Introduction: Stroke is one of the most common causes of impaired gait. The use of an ankle-foot orthosis (AFO) is one of the recommended methods to improve gait function in stroke patients. Although the stiffness of the AFO is adjusted for each stroke patient, the effect of stiffness adjustment remains unclear due to the difficulty in measuring the gait parameters in a clinical setting. Objective: This study aimed to investigate the effect of adjusting the AFO stiffness based on the gait ability of stroke patients using a markerless gait analysis method. Methods: A total of 32 individuals with stroke were directed to walk under five conditions: no-AFO and AFO with four different levels of spring stiffness. These springs were used to resist the plantarflexion movements. Moreover, the best gait speed improvement condition (best condition) was determined from the five gait conditions for each participant and was compared with the other conditions, assuming a clinical setting. Spatiotemporal gait parameters such as the gait speed, cadence, step length, stance phase, and swing phase were measured from body keypoints in RGB images. Results and Conclusion: The experimental results showed that the gait speed, cadence, step length on both sides, and stance time on both sides were significantly improved in the best condition compared with the other conditions. This study demonstrated the usefulness of the markerless gait analysis method using a single RGB camera and the effectiveness of AFO stiffness adjustment based on the gait ability of the users.
{"title":"Single Camera-Based Gait Analysis Using Pose Estimation for Ankle-Foot Orthosis Stiffness Adjustment on Individuals With Stroke","authors":"Masataka Yamamoto;Koji Shimatani;Daisuke Matsuura;Yusuke Murakami;Naoya Oeda;Hiroshi Takemura","doi":"10.1109/JTEHM.2025.3585442","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3585442","url":null,"abstract":"Introduction: Stroke is one of the most common causes of impaired gait. The use of an ankle-foot orthosis (AFO) is one of the recommended methods to improve gait function in stroke patients. Although the stiffness of the AFO is adjusted for each stroke patient, the effect of stiffness adjustment remains unclear due to the difficulty in measuring the gait parameters in a clinical setting. Objective: This study aimed to investigate the effect of adjusting the AFO stiffness based on the gait ability of stroke patients using a markerless gait analysis method. Methods: A total of 32 individuals with stroke were directed to walk under five conditions: no-AFO and AFO with four different levels of spring stiffness. These springs were used to resist the plantarflexion movements. Moreover, the best gait speed improvement condition (best condition) was determined from the five gait conditions for each participant and was compared with the other conditions, assuming a clinical setting. Spatiotemporal gait parameters such as the gait speed, cadence, step length, stance phase, and swing phase were measured from body keypoints in RGB images. Results and Conclusion: The experimental results showed that the gait speed, cadence, step length on both sides, and stance time on both sides were significantly improved in the best condition compared with the other conditions. This study demonstrated the usefulness of the markerless gait analysis method using a single RGB camera and the effectiveness of AFO stiffness adjustment based on the gait ability of the users.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"333-340"},"PeriodicalIF":3.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11063274","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704943","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}
In recent years, visual cancer information retrieval using Artificial Intelligence has been shown to be effective in diagnosis and treatment. Especially for a modern liver-cancer diagnosis system, the automated tumor annotation plays a crucial role. So-called tumor annotation refers to tagging the tumor in Biomedical images by computer vision technologies such as Deep Learning. After annotation, the tumor information such as tumor location, tumor size and tumor characteristics can be output into a clinical report. To this end, this paper proposes an effective approach that includes tumor segmentation, tumor location, tumor measuring, and tumor recognition to achieve high-quality tumor annotation, thereby assisting radiologists in efficiently making accurate diagnosis reports. For tumor segmentation, a Multi-Residual Attention Unet is proposed to alleviate problems of vanishing gradient and information diversity. For tumor location, an effective Multi-SeResUnet is proposed to partition the liver into 8 couinaud segments. Based on the partitioned segments, the tumor is located accurately. For tumor recognition, an effective multi-labeling classifier is used to recognize the tumor characteristics by the visual tumor features. For tumor measuring, a regression model is proposed to measure the tumor size. To reveal the effectiveness of individual methods, each method was evaluated on real datasets. The experimental results reveal that the proposed methods are more promising than the state-of-the-art methods in tumor segmentation, tumor measuring, tumor localization and tumor recognition. Specifically, the average tumor size error and the annotation accuracy are 0.432 cm and 91.6%, respectively, which suggest potential for reducing radiologists’ workload. In summary, this paper proposes an effective tumor annotation for an automated diagnosis support system. Clinical and Translational Impact Statement—The proposed methods have been evaluated and shown to significantly improve the efficiency and accuracy of liver tumor annotation, reducing the time required for radiologists to complete reports on tumor segmentation, liver partition, tumor measuring and tumor recognition. By integrating into existing clinical decision support systems, it has the potential to reduce diagnostic errors and treatment delays, thereby improving patient outcomes and clinical workflow.
