Pub Date : 2025-01-29DOI: 10.1109/JTEHM.2025.3536441
Yuhao Tang;Ye Yuan;Fei Tao;Minghao Tang
In clinical practice, interpreting medical images and composing diagnostic reports typically involve significant manual workload. Therefore, an automated report generation framework that mimics a doctor’s diagnosis better meets the requirements of medical scenarios. Prior investigations often overlook this critical aspect, primarily relying on traditional image captioning frameworks initially designed for general-domain images and sentences. Despite achieving some advancements, these methodologies encounter two primary challenges. First, the strong noise in blurred medical images always hinders the model of capturing the lesion region. Second, during report writing, doctors typically rely on terminology for diagnosis, a crucial aspect that has been neglected in prior frameworks. In this paper, we present a novel approach called Cross-modal Augmented Transformer (CAT) for medical report generation. Unlike previous methods that rely on coarse-grained features without human intervention, our method introduces a “locate then generate” pattern, thereby improving the interpretability of the generated reports. During the locate stage, CAT captures crucial representations by pre-aligning significant patches and their corresponding medical terminologies. This pre-alignment helps reduce visual noise by discarding low-ranking content, ensuring that only relevant information is considered in the report generation process. During the generation phase, CAT utilizes a multi-modality encoder to reinforce the correlation between generated keywords, retrieved terminologies and regions. Furthermore, CAT employs a dual-stream decoder that dynamically determines whether the predicted word should be influenced by the retrieved terminology or the preceding sentence. Experimental results demonstrate the effectiveness of the proposed method on two datasets.Clinical impact: This work aims to design an automated framework for explaining medical images to evaluate the health status of individuals, thereby facilitating their broader application in clinical settings.Clinical and Translational Impact Statement: In our preclinical research, we develop an automated system for generating diagnostic reports. This system mimics manual diagnostic methods by combining fine-grained semantic alignment with dual-stream decoders.
{"title":"Cross-Modal Augmented Transformer for Automated Medical Report Generation","authors":"Yuhao Tang;Ye Yuan;Fei Tao;Minghao Tang","doi":"10.1109/JTEHM.2025.3536441","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3536441","url":null,"abstract":"In clinical practice, interpreting medical images and composing diagnostic reports typically involve significant manual workload. Therefore, an automated report generation framework that mimics a doctor’s diagnosis better meets the requirements of medical scenarios. Prior investigations often overlook this critical aspect, primarily relying on traditional image captioning frameworks initially designed for general-domain images and sentences. Despite achieving some advancements, these methodologies encounter two primary challenges. First, the strong noise in blurred medical images always hinders the model of capturing the lesion region. Second, during report writing, doctors typically rely on terminology for diagnosis, a crucial aspect that has been neglected in prior frameworks. In this paper, we present a novel approach called Cross-modal Augmented Transformer (CAT) for medical report generation. Unlike previous methods that rely on coarse-grained features without human intervention, our method introduces a “locate then generate” pattern, thereby improving the interpretability of the generated reports. During the locate stage, CAT captures crucial representations by pre-aligning significant patches and their corresponding medical terminologies. This pre-alignment helps reduce visual noise by discarding low-ranking content, ensuring that only relevant information is considered in the report generation process. During the generation phase, CAT utilizes a multi-modality encoder to reinforce the correlation between generated keywords, retrieved terminologies and regions. Furthermore, CAT employs a dual-stream decoder that dynamically determines whether the predicted word should be influenced by the retrieved terminology or the preceding sentence. Experimental results demonstrate the effectiveness of the proposed method on two datasets.Clinical impact: This work aims to design an automated framework for explaining medical images to evaluate the health status of individuals, thereby facilitating their broader application in clinical settings.Clinical and Translational Impact Statement: In our preclinical research, we develop an automated system for generating diagnostic reports. This system mimics manual diagnostic methods by combining fine-grained semantic alignment with dual-stream decoders.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"33-48"},"PeriodicalIF":3.7,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10857391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379493","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}
The high volume of emergency room patients often necessitates head CT examinations to rule out ischemic, hemorrhagic, or other organic pathologies. A system that enhances the diagnostic efficacy of head CT imaging in emergency settings through structured reporting would significantly improve clinical decision making. Currently, no AI solutions address this need. Thus, our research aims to develop an automatic radiology reporting system by directly analyzing brain anomalies in head CT data. We propose a multi-branch CNN-LSTM fusion network-driven system for enhanced radiology reporting in emergency settings. We preprocessed head CT scans by resizing all slices, selecting those with significant variability, and applying PCA to retain 95% of the original data variance, ultimately saving the most representative five slices for each scan. We linked the reports to their respective slice IDs, divided them into individual captions, and preprocessed each. We performed an 80-20 split of the dataset for ten times, with 15% of the training set used for validation. Our model utilizes a pretrained VGG16, processing groups of five slices simultaneously, and features multiple end-to-end LSTM branches, each specialized in predicting one caption, subsequently combined to form the ordered reports after a BERT-based semantic evaluation. Our system demonstrates effectiveness and stability, with the postprocessing stage refining the syntax of the generated descriptions. However, there remains an opportunity to empower the evaluation framework to more accurately assess the clinical relevance of the automatically-written reports. Part of future work will include transitioning to 3D and developing an improved version based on vision-language models.
