Lung cancer is the leading cause of cancer-related mortality worldwide. In addition to localizing and segmenting lung nodules, a non-invasive risk assessment system can also help clinicians tailor treatment decisions in a timely manner, ultimately improving patient outcomes. Artificial intelligence (AI) technologies are increasingly being used in medical imaging to assess the risk of lung nodules, especially for malignancy classification. However, little research has been conducted on the assessment of other related risks. This work comprehensively reviews AI applications in lung nodule risk assessment, including malignancy diagnosis, pathological subtype assessment, metastasis risk evaluation, specific receptor expression identification, and disease progression tracking. It details common public databases used and state-of-the-art AI techniques, along with their benefits and challenges like data scarcity, generalizability, and interpretability. We anticipate that future research will tackle these issues, thereby increasing the improved interpretability and generalizability of AI methods in clinical workflows.
{"title":"Review of Artificial Intelligence in Lung Nodule Risk Assessment","authors":"Ying Wei;Qing Zhou;Jiaojiao Wu;Xiaoxian Xu;Yaozong Gao;Lei Chen;Yiqiang Zhan;Xiang Sean Zhou;Chengdi Wang;Feng Shi;Dinggang Shen","doi":"10.1109/RBME.2025.3528946","DOIUrl":"10.1109/RBME.2025.3528946","url":null,"abstract":"Lung cancer is the leading cause of cancer-related mortality worldwide. In addition to localizing and segmenting lung nodules, a non-invasive risk assessment system can also help clinicians tailor treatment decisions in a timely manner, ultimately improving patient outcomes. Artificial intelligence (AI) technologies are increasingly being used in medical imaging to assess the risk of lung nodules, especially for malignancy classification. However, little research has been conducted on the assessment of other related risks. This work comprehensively reviews AI applications in lung nodule risk assessment, including malignancy diagnosis, pathological subtype assessment, metastasis risk evaluation, specific receptor expression identification, and disease progression tracking. It details common public databases used and state-of-the-art AI techniques, along with their benefits and challenges like data scarcity, generalizability, and interpretability. We anticipate that future research will tackle these issues, thereby increasing the improved interpretability and generalizability of AI methods in clinical workflows.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"19 ","pages":"412-427"},"PeriodicalIF":12.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143543539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1109/RBME.2024.3514378
Adriana Blazeski;Guillermo García-Cardeña;Roger D. Kamm
Cardiac organoids represent an important bioengineering opportunity in the development of models to study human heart pathophysiology. By incorporating multiple cardiac cell types in three-dimensional culture and developmentally-guided biochemical signaling, cardiac organoids recapitulate numerous features of heart tissue. However, cardiac tissue also experiences a variety of mechanical forces as the heart develops and over the course of each contraction cycle. It is now clear that these forces impact cellular specification, phenotype, and function, and should be incorporated into the engineering of cardiac organoids in order to generate better models. In this review, we discuss strategies for engineering cardiac organoids and report the effects of organoid design on the function of cardiac cells. We then discuss the mechanical environment of the heart, including forces arising from tissue elasticity, contraction, blood flow, and stretch, and report on efforts to mimic these biophysical cues in cardiac organoids. Finally, we review emerging areas of cardiac organoid research, for the study of cardiac development, the formation of multi-organ models, and the simulation of the effects of spaceflight on cardiac tissue, and consider how these investigations might benefit from the inclusion of mechanical cues.