{"title":"Effective Tumor Annotation for Automated Diagnosis of Liver Cancer","authors":"Yi-Hsuan Chuang;Ja-Hwung Su;Tzu-Chieh Lin;Hue-Xin Cheng;Pin-Hao Shen;Jin-Ping Ou;Ding-Hong Han;Yi-Wen Liao;Yeong-Chyi Lee;Yu-Fan Cheng;Tzung-Pei Hong;Katherine Shu-Min Li;Yi Lu;Chih-Chi Wang","doi":"10.1109/JTEHM.2025.3576827","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3576827","url":null,"abstract":"In recent years, visual cancer information retrieval using Artificial Intelligence has been shown to be effective in diagnosis and treatment. Especially for a modern liver-cancer diagnosis system, the automated tumor annotation plays a crucial role. So-called tumor annotation refers to tagging the tumor in Biomedical images by computer vision technologies such as Deep Learning. After annotation, the tumor information such as tumor location, tumor size and tumor characteristics can be output into a clinical report. To this end, this paper proposes an effective approach that includes tumor segmentation, tumor location, tumor measuring, and tumor recognition to achieve high-quality tumor annotation, thereby assisting radiologists in efficiently making accurate diagnosis reports. For tumor segmentation, a Multi-Residual Attention Unet is proposed to alleviate problems of vanishing gradient and information diversity. For tumor location, an effective Multi-SeResUnet is proposed to partition the liver into 8 couinaud segments. Based on the partitioned segments, the tumor is located accurately. For tumor recognition, an effective multi-labeling classifier is used to recognize the tumor characteristics by the visual tumor features. For tumor measuring, a regression model is proposed to measure the tumor size. To reveal the effectiveness of individual methods, each method was evaluated on real datasets. The experimental results reveal that the proposed methods are more promising than the state-of-the-art methods in tumor segmentation, tumor measuring, tumor localization and tumor recognition. Specifically, the average tumor size error and the annotation accuracy are 0.432 cm and 91.6%, respectively, which suggest potential for reducing radiologists’ workload. In summary, this paper proposes an effective tumor annotation for an automated diagnosis support system. Clinical and Translational Impact Statement—The proposed methods have been evaluated and shown to significantly improve the efficiency and accuracy of liver tumor annotation, reducing the time required for radiologists to complete reports on tumor segmentation, liver partition, tumor measuring and tumor recognition. By integrating into existing clinical decision support systems, it has the potential to reduce diagnostic errors and treatment delays, thereby improving patient outcomes and clinical workflow.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"251-260"},"PeriodicalIF":3.7,"publicationDate":"2025-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11025471","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281292","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 : 2025-06-04DOI: 10.1109/JTEHM.2025.3576570
Thanh-Dung Le;Philippe Jouvet;Rita Noumeir
Transformer-based models have shown outstanding results in natural language processing but face challenges in applications like classifying small-scale clinical texts, especially with constrained computational resources. This study presents a customized Mixture of Expert (MoE) Transformer models for classifying small-scale French clinical texts at CHU Sainte-Justine Hospital. The MoE-Transformer addresses the dual challenges of effective training with limited data and low-resource computation suitable for in-house hospital use. Despite the success of biomedical pre-trained models such as CamemBERT-bio, DrBERT, and AliBERT, their high computational demands make them impractical for many clinical settings. Our MoE-Transformer model not only outperforms DistillBERT, CamemBERT, FlauBERT, and Transformer models on the same dataset but also achieves impressive results: an accuracy of 87%, precision of 87%, recall of 85%, and F1-score of 86%. While the MoE-Transformer does not surpass the performance of biomedical pre-trained BERT models, it can be trained at least 190 times faster, offering a viable alternative for settings with limited data and computational resources. Although the MoE-Transformer addresses challenges of generalization gaps and sharp minima, demonstrating some limitations for efficient and accurate clinical text classification, this model still represents a significant advancement in the field. It is particularly valuable for classifying small French clinical narratives within the privacy and constraints of hospital-based computational resources. Clinical and Translational Impact Statement—This study highlights the potential of customized MoE-Transformers in enhancing clinical text classification, particularly for small-scale datasets like French clinical narratives. The MoE-Transformer's ability to outperform several pre-trained BERT models marks a stride in applying NLP techniques to clinical data and integrating into a Clinical Decision Support System in a Pediatric Intensive Care Unit. The study underscores the importance of model selection and customization in achieving optimal performance for specific clinical applications, especially with limited data availability and within the constraints of hospital-based computational resources