{"title":"Multi-Branch CNN-LSTM Fusion Network-Driven System With BERT Semantic Evaluator for Radiology Reporting in Emergency Head CTs","authors":"Selene Tomassini;Damiano Duranti;Abdallah Zeggada;Carlo Cosimo Quattrocchi;Farid Melgani;Paolo Giorgini","doi":"10.1109/JTEHM.2025.3535676","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3535676","url":null,"abstract":"The high volume of emergency room patients often necessitates head CT examinations to rule out ischemic, hemorrhagic, or other organic pathologies. A system that enhances the diagnostic efficacy of head CT imaging in emergency settings through structured reporting would significantly improve clinical decision making. Currently, no AI solutions address this need. Thus, our research aims to develop an automatic radiology reporting system by directly analyzing brain anomalies in head CT data. We propose a multi-branch CNN-LSTM fusion network-driven system for enhanced radiology reporting in emergency settings. We preprocessed head CT scans by resizing all slices, selecting those with significant variability, and applying PCA to retain 95% of the original data variance, ultimately saving the most representative five slices for each scan. We linked the reports to their respective slice IDs, divided them into individual captions, and preprocessed each. We performed an 80-20 split of the dataset for ten times, with 15% of the training set used for validation. Our model utilizes a pretrained VGG16, processing groups of five slices simultaneously, and features multiple end-to-end LSTM branches, each specialized in predicting one caption, subsequently combined to form the ordered reports after a BERT-based semantic evaluation. Our system demonstrates effectiveness and stability, with the postprocessing stage refining the syntax of the generated descriptions. However, there remains an opportunity to empower the evaluation framework to more accurately assess the clinical relevance of the automatically-written reports. Part of future work will include transitioning to 3D and developing an improved version based on vision-language models.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"61-74"},"PeriodicalIF":3.7,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10856282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403879","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 : 2025-01-22DOI: 10.1109/JTEHM.2025.3532801
Hsiu-Lin Chen;Bor-Shing Lin;Chieh-Miao Chang;Hao-Wei Chung;Shu-Ting Yang;Bor-Shyh Lin
High-risk infants in the neonatal intensive care unit often encounter the problems with hemodynamic instability, and the poor blood circulation may cause shock or other sequelae. But the appearance of shock is not easy to be noticed in the initial stage, and most of the clinical judgments are subjectively dependent on the experienced physicians. Therefore, how to effectively evaluate the neonatal blood circulation state is important for the treatment in time. Although some instruments, such as laser Doppler flow meter, can estimate the information of blood flow, there is still lack of monitoring systems to evaluate the neonatal blood circulation directly. Based on the technique of near-infrared spectroscopy, an intelligent neonatal blood perfusion assessment system was proposed in this study, to monitor the changes of hemoglobin concentration and tissue oxygen saturation simultaneously and further estimate the neonatal blood perfusion. Several indexes were defined from the changes of hemoglobin parameters under applying and relaxing pressure to obtain the neonatal perfusion information. Moreover, the neural network-based classifier was also used to effectively classify the groups with different blood perfusion states. From the experimental results, the difference between the groups with different blood perfusion states could exactly be reflected on several defined indexes and could be effectively recognized by using the technique of neural network. Clinical and Translational Impact Statement—An intelligent neonatal blood perfusion assessment system was proposed to monitor the changes of hemoglobin concentration and tissue oxygen saturation simultaneously and further estimate the neonatal blood perfusion (Category: Preclinical Research)