{"title":"Advancing Cardiac Organoid Engineering Through Application of Biophysical Forces","authors":"Adriana Blazeski;Guillermo García-Cardeña;Roger D. Kamm","doi":"10.1109/RBME.2024.3514378","DOIUrl":"https://doi.org/10.1109/RBME.2024.3514378","url":null,"abstract":"Cardiac organoids represent an important bioengineering opportunity in the development of models to study human heart pathophysiology. By incorporating multiple cardiac cell types in three-dimensional culture and developmentally-guided biochemical signaling, cardiac organoids recapitulate numerous features of heart tissue. However, cardiac tissue also experiences a variety of mechanical forces as the heart develops and over the course of each contraction cycle. It is now clear that these forces impact cellular specification, phenotype, and function, and should be incorporated into the engineering of cardiac organoids in order to generate better models. In this review, we discuss strategies for engineering cardiac organoids and report the effects of organoid design on the function of cardiac cells. We then discuss the mechanical environment of the heart, including forces arising from tissue elasticity, contraction, blood flow, and stretch, and report on efforts to mimic these biophysical cues in cardiac organoids. Finally, we review emerging areas of cardiac organoid research, for the study of cardiac development, the formation of multi-organ models, and the simulation of the effects of spaceflight on cardiac tissue, and consider how these investigations might benefit from the inclusion of mechanical cues.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"211-230"},"PeriodicalIF":17.2,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The human ear has emerged as a bidirectional gateway to the brain's and body's signals. Recent advances in around-the-ear and in-ear sensors have enabled the assessment of biomarkers and physiomarkers derived from brain and cardiac activity using ear-electroencephalography (ear-EEG), photoplethysmography (ear-PPG), and chemical sensing of analytes from the ear, with ear-EEG having been taken beyond-the-lab to outer space. Parallel advances in non-invasive and minimally invasive brain stimulation techniques have leveraged the ear's access to two cranial nerves to modulate brain and body activity. The vestibulocochlear nerve stimulates the auditory cortex and limbic system with sound, while the auricular branch of the vagus nerve indirectly but significantly couples to the autonomic nervous system and cardiac output. Acoustic and current mode stimuli delivered using discreet and unobtrusive earables are an active area of research, aiming to make biofeedback and bioelectronic medicine deliverable outside of the clinic, with remote and continuous monitoring of therapeutic responsivity and long-term adaptation. Leveraging recent advances in ear-EEG, transcutaneous auricular vagus nerve stimulation (taVNS), and unobtrusive acoustic stimulation, we review accumulating evidence that combines their potential into an integrated earable platform for closed-loop multimodal sensing and neuromodulation, towards personalized and holistic therapies that are near, in- and around-the-ear.
{"title":"Earable Multimodal Sensing and Stimulation: A Prospective Toward Unobtrusive Closed-Loop Biofeedback","authors":"Yuchen Xu;Abhinav Uppal;Min Suk Lee;Kuldeep Mahato;Brian L. Wuerstle;Muyang Lin;Omeed Djassemi;Tao Chen;Rui Lin;Akshay Paul;Soumil Jain;Florian Chapotot;Esra Tasali;Patrick Mercier;Sheng Xu;Joseph Wang;Gert Cauwenberghs","doi":"10.1109/RBME.2024.3508713","DOIUrl":"https://doi.org/10.1109/RBME.2024.3508713","url":null,"abstract":"The human ear has emerged as a bidirectional gateway to the brain's and body's signals. Recent advances in around-the-ear and in-ear sensors have enabled the assessment of biomarkers and physiomarkers derived from brain and cardiac activity using ear-electroencephalography (ear-EEG), photoplethysmography (ear-PPG), and chemical sensing of analytes from the ear, with ear-EEG having been taken beyond-the-lab to outer space. Parallel advances in non-invasive and minimally invasive brain stimulation techniques have leveraged the ear's access to two cranial nerves to modulate brain and body activity. The vestibulocochlear nerve stimulates the auditory cortex and limbic system with sound, while the auricular branch of the vagus nerve indirectly but significantly couples to the autonomic nervous system and cardiac output. Acoustic and current mode stimuli delivered using discreet and unobtrusive earables are an active area of research, aiming to make biofeedback and bioelectronic medicine deliverable outside of the clinic, with remote and continuous monitoring of therapeutic responsivity and long-term adaptation. Leveraging recent advances in ear-EEG, transcutaneous auricular vagus nerve stimulation (taVNS), and unobtrusive acoustic stimulation, we review accumulating evidence that combines their potential into an integrated earable platform for closed-loop multimodal sensing and neuromodulation, towards personalized and holistic therapies that are near, in- and around-the-ear.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"5-25"},"PeriodicalIF":17.2,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105660","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-22DOI: 10.1109/RBME.2024.3505073
N. S. Sarna;N. M. Curry;E. Aalaei;B. G. Kaufman;M. R. King
Immunomechanobiology, the study of how physical forces influence the behavior and function of immune cells, is a rapidly growing area of research. It is becoming increasingly recognized that mechanical stimuli, such as fluid shear forces, are a critical determinant of immune cell regulation. In this review, we discuss the principles and significance of various mechanical forces present within the human body, with a focus on fluid shear flow and its impact on immune cell activation and function. Moreover, we discuss engineering approaches used to study immune cell mechanobiology, and their implications in health and diseases such as cancer, autoimmune disorders, and infectious disease.