{"title":"Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset","authors":"Thanh-Dung Le;Philippe Jouvet;Rita Noumeir","doi":"10.1109/JTEHM.2025.3576570","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3576570","url":null,"abstract":"Transformer-based models have shown outstanding results in natural language processing but face challenges in applications like classifying small-scale clinical texts, especially with constrained computational resources. This study presents a customized Mixture of Expert (MoE) Transformer models for classifying small-scale French clinical texts at CHU Sainte-Justine Hospital. The MoE-Transformer addresses the dual challenges of effective training with limited data and low-resource computation suitable for in-house hospital use. Despite the success of biomedical pre-trained models such as CamemBERT-bio, DrBERT, and AliBERT, their high computational demands make them impractical for many clinical settings. Our MoE-Transformer model not only outperforms DistillBERT, CamemBERT, FlauBERT, and Transformer models on the same dataset but also achieves impressive results: an accuracy of 87%, precision of 87%, recall of 85%, and F1-score of 86%. While the MoE-Transformer does not surpass the performance of biomedical pre-trained BERT models, it can be trained at least 190 times faster, offering a viable alternative for settings with limited data and computational resources. Although the MoE-Transformer addresses challenges of generalization gaps and sharp minima, demonstrating some limitations for efficient and accurate clinical text classification, this model still represents a significant advancement in the field. It is particularly valuable for classifying small French clinical narratives within the privacy and constraints of hospital-based computational resources. Clinical and Translational Impact Statement—This study highlights the potential of customized MoE-Transformers in enhancing clinical text classification, particularly for small-scale datasets like French clinical narratives. The MoE-Transformer's ability to outperform several pre-trained BERT models marks a stride in applying NLP techniques to clinical data and integrating into a Clinical Decision Support System in a Pediatric Intensive Care Unit. The study underscores the importance of model selection and customization in achieving optimal performance for specific clinical applications, especially with limited data availability and within the constraints of hospital-based computational resources","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"261-274"},"PeriodicalIF":3.7,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023574","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299303","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 : 2025-06-04DOI: 10.1109/JTEHM.2025.3576596
Christopher Nielsen;Matthias Wilms;Nils D. Forkert
The retinal age gap (RAG; the difference between the retina’s biological and chronological age) has recently gained increased attention as a potential image-based, non-invasive, and accessible biomarker for a broad spectrum of ocular and non-ocular diseases. Traditionally, machine learning predictions of biological retinal age utilize convolutional neural network (CNN) architectures and data from color fundus photography (CFP). Despite being previously unexplored, the multimodal fusion of two-dimensional CFP with three-dimensional optical coherence tomography (OCT) data has significant potential to enhance retinal age prediction accuracy and the diagnostic utility of the RAG biomarker. Therefore, this work presents a novel foundation model-based framework for multimodal retinal age prediction. Technology or Method: Feature representations from CFP and OCT images were extracted using RETFound, a powerful foundation model for retinal image analysis. These representations were then combined using an innovative fusion strategy to train a lightweight linear regression head model for predicting retinal age. Training and evaluation of the developed multimodal retinal age prediction model was achieved using retinal images from over 80,000 participants in the UK Biobank. Results: The developed multimodal model sets a new benchmark in retinal age prediction (mean absolute error of 2.75 years), outperforming traditional CNN and single-modality approaches. Additionally, multimodal RAG values demonstrated superior performance in classifying patients with diabetes mellitus type 1, multiple sclerosis, and chronic kidney disease, highlighting the clinical relevance of the proposed multimodal approach for non-ocular disease detection. Conclusions: This work demonstrates that multimodal fusion of CFP and OCT significantly improves retinal age prediction and subsequent RAG-based analyses. By leveraging foundation models and multimodal retinal imaging, the proposed approach enhances disease classification accuracy and demonstrates the potential of integrating the RAG into clinical workflows as a scalable, non-invasive screening tool. Significance: The findings underscore the potential of multimodal retinal imaging to transform RAG into a clinically relevant and highly accessible biomarker for disease detection.