{"title":"Intelligent Neonatal Blood Perfusion Assessment System Based on Near-Infrared Spectroscopy","authors":"Hsiu-Lin Chen;Bor-Shing Lin;Chieh-Miao Chang;Hao-Wei Chung;Shu-Ting Yang;Bor-Shyh Lin","doi":"10.1109/JTEHM.2025.3532801","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3532801","url":null,"abstract":"High-risk infants in the neonatal intensive care unit often encounter the problems with hemodynamic instability, and the poor blood circulation may cause shock or other sequelae. But the appearance of shock is not easy to be noticed in the initial stage, and most of the clinical judgments are subjectively dependent on the experienced physicians. Therefore, how to effectively evaluate the neonatal blood circulation state is important for the treatment in time. Although some instruments, such as laser Doppler flow meter, can estimate the information of blood flow, there is still lack of monitoring systems to evaluate the neonatal blood circulation directly. Based on the technique of near-infrared spectroscopy, an intelligent neonatal blood perfusion assessment system was proposed in this study, to monitor the changes of hemoglobin concentration and tissue oxygen saturation simultaneously and further estimate the neonatal blood perfusion. Several indexes were defined from the changes of hemoglobin parameters under applying and relaxing pressure to obtain the neonatal perfusion information. Moreover, the neural network-based classifier was also used to effectively classify the groups with different blood perfusion states. From the experimental results, the difference between the groups with different blood perfusion states could exactly be reflected on several defined indexes and could be effectively recognized by using the technique of neural network. Clinical and Translational Impact Statement—An intelligent neonatal blood perfusion assessment system was proposed to monitor the changes of hemoglobin concentration and tissue oxygen saturation simultaneously and further estimate the neonatal blood perfusion (Category: Preclinical Research)","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"23-32"},"PeriodicalIF":3.7,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10849653","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105528","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 : 2025-01-14DOI: 10.1109/JTEHM.2025.3529748
Saurabh Jain;Bijoy Dripta Barua Chowdhury;Jarrod M. Mosier;Vignesh Subbian;Kate Hughes;Young-Jun Son
For over 40 years, airway management simulation has been a cornerstone of medical training, aiming to reduce procedural risks for critically ill patients. However, existing simulation technologies often lack the versatility and realism needed to replicate the cognitive and physical challenges of complex airway management scenarios. We developed a novel Virtual Reality (VR)-based simulation system designed to enhance immersive airway management training and research. This system integrates physical and virtual environments with an external sensory framework to capture high-fidelity data on user performance. Advanced calibration techniques ensure precise positional tracking and realistic physics-based interactions, providing a cohesive mixed-reality experience. Validation studies conducted in a dedicated medical training center demonstrated the system’s effectiveness in replicating real-world conditions. Positional calibration accuracy was achieved within 0.1 cm, with parameter calibrations showing no significant discrepancies. Validation using Pre- and post-simulation surveys indicated positive feedback on training aspects, perceived usefulness, and ease of use. These results suggest that the system offers a significant improvement in procedural and cognitive training for high-stakes medical environments.
{"title":"Design and Development of an Integrated Virtual Reality (VR)-Based Training System for Difficult Airway Management","authors":"Saurabh Jain;Bijoy Dripta Barua Chowdhury;Jarrod M. Mosier;Vignesh Subbian;Kate Hughes;Young-Jun Son","doi":"10.1109/JTEHM.2025.3529748","DOIUrl":"https://doi.org/10.1109/JTEHM.2025.3529748","url":null,"abstract":"For over 40 years, airway management simulation has been a cornerstone of medical training, aiming to reduce procedural risks for critically ill patients. However, existing simulation technologies often lack the versatility and realism needed to replicate the cognitive and physical challenges of complex airway management scenarios. We developed a novel Virtual Reality (VR)-based simulation system designed to enhance immersive airway management training and research. This system integrates physical and virtual environments with an external sensory framework to capture high-fidelity data on user performance. Advanced calibration techniques ensure precise positional tracking and realistic physics-based interactions, providing a cohesive mixed-reality experience. Validation studies conducted in a dedicated medical training center demonstrated the system’s effectiveness in replicating real-world conditions. Positional calibration accuracy was achieved within 0.1 cm, with parameter calibrations showing no significant discrepancies. Validation using Pre- and post-simulation surveys indicated positive feedback on training aspects, perceived usefulness, and ease of use. These results suggest that the system offers a significant improvement in procedural and cognitive training for high-stakes medical environments.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"49-60"},"PeriodicalIF":3.7,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10841389","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403882","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}
