently, affine propagation clustering is used to perform cluster analysis on the common basis under multiple running conditions to obtain the co-modules for the selection of different RNA elements. Results: We applied sparse ICA to Liver Hepatocellular Carcinoma (LIHC) dataset and the experiment results demonstrate that the proposed sparse ICA method can effectively discover biologically functional expression common modules. Conclusion: It may provide insights into the function of lncRNAs and molecular mechanism of LIHC. Clinical and Translational Impact Statement–The results on LIHC dataset demonstrate that the proposed sparse ICA method can effectively discover biologically functional expression common modules, which may provide insights into the function of IncRNAs and molecular mechanism of LIHC.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"384-393"},"PeriodicalIF":3.4,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10145103","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9854603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-06DOI: 10.1109/JTEHM.2023.3283444
Jithin Joseph;Sudhish N. George;Kiran Raja
Objective: Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the diagnostic quality of images. These scattered white regions severely affect the visual appearance of images for both endoscopists and the computer-aided diagnosis of diseases. Methods & Results: We introduce a new parameter-free matrix decomposition technique to remove the specular reflections. The proposed method decomposes the original image into a highlight-free pseudo-low-rank component and a highlight component. Along with the highlight removal, the approach also removes the boundary artifacts present around the highlight regions, unlike the previous works based on family of Robust Principal Component Analysis (RPCA). The approach is evaluated on three publicly available endoscopy datasets: Kvasir Polyp, Kvasir Normal-Pylorus and Kvasir Capsule datasets. Our evaluation is benchmarked against 4 different state-of-the-art approaches using three different well-used metrics such as Structural Similarity Index Measure (SSIM), Percentage of highlights remaining and Coefficient of Variation (CoV). Conclusions: The results show significant improvements over the compared methods on all three metrics. The approach is further validated for statistical significance where it emerges better than other state-of-the-art approaches. Clinical and Translational Impact Statement— The mathematical concepts of low rank and rank decomposition in matrix algebra are translated to remove specularities in the endoscopic images The result shows the impact of the proposed method in removing specular reflections from endoscopic images indicating improved diagnosis efficiency for both endoscopists and computer-aided diagnosis systems
目的：内窥镜是一种医学诊断程序，用于在称为内窥镜的摄像头连接系统的帮助下观察人体内部。内窥镜图像和视频会受到镜面反射（或高光）的影响，并可能对图像的诊断质量产生不利影响。这些分散的白色区域严重影响内窥镜医生和疾病计算机辅助诊断的图像视觉外观。方法与结果：我们引入了一种新的无参数矩阵分解技术来去除镜面反射。该方法将原始图像分解为无高光伪低阶分量和高光分量。除了去除高光之外，该方法还去除了高光区域周围的边界伪影，这与以前基于稳健主成分分析（RPCA）家族的工作不同。该方法在三个公开的内窥镜检查数据集上进行了评估：Kvasir Polyp、Kvasir Normal Pylorus和Kvasir Capsule数据集。我们的评估以4种不同的最先进方法为基准，使用三种不同的常用指标，如结构相似性指数测量（SSIM）、剩余亮点百分比和变异系数（CoV）。结论：结果表明，在所有三个指标上，与比较方法相比，都有显著改进。该方法在统计显著性方面得到了进一步验证，其表现优于其他最先进的方法。临床和转化影响声明矩阵代数中的低秩和秩分解的数学概念被转化为去除内窥镜图像中的镜面反射。结果显示了所提出的方法在去除内窥镜中的镜面反射方面的影响，这表明内窥镜医生和计算机辅助诊断系统的诊断效率都有所提高。
{"title":"Parameter-Free Matrix Decomposition for Specular Reflections Removal in Endoscopic Images","authors":"Jithin Joseph;Sudhish N. George;Kiran Raja","doi":"10.1109/JTEHM.2023.3283444","DOIUrl":"10.1109/JTEHM.2023.3283444","url":null,"abstract":"<italic>Objective:</i>\u0000 Endoscopy is a medical diagnostic procedure used to see inside the human body with the help of a camera-attached system called the endoscope. Endoscopic images and videos suffer from specular reflections (or highlight) and can have an adverse impact on the diagnostic quality of images. These scattered white regions severely affect the visual appearance of images for both endoscopists and the computer-aided diagnosis of diseases. Methods & Results: We introduce a new parameter-free matrix decomposition technique to remove the specular reflections. The proposed method decomposes the original image into a highlight-free pseudo-low-rank component and a highlight component. Along with the highlight removal, the approach also removes the boundary artifacts present around the highlight regions, unlike the previous works based on family of Robust Principal Component Analysis (RPCA). The approach is evaluated on three publicly available endoscopy datasets: Kvasir Polyp, Kvasir Normal-Pylorus and Kvasir Capsule datasets. Our evaluation is benchmarked against 4 different state-of-the-art approaches using three different well-used metrics such as Structural Similarity Index Measure (SSIM), Percentage of highlights remaining and Coefficient of Variation (CoV). Conclusions: The results show significant improvements over the compared methods on all three metrics. The approach is further validated for statistical significance where it emerges better than other state-of-the-art approaches.