{"title":"A Novel Foundation Model-Based Framework for Multimodal Retinal Age Prediction","authors":"Christopher Nielsen;Matthias Wilms;Nils D. Forkert","doi":"10.1109/JTEHM.2025.3576596","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3576596","url":null,"abstract":"The retinal age gap (RAG; the difference between the retina’s biological and chronological age) has recently gained increased attention as a potential image-based, non-invasive, and accessible biomarker for a broad spectrum of ocular and non-ocular diseases. Traditionally, machine learning predictions of biological retinal age utilize convolutional neural network (CNN) architectures and data from color fundus photography (CFP). Despite being previously unexplored, the multimodal fusion of two-dimensional CFP with three-dimensional optical coherence tomography (OCT) data has significant potential to enhance retinal age prediction accuracy and the diagnostic utility of the RAG biomarker. Therefore, this work presents a novel foundation model-based framework for multimodal retinal age prediction. Technology or Method: Feature representations from CFP and OCT images were extracted using RETFound, a powerful foundation model for retinal image analysis. These representations were then combined using an innovative fusion strategy to train a lightweight linear regression head model for predicting retinal age. Training and evaluation of the developed multimodal retinal age prediction model was achieved using retinal images from over 80,000 participants in the UK Biobank. Results: The developed multimodal model sets a new benchmark in retinal age prediction (mean absolute error of 2.75 years), outperforming traditional CNN and single-modality approaches. Additionally, multimodal RAG values demonstrated superior performance in classifying patients with diabetes mellitus type 1, multiple sclerosis, and chronic kidney disease, highlighting the clinical relevance of the proposed multimodal approach for non-ocular disease detection. Conclusions: This work demonstrates that multimodal fusion of CFP and OCT significantly improves retinal age prediction and subsequent RAG-based analyses. By leveraging foundation models and multimodal retinal imaging, the proposed approach enhances disease classification accuracy and demonstrates the potential of integrating the RAG into clinical workflows as a scalable, non-invasive screening tool. Significance: The findings underscore the potential of multimodal retinal imaging to transform RAG into a clinically relevant and highly accessible biomarker for disease detection.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"299-309"},"PeriodicalIF":3.7,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023594","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144524371","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 : 2025-04-30DOI: 10.1109/JTEHM.2025.3565986
Mhairi Mcinnes;Dimitra Blana;Andrew Starkey;Edward K. Chadwick
Inertial sensors have the potential to be a useful clinical tool because they can facilitate human motion capture outside the research setting. A major barrier to the widespread application of inertial motion capture is the lack of accepted calibration methods for ensuring accuracy, in particular the lack of a common convention for calculating the rotational offset of the sensors, known as sensor-to-segment calibration. The purpose of this study was to develop and test a sensor-to-segment calibration method for upper limb motion capture which is practical for clinical applications.We developed a calibration method which depends mainly on the estimation of joint axes from arbitrary elbow motion, and partially on the design of custom attachment mounts to achieve physical alignment. With twenty healthy participants, we used OpenSim’s inertial sensor workflow to calculate joint kinematics, and evaluated the accuracy of the method through comparison with optical motion capture.We found the new calibration method resulted in upper limb kinematics with a median RMS error of 5–8°, and a median correlation coefficient of 0.977–0.987, which was significantly more accurate than a static pose calibration (p-value < 0.001).This work has demonstrated a method of calibration which is practical for clinical applications because it is quick to perform and does not depend on the subject’s ability to perform specific movements, or on the operator’s ability to carefully place sensors.Clinical Impact: The calibration method proposed in this work is a realistic option for the translation of inertial sensor technology into everyday clinical use.
{"title":"A Practical Sensor-to-Segment Calibration Method for Upper Limb Inertial Motion Capture in a Clinical Setting","authors":"Mhairi Mcinnes;Dimitra Blana;Andrew Starkey;Edward K. Chadwick","doi":"10.1109/JTEHM.2025.3565986","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3565986","url":null,"abstract":"Inertial sensors have the potential to be a useful clinical tool because they can facilitate human motion capture outside the research setting. A major barrier to the widespread application of inertial motion capture is the lack of accepted calibration methods for ensuring accuracy, in particular the lack of a common convention for calculating the rotational offset of the sensors, known as sensor-to-segment calibration. The purpose of this study was to develop and test a sensor-to-segment calibration method for upper limb motion capture which is practical for clinical applications.We developed a calibration method which depends mainly on the estimation of joint axes from arbitrary elbow motion, and partially on the design of custom attachment mounts to achieve physical alignment. With twenty healthy participants, we used OpenSim’s inertial sensor workflow to calculate joint kinematics, and evaluated the accuracy of the method through comparison with optical motion capture.We found the new calibration method resulted in upper limb kinematics with a median RMS error of 5–8°, and a median correlation coefficient of 0.977–0.987, which was significantly more accurate than a static pose calibration (p-value < 0.001).This work has demonstrated a method of calibration which is practical for clinical applications because it is quick to perform and does not depend on the subject’s ability to perform specific movements, or on the operator’s ability to carefully place sensors.Clinical Impact: The calibration method proposed in this work is a realistic option for the translation of inertial sensor technology into everyday clinical use.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"216-226"},"PeriodicalIF":3.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10981591","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943979","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}
Parkinson’s disease (PD) is characterized by gait disturbances with freezing of gait (FoG) being one of the most disabling symptoms. The FoG episode is often preceded by an increase in variability in Step Time. As the disease progresses, such gait impairment may become resistant to pharmacotherapy. Use of external cues is an alternative. Existing solutions deliver external cues in a continuous manner that might cause habituation effects, thereby emphasizing the need for on-demand cueing. Manual on-demand cueing upon freezing has been shown to be powerful in bringing an individual out of a freezing state. This can be achieved if one’s proneness to freeze before entering into freezing state can be sensed, and in-turn triggering an external cue on-demand. Motivated by this, we have developed a wearable device ($mathrm{SmartWalk}_{mathrm {VC}}$ ) that can sense such proneness based on variability in Step Time to offer a visual cue on-demand. We conducted a study involving 20 age-matched healthy individuals and those with PD who walked overground while wearing SmartWalkVC operated in three modes with regard to offering visual cue, namely (a) On-demand cueing, (b) Continuous cueing and (c) No cueing. The results of our study showed that with on-demand cueing, those with PD had minimum variability of Step Time among all the three modes unlike healthy individuals whose gait remained majorly unaffected by different cueing modes. Also, walking speed increased along with a reduction in FoG episodes for those with PD in the on-demand cueing mode compared with the other two modes.Clinical and Translational Impact Statement: Wearable SmartWalkVC quantifies one’s Step Time variability to offer visual cue on-demand, reducing one’s Freezing of Gait that can have clinical significance and be translated to impact one’s social presence.