{"title":"Immunomechanobiology: Engineering the Activation and Function of Immune Cells With the Mechanical Signal of Fluid Shear Stress","authors":"N. S. Sarna;N. M. Curry;E. Aalaei;B. G. Kaufman;M. R. King","doi":"10.1109/RBME.2024.3505073","DOIUrl":"https://doi.org/10.1109/RBME.2024.3505073","url":null,"abstract":"Immunomechanobiology, the study of how physical forces influence the behavior and function of immune cells, is a rapidly growing area of research. It is becoming increasingly recognized that mechanical stimuli, such as fluid shear forces, are a critical determinant of immune cell regulation. In this review, we discuss the principles and significance of various mechanical forces present within the human body, with a focus on fluid shear flow and its impact on immune cell activation and function. Moreover, we discuss engineering approaches used to study immune cell mechanobiology, and their implications in health and diseases such as cancer, autoimmune disorders, and infectious disease.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"231-249"},"PeriodicalIF":17.2,"publicationDate":"2024-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10764720","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-21DOI: 10.1109/RBME.2024.3503761
Raid Halawani;Michael Buchert;Yi-Ping Phoebe Chen
Genomics plays an essential role in the early detection, classification, and targeted cancer therapy based on the analysis of precise alterations at the molecular level. Using the most reliable approach is essential for the exact interrogation and cross-examination of complex and multi-high-dimensional “Multi-omics” cancer genomics data. In recent years, deep learning has been successfully utilized to deal with large cancer genomics data and has the potential to transform predictive biology. This review aims to explore the recent advancements in the application of deep learning models in basic cancer omics research, including different methodologies for the interrogation of bulk cancer omics data and the importance of cross-platform data integration. The paper provides insights into advantages, limitations, potential for improvement, research gaps, future direction, and an in-depth comparison of the models currently used in the field of cancer genomics, highlighting the crucial need for collaboration and interdisciplinary research in the field.
{"title":"Utilizing Neurons to Interrogate Cancer: Integrative Analysis of Cancer Omics Data With Deep Learning Models","authors":"Raid Halawani;Michael Buchert;Yi-Ping Phoebe Chen","doi":"10.1109/RBME.2024.3503761","DOIUrl":"https://doi.org/10.1109/RBME.2024.3503761","url":null,"abstract":"Genomics plays an essential role in the early detection, classification, and targeted cancer therapy based on the analysis of precise alterations at the molecular level. Using the most reliable approach is essential for the exact interrogation and cross-examination of complex and multi-high-dimensional “Multi-omics” cancer genomics data. In recent years, deep learning has been successfully utilized to deal with large cancer genomics data and has the potential to transform predictive biology. This review aims to explore the recent advancements in the application of deep learning models in basic cancer omics research, including different methodologies for the interrogation of bulk cancer omics data and the importance of cross-platform data integration. The paper provides insights into advantages, limitations, potential for improvement, research gaps, future direction, and an in-depth comparison of the models currently used in the field of cancer genomics, highlighting the crucial need for collaboration and interdisciplinary research in the field.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"281-299"},"PeriodicalIF":17.2,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Foundation model, trained on a diverse range of data and adaptable to a myriad of tasks, is advancing healthcare. It fosters the development of healthcare artificial intelligence (AI) models tailored to the intricacies of the medical field, bridging the gap between limited AI models and the varied nature of healthcare practices. The advancement of a healthcare foundation model (HFM) brings forth tremendous potential to augment intelligent healthcare services across a broad spectrum of scenarios. However, despite the imminent widespread deployment of HFMs, there is currently a lack of clear understanding regarding their operation in the healthcare field, their existing challenges, and their future trajectory. To answer these critical inquiries, we present a comprehensive and in-depth examination that delves into the landscape of HFMs. It begins with a comprehensive overview of HFMs, encompassing their methods, data, and applications, to provide a quick understanding of the current progress. Subsequently, it delves into a thorough exploration of the challenges associated with data, algorithms, and computing infrastructures in constructing and widely applying foundation models in healthcare. Furthermore, this survey identifies promising directions for future development in this field. We believe that this survey will enhance the community's understanding of the current progress of HFMs and serve as a valuable source of guidance for future advancements in this domain.