Methamphetamine use disorder (MUD) is a substance use disorder. Because MUD has become more prevalent due to the COVID-19 pandemic, alternative ways to help the efficiency of mass screening of MUD are important. Previous studies used electroencephalogram (EEG), heart rate variability (HRV), and galvanic skin response (GSR) aberrations during the virtual reality (VR) induction of drug craving to accurately separate patients with MUD from the healthy controls. However, whether these abnormalities present without induction of drug-cue reactivity to enable separation between patients and healthy subjects remains unclear. Here, we propose a clinically comparable intelligent system using the fusion of 5–channel EEG, HRV, and GSR data during resting state to aid in detecting MUD. Forty-six patients with MUD and 26 healthy controls were recruited and machine learning methods were employed to systematically compare the classification results of different fusion models. The analytic results revealed that the fusion of HRV and GSR features leads to the most accurate separation rate of 79%. The use of EEG, HRV, and GSR features provides more robust information, leading to relatively similar and enhanced accuracy across different classifiers. In conclusion, we demonstrated that a clinically applicable intelligent system using resting-state EEG, ECG, and GSR features without the induction of drug cue reactivity enhances the detection of MUD. This system is easy to implement in the clinical setting and can save a lot of time on setting up and experimenting while maintaining excellent accuracy to assist in mass screening of MUD.
甲基苯丙胺使用障碍（Methamphetamine use disorder， MUD）是一种物质使用障碍。由于COVID-19大流行使MUD变得更加普遍，因此提高MUD大规模筛查效率的替代方法非常重要。先前的研究使用虚拟现实（VR）诱导药物渴望时的脑电图（EEG）、心率变异性（HRV）和皮肤电反应（GSR）畸变来准确区分MUD患者和健康对照组。然而，这些异常是否没有引起药物提示反应，从而使患者与健康受试者分离，目前尚不清楚。在这里，我们提出了一种临床可比较的智能系统，该系统使用静息状态下的5通道EEG， HRV和GSR数据融合来帮助检测MUD。选取46例MUD患者和26例健康对照者，采用机器学习方法系统比较不同融合模型的分类结果。分析结果表明，HRV和GSR特征的融合使分离准确率达到79%。EEG、HRV和GSR特征的使用提供了更鲁棒的信息，导致不同分类器之间相对相似和提高的准确性。总之，我们证明了一个临床适用的智能系统，利用静息状态EEG， ECG和GSR特征，而不诱导药物线索反应性，可以增强对MUD的检测。该系统易于在临床环境中实施，可以节省大量的设置和实验时间，同时保持良好的准确性，以协助大规模筛查MUD。
{"title":"Fusion Model Using Resting Neurophysiological Data to Help Mass Screening of Methamphetamine Use Disorder","authors":"Chun-Chuan Chen;Meng-Chang Tsai;Eric Hsiao-Kuang Wu;Shao-Rong Sheng;Jia-Jeng Lee;Yung-En Lu;Shih-Ching Yeh","doi":"10.1109/JTEHM.2024.3522356","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3522356","url":null,"abstract":"Methamphetamine use disorder (MUD) is a substance use disorder. Because MUD has become more prevalent due to the COVID-19 pandemic, alternative ways to help the efficiency of mass screening of MUD are important. Previous studies used electroencephalogram (EEG), heart rate variability (HRV), and galvanic skin response (GSR) aberrations during the virtual reality (VR) induction of drug craving to accurately separate patients with MUD from the healthy controls. However, whether these abnormalities present without induction of drug-cue reactivity to enable separation between patients and healthy subjects remains unclear. Here, we propose a clinically comparable intelligent system using the fusion of 5–channel EEG, HRV, and GSR data during resting state to aid in detecting MUD. Forty-six patients with MUD and 26 healthy controls were recruited and machine learning methods were employed to systematically compare the classification results of different fusion models. The analytic results revealed that the fusion of HRV and GSR features leads to the most accurate separation rate of 79%. The use of EEG, HRV, and GSR features provides more robust information, leading to relatively similar and enhanced accuracy across different classifiers. In conclusion, we demonstrated that a clinically applicable intelligent system using resting-state EEG, ECG, and GSR features without the induction of drug cue reactivity enhances the detection of MUD. This system is easy to implement in the clinical setting and can save a lot of time on setting up and experimenting while maintaining excellent accuracy to assist in mass screening of MUD.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"1-8"},"PeriodicalIF":3.7,"publicationDate":"2024-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10816093","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142938217","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 : 2024-12-13DOI: 10.1109/JTEHM.2024.3516335
{"title":"IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE","authors":"","doi":"10.1109/JTEHM.2024.3516335","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3516335","url":null,"abstract":"","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"C3-C3"},"PeriodicalIF":3.7,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10799104","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142825791","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 : 2024-12-13DOI: 10.1109/JTEHM.2024.3513733