{"title":"On-Demand Cueing Sensitive to Step Variability: Understanding Its Impact on Gait of Individuals With Parkinson’s Disease","authors":"Priya Pallavi;Ankita Raghuvanshi;Suhagiya Dharmik Kumar;Niravkumar Patel;Manasi Kanetkar;Rahul Chhatlani;Manish Rana;Sagar Betai;Roopa Rajan;Uttama Lahiri","doi":"10.1109/JTEHM.2025.3563381","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3563381","url":null,"abstract":"Parkinson’s disease (PD) is characterized by gait disturbances with freezing of gait (FoG) being one of the most disabling symptoms. The FoG episode is often preceded by an increase in variability in Step Time. As the disease progresses, such gait impairment may become resistant to pharmacotherapy. Use of external cues is an alternative. Existing solutions deliver external cues in a continuous manner that might cause habituation effects, thereby emphasizing the need for on-demand cueing. Manual on-demand cueing upon freezing has been shown to be powerful in bringing an individual out of a freezing state. This can be achieved if one’s proneness to freeze before entering into freezing state can be sensed, and in-turn triggering an external cue on-demand. Motivated by this, we have developed a wearable device (<inline-formula> <tex-math>$mathrm{SmartWalk}_{mathrm {VC}}$ </tex-math></inline-formula>) that can sense such proneness based on variability in Step Time to offer a visual cue on-demand. We conducted a study involving 20 age-matched healthy individuals and those with PD who walked overground while wearing SmartWalkVC operated in three modes with regard to offering visual cue, namely (a) On-demand cueing, (b) Continuous cueing and (c) No cueing. The results of our study showed that with on-demand cueing, those with PD had minimum variability of Step Time among all the three modes unlike healthy individuals whose gait remained majorly unaffected by different cueing modes. Also, walking speed increased along with a reduction in FoG episodes for those with PD in the on-demand cueing mode compared with the other two modes.Clinical and Translational Impact Statement: Wearable SmartWalkVC quantifies one’s Step Time variability to offer visual cue on-demand, reducing one’s Freezing of Gait that can have clinical significance and be translated to impact one’s social presence.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"183-192"},"PeriodicalIF":3.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10976342","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896394","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 : 2025-04-24DOI: 10.1109/JTEHM.2025.3563985
Sara Bernasconi;Giovanni Maria Oriolo;Giovanni Farina;Andrea Aliverti;Antonella Lomauro
Lymphedema, characterized by limb swelling, is typically treated with Complex Decongestive Therapy (CDT), which includes physical exercise. This study seeks to design and validate a wearable device aimed at enhancing CDT by monitoring patient adherence to prescribed exercises and tracking changes in the range of motion of the affected limbs. A wearable device, constituted by two boards with 2 IMUs, connected by a flexible flat cable, was designed and developed for placement across targeted joints. It communicates wirelessly with PCs, where raw data from IMUs are collected. Through the application of the Madgwick filter, orientation of the units is obtained and finally joints angles are computed. The device was validated through bench testing using an orthopedic goniometer and field testing with an optoelectronic system. The in vivo validation involved 18 volunteers, including 10 healthy individuals and 8 individuals with lymphedema, who performed flexion-extension movements and walked on a treadmill (at speeds of 3 km/h and 5 km/h). Bench testing demonstrated strong correlation and agreement (r2=0.999, mean percentage error = -0.51°, standard deviation = 2.00°). Once worn by the participants, the device enabled the measurement of joint angles during flexion-extension exercises (r2=0.852, mean percentage error = 1.44°, standard deviation = 11.7°) and the extraction of step counting, step time and toe off during walk at different speeds. The developed wearable device exhibited robust performance in both bench and field testing. This device, designed specifically for lymphedema patients, offers valuable insights into limb function and exercise adherence, potentially improving personalized treatment strategies.