基金会模型在各种数据基础上进行训练，可适应无数任务，正在推动医疗保健事业的发展。它促进了医疗人工智能（AI）模型的发展，使其适合医疗领域的复杂性，弥补了有限的 AI 模型与医疗实践的多样性之间的差距。医疗保健基础模型（HFM）的发展为在各种场景中增强智能医疗保健服务带来了巨大潜力。然而，尽管 HFM 的广泛部署迫在眉睫，但目前人们对其在医疗保健领域的运作、现有挑战及其未来发展轨迹还缺乏清晰的认识。为了回答这些关键问题，我们对高频医疗设备的发展前景进行了全面深入的研究。首先，我们将全面概述高频市场，包括其方法、数据和应用，以便快速了解当前的进展情况。随后，它深入探讨了在医疗保健领域构建和广泛应用基础模型时与数据、算法和计算基础设施相关的挑战。此外，本调查还为该领域的未来发展指明了前景广阔的方向。我们相信，这份调查报告将增进社区对 HFM 当前进展的了解，并为该领域的未来发展提供宝贵的指导。如需了解最新的 HFM 论文和相关资源，请访问我们的网站。
{"title":"Foundation Model for Advancing Healthcare: Challenges, Opportunities and Future Directions","authors":"Yuting He;Fuxiang Huang;Xinrui Jiang;Yuxiang Nie;Minghao Wang;Jiguang Wang;Hao Chen","doi":"10.1109/RBME.2024.3496744","DOIUrl":"10.1109/RBME.2024.3496744","url":null,"abstract":"Foundation model, trained on a diverse range of data and adaptable to a myriad of tasks, is advancing healthcare. It fosters the development of healthcare artificial intelligence (AI) models tailored to the intricacies of the medical field, bridging the gap between limited AI models and the varied nature of healthcare practices. The advancement of a healthcare foundation model (HFM) brings forth tremendous potential to augment intelligent healthcare services across a broad spectrum of scenarios. However, despite the imminent widespread deployment of HFMs, there is currently a lack of clear understanding regarding their operation in the healthcare field, their existing challenges, and their future trajectory. To answer these critical inquiries, we present a comprehensive and in-depth examination that delves into the landscape of HFMs. It begins with a comprehensive overview of HFMs, encompassing their methods, data, and applications, to provide a quick understanding of the current progress. Subsequently, it delves into a thorough exploration of the challenges associated with data, algorithms, and computing infrastructures in constructing and widely applying foundation models in healthcare. Furthermore, this survey identifies promising directions for future development in this field. We believe that this survey will enhance the community's understanding of the current progress of HFMs and serve as a valuable source of guidance for future advancements in this domain.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"172-191"},"PeriodicalIF":17.2,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142630123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-08DOI: 10.1109/RBME.2024.3494715
Yesh Doctor;Milan Sanghvi;Prashant Mali
Genome and transcriptome engineering have emerged as powerful tools in modern biotechnology, driving advancements in precision medicine and novel therapeutics. In this review, we provide a comprehensive overview of the current methodologies, applications, and future directions in genome and transcriptome engineering. Through this, we aim to provide a guide for tool selection, critically analyzing the strengths, weaknesses, and best use cases of these tools to provide context on their suitability for various applications. We explore standard and recent developments in genome engineering, such as base editors and prime editing, and provide insight into tool selection for change of function (knockout, deletion, insertion, substitution) and change of expression (repression, activation) contexts. Advancements in transcriptome engineering are also explored, focusing on established technologies like antisense oligonucleotides (ASOs) and RNA interference (RNAi), as well as recent developments such as CRISPR-Cas13 and adenosine deaminases acting on RNA (ADAR). This review offers a comparison of different approaches to achieve similar biological goals, and consideration of high-throughput applications that enable the probing of a variety of targets. This review elucidates the transformative impact of genome and transcriptome engineering on biological research and clinical applications that will pave the way for future innovations in the field.
{"title":"A Manual for Genome and Transcriptome Engineering","authors":"Yesh Doctor;Milan Sanghvi;Prashant Mali","doi":"10.1109/RBME.2024.3494715","DOIUrl":"10.1109/RBME.2024.3494715","url":null,"abstract":"Genome and transcriptome engineering have emerged as powerful tools in modern biotechnology, driving advancements in precision medicine and novel therapeutics. In this review, we provide a comprehensive overview of the current methodologies, applications, and future directions in genome and transcriptome engineering. Through this, we aim to provide a guide for tool selection, critically analyzing the strengths, weaknesses, and best use cases of these tools to provide context on their suitability for various applications. We explore standard and recent developments in genome engineering, such as base editors and prime editing, and provide insight into tool selection for change of function (knockout, deletion, insertion, substitution) and change of expression (repression, activation) contexts. Advancements in transcriptome engineering are also explored, focusing on established technologies like antisense oligonucleotides (ASOs) and RNA interference (RNAi), as well as recent developments such as CRISPR-Cas13 and adenosine deaminases acting on RNA (ADAR). This review offers a comparison of different approaches to achieve similar biological goals, and consideration of high-throughput applications that enable the probing of a variety of targets. This review elucidates the transformative impact of genome and transcriptome engineering on biological research and clinical applications that will pave the way for future innovations in the field.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"250-267"},"PeriodicalIF":17.2,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142606573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Large-scale Artificial General Intelligence (AGI) models, including Large Language Models (LLMs) such as ChatGPT/GPT-4, have achieved unprecedented success in a variety of general domain tasks. Yet, when applied directly to specialized domains like medical imaging, which require in-depth expertise, these models face notable challenges arising from the medical field's inherent complexities and unique characteristics. In this review, we delve into the potential applications of AGI models in medical imaging and healthcare, with a primary focus on LLMs, Large Vision Models, and Large Multimodal Models. We provide a thorough overview of the key features and enabling techniques of LLMs and AGI, and further examine the roadmaps guiding the evolution and implementation of AGI models in the medical sector, summarizing their present applications, potentialities, and associated challenges. In addition, we highlight potential future research directions, offering a holistic view on upcoming ventures. This comprehensive review aims to offer insights into the future implications of AGI in medical imaging, healthcare, and beyond.