\u0000<italic>Clinical and Translational Impact Statement—</i>\u0000The mathematical concepts of low rank and rank decomposition in matrix algebra are translated to remove specularities in the endoscopic images The result shows the impact of the proposed method in removing specular reflections from endoscopic images indicating improved diagnosis efficiency for both endoscopists and computer-aided diagnosis systems","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"360-374"},"PeriodicalIF":3.4,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10144758","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10191715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-02DOI: 10.1109/JTEHM.2023.3282245
Jing Chen;Jiping Wang;Qun Yuan;Zhao Yang
Identifying human actions from video data is an important problem in the fields of intelligent rehabilitation assessment. Motion feature extraction and pattern recognition are the two key procedures to achieve such goals. Traditional action recognition models are usually based on the geometric features manually extracted from video frames, which are however difficult to adapt to complex scenarios and cannot achieve high-precision recognition and robustness. We investigate a motion recognition model and apply it to recognize the sequence of complicated actions of a traditional Chinese exercise (ie, Baduanjin). We first developed a combined convolutional neural network (CNN) and long short-term memory (LSTM) model for recognizing the sequence of actions captured in video frames, and applied it to recognize the actions of Baduanjin. Moreover, this method has been compared with the traditional action recognition model based on geometric motion features in which Openpose is used to identify the joint positions in the skeletons. Its performance of high recognition accuracy has been verified on the testing video dataset, containing the video clips from 18 different practicers. The CNN-LSTM recognition model achieved 96.43% accuracy on the testing set; while those manually extracted features in the traditional action recognition model were only able to achieve 66.07% classification accuracy on the testing video dataset. The abstract image features extracted by the CNN module are more effective on improving the classification accuracy of the LSTM model. The proposed CNN-LSTM based method can be a useful tool in recognizing the complicated actions.
{"title":"CNN-LSTM Model for Recognizing Video-Recorded Actions Performed in a Traditional Chinese Exercise","authors":"Jing Chen;Jiping Wang;Qun Yuan;Zhao Yang","doi":"10.1109/JTEHM.2023.3282245","DOIUrl":"10.1109/JTEHM.2023.3282245","url":null,"abstract":"Identifying human actions from video data is an important problem in the fields of intelligent rehabilitation assessment. Motion feature extraction and pattern recognition are the two key procedures to achieve such goals. Traditional action recognition models are usually based on the geometric features manually extracted from video frames, which are however difficult to adapt to complex scenarios and cannot achieve high-precision recognition and robustness. We investigate a motion recognition model and apply it to recognize the sequence of complicated actions of a traditional Chinese exercise (ie, Baduanjin). We first developed a combined convolutional neural network (CNN) and long short-term memory (LSTM) model for recognizing the sequence of actions captured in video frames, and applied it to recognize the actions of Baduanjin. Moreover, this method has been compared with the traditional action recognition model based on geometric motion features in which Openpose is used to identify the joint positions in the skeletons. Its performance of high recognition accuracy has been verified on the testing video dataset, containing the video clips from 18 different practicers. The CNN-LSTM recognition model achieved 96.43% accuracy on the testing set; while those manually extracted features in the traditional action recognition model were only able to achieve 66.07% classification accuracy on the testing video dataset. The abstract image features extracted by the CNN module are more effective on improving the classification accuracy of the LSTM model. The proposed CNN-LSTM based method can be a useful tool in recognizing the complicated actions.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"11 ","pages":"351-359"},"PeriodicalIF":3.4,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10143200","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10173160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：