{"title":"Design and Validation of a Wearable System for Enhanced Monitoring of Lower Limb Lymphedema","authors":"Sara Bernasconi;Giovanni Maria Oriolo;Giovanni Farina;Andrea Aliverti;Antonella Lomauro","doi":"10.1109/JTEHM.2025.3563985","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3563985","url":null,"abstract":"Lymphedema, characterized by limb swelling, is typically treated with Complex Decongestive Therapy (CDT), which includes physical exercise. This study seeks to design and validate a wearable device aimed at enhancing CDT by monitoring patient adherence to prescribed exercises and tracking changes in the range of motion of the affected limbs. A wearable device, constituted by two boards with 2 IMUs, connected by a flexible flat cable, was designed and developed for placement across targeted joints. It communicates wirelessly with PCs, where raw data from IMUs are collected. Through the application of the Madgwick filter, orientation of the units is obtained and finally joints angles are computed. The device was validated through bench testing using an orthopedic goniometer and field testing with an optoelectronic system. The in vivo validation involved 18 volunteers, including 10 healthy individuals and 8 individuals with lymphedema, who performed flexion-extension movements and walked on a treadmill (at speeds of 3 km/h and 5 km/h). Bench testing demonstrated strong correlation and agreement (r<sup>2</sup>=0.999, mean percentage error = -0.51°, standard deviation = 2.00°). Once worn by the participants, the device enabled the measurement of joint angles during flexion-extension exercises (r<sup>2</sup>=0.852, mean percentage error = 1.44°, standard deviation = 11.7°) and the extraction of step counting, step time and toe off during walk at different speeds. The developed wearable device exhibited robust performance in both bench and field testing. This device, designed specifically for lymphedema patients, offers valuable insights into limb function and exercise adherence, potentially improving personalized treatment strategies.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"193-201"},"PeriodicalIF":3.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975766","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143925066","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}
Accurate prediction of survival rates in esophageal cancer (EC) is crucial for guiding personalized treatment decisions. Deep learning-based survival models have gained increasing attention due to their powerful ability to capture complex embeddings in medical data. However, the primary limitation of current frameworks for predicting survival lies in their lack of attention to the contextual interactions between tumor and lymph node regions, which are vital for survival predictions. In the current study, we aimed to develop an effective EC survival risk prediction using only 3D computed tomography (CT) images.The proposed model consists of two essential components: 1) non-local feature aggregation module(NFAM) that integrates visual features from tumor and lymph nodes at both local and global scales, 2) graph-based spatial interaction module(GSIM) that explores the latent contextual interactions between tumors and lymph nodes.The experimental results demonstrate that our model achieves superior performance compared to state-of-the-art survival prediction methods, emphasizing its robust predictive capability. Moreover, we found that retaining lymph nodes with major axis $geq 8$ mm yields the best predictive results (C-index: 0.725), offering valuable guidance on choosing prognostic factors for esophageal cancer.For EC survival prediction using solely 3D CT images, integrating lymph node information with tumor information helps to improve the predictive performance of deep learning models.Clinical impact: The American Joint Committee on Cancer (TNM) classification serves as the primary framework for risk stratification, prognostic evaluation, and therapeutic decision-making in oncology. Nevertheless, this prognostic tool has demonstrated limited predictive accuracy in assessing long-term survival for esophageal carcinoma patients undergoing multimodal therapeutic regimens. Notably, even among those categorized within identical staging parameters, significant outcome heterogeneity persists, with survival trajectories diverging substantially across clinically matched populations. Our model serves as a complementary tool to the TNM staging system. By stratifying patients into distinct risk categories, this approach enables accurate prognosis assessment and provides critical guidance for postoperative adjuvant therapy decisions (such as whether to administer adjuvant radiotherapy or chemotherapy), thereby facilitating personalized treatment recommendations.