{"title":">IEEE Journal on Translational Engineering in Medicine and Biology publication information","authors":"","doi":"10.1109/JTEHM.2024.3513733","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3513733","url":null,"abstract":"","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"C2-C2"},"PeriodicalIF":3.7,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10799063","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821245","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 : 2024-12-11DOI: 10.1109/JTEHM.2024.3507892
{"title":"List of Reviewers","authors":"","doi":"10.1109/JTEHM.2024.3507892","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3507892","url":null,"abstract":"","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"12 ","pages":"739-739"},"PeriodicalIF":3.7,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10794571","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810324","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 : 2024-12-02DOI: 10.1109/JTEHM.2024.3510429
Qunxi Dong;Yuhang Sheng;Junru Zhu;Honghong Liu;Zhigang Li;Jingyu Liu;Yalin Wang;Bin Hu
Based on available magnetic resonance imaging (MRI) studies, hippocampal alteration is one of the hallmarks during cognitive decline. However, the longitudinal hippocampal morphometric changes during the initial cognitive decline are unclear. Exploring a validated biomarker with high clinical relevance is urgent. This work proposed an automated MRI-driven longitudinal hippocampal alteration analysis system (LHAAS), which consists of hippocampal segmentation, reconstruction, registration, multivariate morphometric feature extraction, and longitudinal analysis of hippocampal morphometric and volumetric differences between groups. LHAAS was applied on two groups: cognitive unimpaired (CU) participants who maintained cognitive unimpaired (non-Progressors), and participants who converted to MCI during the following four years (Progressors). LHAAS can detect and visualize subtle deformations in the bilateral hippocampus of CU progressors four years before they show initial cognitive decline. For CU progressors, hippocampal atrophy initially occurs at the CA1 subregion and then along with disease progression, spreading to the CA2-3 and Subiculum subregion, exhibiting a left-greater-than-right trend. The volumetric analyses showed similar results. Besides, hippocampal subregions highly correlated with clinical measurement were identified by correlation analysis. LHAAS can accurately reflect the small hippocampal subregional atrophy at preclinical AD. This proposed system can track the longitudinal hippocampal alterations in the early stages of AD and provide insights for early intervention. Clinical and Translational Impact Statement: LHAAS offers early detection of subtle hippocampal alterations at preclinical AD. This advance enables pathological research and timely interventions to potentially improve patient outcomes in clinical implementation.
{"title":"MRI-Driven Longitudinal Studies of Hippocampal Alterations During the Initial Cognitive Decline","authors":"Qunxi Dong;Yuhang Sheng;Junru Zhu;Honghong Liu;Zhigang Li;Jingyu Liu;Yalin Wang;Bin Hu","doi":"10.1109/JTEHM.2024.3510429","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3510429","url":null,"abstract":"Based on available magnetic resonance imaging (MRI) studies, hippocampal alteration is one of the hallmarks during cognitive decline. However, the longitudinal hippocampal morphometric changes during the initial cognitive decline are unclear. Exploring a validated biomarker with high clinical relevance is urgent. This work proposed an automated MRI-driven longitudinal hippocampal alteration analysis system (LHAAS), which consists of hippocampal segmentation, reconstruction, registration, multivariate morphometric feature extraction, and longitudinal analysis of hippocampal morphometric and volumetric differences between groups. LHAAS was applied on two groups: cognitive unimpaired (CU) participants who maintained cognitive unimpaired (non-Progressors), and participants who converted to MCI during the following four years (Progressors). LHAAS can detect and visualize subtle deformations in the bilateral hippocampus of CU progressors four years before they show initial cognitive decline. For CU progressors, hippocampal atrophy initially occurs at the CA1 subregion and then along with disease progression, spreading to the CA2-3 and Subiculum subregion, exhibiting a left-greater-than-right trend. The volumetric analyses showed similar results. Besides, hippocampal subregions highly correlated with clinical measurement were identified by correlation analysis. LHAAS can accurately reflect the small hippocampal subregional atrophy at preclinical AD. This proposed system can track the longitudinal hippocampal alterations in the early stages of AD and provide insights for early intervention. Clinical and Translational Impact Statement: LHAAS offers early detection of subtle hippocampal alterations at preclinical AD. This advance enables pathological research and timely interventions to potentially improve patient outcomes in clinical implementation.","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"98-110"},"PeriodicalIF":3.7,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10772627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143553306","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 : 2024-11-26DOI: 10.1109/JTEHM.2024.3506556