{"title":"Survival Prediction of Esophageal Cancer Using 3D CT Imaging: A Context-Aware Approach With Non-Local Feature Aggregation and Graph-Based Spatial Interaction","authors":"Fuce Guo;Chen Huang;Shengmei Lin;Yongmei Dai;Qianshun Chen;Shu Zhang;Xunyu XU","doi":"10.1109/JTEHM.2025.3562724","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3562724","url":null,"abstract":"Accurate prediction of survival rates in esophageal cancer (EC) is crucial for guiding personalized treatment decisions. Deep learning-based survival models have gained increasing attention due to their powerful ability to capture complex embeddings in medical data. However, the primary limitation of current frameworks for predicting survival lies in their lack of attention to the contextual interactions between tumor and lymph node regions, which are vital for survival predictions. In the current study, we aimed to develop an effective EC survival risk prediction using only 3D computed tomography (CT) images.The proposed model consists of two essential components: 1) non-local feature aggregation module(NFAM) that integrates visual features from tumor and lymph nodes at both local and global scales, 2) graph-based spatial interaction module(GSIM) that explores the latent contextual interactions between tumors and lymph nodes.The experimental results demonstrate that our model achieves superior performance compared to state-of-the-art survival prediction methods, emphasizing its robust predictive capability. Moreover, we found that retaining lymph nodes with major axis <inline-formula> <tex-math>$geq 8$ </tex-math></inline-formula>mm yields the best predictive results (C-index: 0.725), offering valuable guidance on choosing prognostic factors for esophageal cancer.For EC survival prediction using solely 3D CT images, integrating lymph node information with tumor information helps to improve the predictive performance of deep learning models.Clinical impact: The American Joint Committee on Cancer (TNM) classification serves as the primary framework for risk stratification, prognostic evaluation, and therapeutic decision-making in oncology. Nevertheless, this prognostic tool has demonstrated limited predictive accuracy in assessing long-term survival for esophageal carcinoma patients undergoing multimodal therapeutic regimens. Notably, even among those categorized within identical staging parameters, significant outcome heterogeneity persists, with survival trajectories diverging substantially across clinically matched populations. Our model serves as a complementary tool to the TNM staging system. By stratifying patients into distinct risk categories, this approach enables accurate prognosis assessment and provides critical guidance for postoperative adjuvant therapy decisions (such as whether to administer adjuvant radiotherapy or chemotherapy), thereby facilitating personalized treatment recommendations.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"202-213"},"PeriodicalIF":3.7,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10971407","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913401","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 : 2025-04-15DOI: 10.1109/JTEHM.2025.3560877
Yang Li;Leo Yan Li-Han;Hua Tian
The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles—Center-Edge (CE), Tönnis, and Sharp angles—from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, Tönnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, Tönnis, and Sharp angles were 0.957 (95% CI: 0.952–0.962), 0.942 (95% CI: 0.937–0.947), and 0.966 (95% CI: 0.964–0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851–0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737–0.817, $p = 0.005$ ), as well as using clinical diagnostic criteria for each angle individually ($plt 0.001$ ). The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians.Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.
{"title":"Deep Learning-Based Automatic Diagnosis System for Developmental Dysplasia of the Hip","authors":"Yang Li;Leo Yan Li-Han;Hua Tian","doi":"10.1109/JTEHM.2025.3560877","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3560877","url":null,"abstract":"The clinical diagnosis of developmental dysplasia of the hip (DDH) typically involves manually measuring key radiological angles—Center-Edge (CE), Tönnis, and Sharp angles—from pelvic radiographs, a process that is time-consuming and susceptible to variability. This study aims to develop an automated system that integrates these measurements to enhance the accuracy and consistency of DDH diagnosis. We developed an end-to-end deep learning model for keypoint detection that accurately identifies eight anatomical keypoints from pelvic radiographs, enabling the automated calculation of CE, Tönnis, and Sharp angles. To support the diagnostic decision, we introduced a novel data-driven scoring system that combines the information from all three angles into a comprehensive and explainable diagnostic output. The system demonstrated superior consistency in angle measurements compared to a cohort of eight moderately experienced orthopedists. The intraclass correlation coefficients for the CE, Tönnis, and Sharp angles were 0.957 (95% CI: 0.952–0.962), 0.942 (95% CI: 0.937–0.947), and 0.966 (95% CI: 0.964–0.968), respectively. The system achieved a diagnostic F1 score of 0.863 (95% CI: 0.851–0.876), significantly outperforming the orthopedist group (0.777, 95% CI: 0.737–0.817, <inline-formula> <tex-math>$p = 0.005$ </tex-math></inline-formula>), as well as using clinical diagnostic criteria for each angle individually (<inline-formula> <tex-math>$plt 0.001$ </tex-math></inline-formula>). The proposed system provides reliable and consistent automated measurements of radiological angles and an explainable diagnostic output for DDH, outperforming moderately experienced clinicians.Clinical impact: This AI-powered solution reduces the variability and potential errors of manual measurements, offering clinicians a more consistent and interpretable tool for DDH diagnosis.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"174-182"},"PeriodicalIF":3.7,"publicationDate":"2025-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10965781","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896492","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 : 2025-04-10DOI: 10.1109/JTEHM.2025.3559693
Felipe Perez;Jorge Morisaki;Haitham Kanakri;Maher Rizkalla;Ahmed Abdalla
Late Onset Alzheimer’s Disease (LOAD) is the most common cause of dementia, characterized by the deposition of plaques primarily of neurotoxic amyloid-$beta $ ($Abeta $ ) peptide and tau protein. Our objective is to develop a noninvasive therapy to decrease the toxic A$beta $ levels, using repeated electromagnetic field stimulation (REMFS) in the brain of Alzheimer’s disease patients. We previously examined the effects of REMFS on $Abeta $ levels in primary human brain (PHB) cultures at different frequencies, powers, and specific absorption rates (SAR). PHB cultures at day in vitro (DIV7) treated with 64 MHz with a SAR of 0.6 W/Kg, one hour daily for 14 days (DIV 21) had significantly reduced (p =0.001) levels of secreted $Abeta $ -42 and $Abeta $ -40 peptide without evidence of toxicity. The EMF frequency and power, and SAR levels used in our work is utilized in MRI’s, thus suggesting REMFS can be further developed in clinical settings to lower ($Abeta $ ) levels and improve the memory in AD patients. These findings and numerous studies in rodent AD models prompted us to design a portable RF device, appropriate for human use, that will deliver a homogeneous RF power deposition with a SAR value of 0.4-0.9 W/kg to all human brain memory areas, lower ($Abeta $ ) levels, and potentially improve memory in human AD patients.The research took place at the Indiana University School of Medicine (IUSM) and Purdue University Indianapolis. The first phase was done in PHB cultures at the IUSM. Through this phase, we found that a 64 MHz frequency and an RF power deposition with a SAR of 0.4-0.6 W/kg reduced the (A$beta $ ) levels potentially impacting Alzheimer’s disease. The second phase of the project was conducted at Purdue University, we used ANSYS HFSS (High Frequency Simulation System) to design the devices that produced an appropriate penetration depth, polarization, and power deposition with a SAR of 0.4-0.9 W/kg to all memory brain areas of several numerical models. In Phase II-B will validate the device in a physical phantom. Phase III will require the FDA approval and application in clinical trials.The research parameters were translated into a designed product that fits comfortably in human head and fed from an external RF source that generates an RF power deposition with a SAR of 0.4-0.9 W/kg to a realistic numerical brain. The engineering design is flexible by varying the leg capacitors of the Meander Line Antenna (MLA) devices. Thermal outcomes of the resu
{"title":"A Novel Design of a Portable Birdcage via Meander Line Antenna (MLA) to Lower Beta Amyloid (Aβ) in Alzheimer’s Disease","authors":"Felipe Perez;Jorge Morisaki;Haitham Kanakri;Maher Rizkalla;Ahmed Abdalla","doi":"10.1109/JTEHM.2025.3559693","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3559693","url":null,"abstract":"Late Onset Alzheimer’s Disease (LOAD) is the most common cause of dementia, characterized by the deposition of plaques primarily of neurotoxic amyloid-<inline-formula> <tex-math>$beta $ </tex-math></inline-formula> (<inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula>) peptide and tau protein. Our objective is to develop a noninvasive therapy to decrease the toxic A<inline-formula> <tex-math>$beta $ </tex-math></inline-formula> levels, using repeated electromagnetic field stimulation (REMFS) in the brain of Alzheimer’s disease patients. We previously examined the effects of REMFS on <inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula> levels in primary human brain (PHB) cultures at different frequencies, powers, and specific absorption rates (SAR). PHB cultures at day in vitro (DIV7) treated with 64 MHz with a SAR of 0.6 W/Kg, one hour daily for 14 days (DIV 21) had significantly reduced (p =0.001) levels of secreted <inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula>-42 and <inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula>-40 peptide without evidence of toxicity. The EMF frequency and power, and SAR levels used in our work is utilized in MRI’s, thus suggesting REMFS can be further developed in clinical settings to lower (<inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula>) levels and improve the memory in AD patients. These findings and numerous studies in rodent AD models prompted us to design a portable RF device, appropriate for human use, that will deliver a homogeneous RF power deposition with a SAR value of 0.4-0.9 W/kg to all human brain memory areas, lower (<inline-formula> <tex-math>$Abeta $ </tex-math></inline-formula>) levels, and potentially improve memory in human AD patients.The research took place at the Indiana University School of Medicine (IUSM) and Purdue University Indianapolis. The first phase was done in PHB cultures at the IUSM. Through this phase, we found that a 64 MHz frequency and an RF power deposition with a SAR of 0.4-0.6 W/kg reduced the (A<inline-formula> <tex-math>$beta $ </tex-math></inline-formula>) levels potentially impacting Alzheimer’s disease. The second phase of the project was conducted at Purdue University, we used ANSYS HFSS (High Frequency Simulation System) to design the devices that produced an appropriate penetration depth, polarization, and power deposition with a SAR of 0.4-0.9 W/kg to all memory brain areas of several numerical models. In Phase II-B will validate the device in a physical phantom. Phase III will require the FDA approval and application in clinical trials.The research parameters were translated into a designed product that fits comfortably in human head and fed from an external RF source that generates an RF power deposition with a SAR of 0.4-0.9 W/kg to a realistic numerical brain. The engineering design is flexible by varying the leg capacitors of the Meander Line Antenna (MLA) devices. Thermal outcomes of the resu","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"158-173"},"PeriodicalIF":3.7,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10962220","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883508","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：