Lok Hua Lee;Cyrus Su Hui Ho;Yee Ling Chan;Gabrielle Wann Nii Tay;Cheng-Kai Lu;Tong Boon Tang
While functional near-infrared spectroscopy (fNIRS) had previously been suggested for major depressive disorder (MDD) diagnosis, the clinical application to predict antidepressant treatment response (ATR) is still unclear. To address this, the aim of the current study is to investigate MDD ATR at three response levels using fNIRS and micro-ribonucleic acids (miRNAs). Our proposed algorithm includes a custom inter-subject variability reduction based on the principal component analysis (PCA). The principal components of extracted features are first identified for non-responders’ group. The first few components that sum up to 99% of explained variance are discarded to minimize inter-subject variability while the remaining projection vectors are applied on all response groups (24 non-responders, 15 partial-responders, 13 responders) to obtain their relative projections in feature space. The entire algorithm achieved a better performance through the radial basis function (RBF) support vector machine (SVM), with 82.70% accuracy, 78.44% sensitivity, 86.15% precision, and 91.02% specificity, respectively, when compared with conventional machine learning approaches that combine clinical, sociodemographic and genetic information as the predictor. The performance of the proposed custom algorithm suggests the prediction of ATR can be improved with multiple features sources, provided that the inter-subject variability is properly addressed, and can be an effective tool for clinical decision support system in MDD ATR prediction. Clinical and Translational Impact Statement—The fusion of neuroimaging fNIRS features and miRNA profiles significantly enhances the prediction accuracy of MDD ATR. The minimally required features also make the personalized medicine more practical and realizable
{"title":"Antidepressant Treatment Response Prediction With Early Assessment of Functional Near-Infrared Spectroscopy and Micro-RNA","authors":"Lok Hua Lee;Cyrus Su Hui Ho;Yee Ling Chan;Gabrielle Wann Nii Tay;Cheng-Kai Lu;Tong Boon Tang","doi":"10.1109/JTEHM.2024.3506556","DOIUrl":"https://doi.org/10.1109/JTEHM.2024.3506556","url":null,"abstract":"While functional near-infrared spectroscopy (fNIRS) had previously been suggested for major depressive disorder (MDD) diagnosis, the clinical application to predict antidepressant treatment response (ATR) is still unclear. To address this, the aim of the current study is to investigate MDD ATR at three response levels using fNIRS and micro-ribonucleic acids (miRNAs). Our proposed algorithm includes a custom inter-subject variability reduction based on the principal component analysis (PCA). The principal components of extracted features are first identified for non-responders’ group. The first few components that sum up to 99% of explained variance are discarded to minimize inter-subject variability while the remaining projection vectors are applied on all response groups (24 non-responders, 15 partial-responders, 13 responders) to obtain their relative projections in feature space. The entire algorithm achieved a better performance through the radial basis function (RBF) support vector machine (SVM), with 82.70% accuracy, 78.44% sensitivity, 86.15% precision, and 91.02% specificity, respectively, when compared with conventional machine learning approaches that combine clinical, sociodemographic and genetic information as the predictor. The performance of the proposed custom algorithm suggests the prediction of ATR can be improved with multiple features sources, provided that the inter-subject variability is properly addressed, and can be an effective tool for clinical decision support system in MDD ATR prediction. Clinical and Translational Impact Statement—The fusion of neuroimaging fNIRS features and miRNA profiles significantly enhances the prediction accuracy of MDD ATR. The minimally required features also make the personalized medicine more practical and realizable","PeriodicalId":54255,"journal":{"name":"IEEE Journal of Translational Engineering in Health and Medicine-Jtehm","volume":"13 ","pages":"9-22"},"PeriodicalIF":3.7,"publicationDate":"2024-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10767732","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993375","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：