{"title":"Artificial General Intelligence for Medical Imaging Analysis","authors":"Xiang Li;Lin Zhao;Lu Zhang;Zihao Wu;Zhengliang Liu;Hanqi Jiang;Chao Cao;Shaochen Xu;Yiwei Li;Haixing Dai;Yixuan Yuan;Jun Liu;Gang Li;Dajiang Zhu;Pingkun Yan;Quanzheng Li;Wei Liu;Tianming Liu;Dinggang Shen","doi":"10.1109/RBME.2024.3493775","DOIUrl":"10.1109/RBME.2024.3493775","url":null,"abstract":"Large-scale Artificial General Intelligence (AGI) models, including Large Language Models (LLMs) such as ChatGPT/GPT-4, have achieved unprecedented success in a variety of general domain tasks. Yet, when applied directly to specialized domains like medical imaging, which require in-depth expertise, these models face notable challenges arising from the medical field's inherent complexities and unique characteristics. In this review, we delve into the potential applications of AGI models in medical imaging and healthcare, with a primary focus on LLMs, Large Vision Models, and Large Multimodal Models. We provide a thorough overview of the key features and enabling techniques of LLMs and AGI, and further examine the roadmaps guiding the evolution and implementation of AGI models in the medical sector, summarizing their present applications, potentialities, and associated challenges. In addition, we highlight potential future research directions, offering a holistic view on upcoming ventures. This comprehensive review aims to offer insights into the future implications of AGI in medical imaging, healthcare, and beyond.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"113-129"},"PeriodicalIF":17.2,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142606494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-06DOI: 10.1109/RBME.2024.3490455
P. Hunter;B. de Bono;D. Brooks;R. Christie;J. Hussan;M. Lin;D. Nickerson
Interest in the concept of a virtual human model that can encompass human physiology and anatomy on a biophysical (mechanistic) basis, and can assist with the clinical diagnosis and treatment of disease, appears to be growing rapidly around the globe. When such models are personalised and coupled with continual diagnostic measurements, they are called ‘digital twins’. We argue here that the most useful form of virtual human model will be one that is constrained by the laws of physics, contains a comprehensive knowledge graph of all human physiology and anatomy, is multiscale in the sense of linking systems physiology down to protein function, and can to some extent be personalized and linked directly with clinical records. We discuss current progress from the IUPS Physiome Project and the requirements for a framework to achieve such a model.
{"title":"The Physiome Project and Digital Twins","authors":"P. Hunter;B. de Bono;D. Brooks;R. Christie;J. Hussan;M. Lin;D. Nickerson","doi":"10.1109/RBME.2024.3490455","DOIUrl":"10.1109/RBME.2024.3490455","url":null,"abstract":"Interest in the concept of a virtual human model that can encompass human physiology and anatomy on a biophysical (mechanistic) basis, and can assist with the clinical diagnosis and treatment of disease, appears to be growing rapidly around the globe. When such models are personalised and coupled with continual diagnostic measurements, they are called ‘digital twins’. We argue here that the most useful form of virtual human model will be one that is constrained by the laws of physics, contains a comprehensive knowledge graph of all human physiology and anatomy, is multiscale in the sense of linking systems physiology down to protein function, and can to some extent be personalized and linked directly with clinical records. We discuss current progress from the IUPS Physiome Project and the requirements for a framework to achieve such a model.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"300-315"},"PeriodicalIF":17.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142591973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-06DOI: 10.1109/RBME.2024.3492381
Chenqi Li;Timothy Denison;Tingting Zhu
Advancements in wearable sensor technologies and the digitization of medical records have contributed to the unprecedented ubiquity of biomedical time series data. Data-driven models have tremendous potential to assist clinical diagnosis and improve patient care by improving long-term monitoring capabilities, facilitating early disease detection and intervention, as well as promoting personalized healthcare delivery. However, accessing extensively labeled datasets to train data-hungry deep learning models encounters many barriers, such as long-tail distribution of rare diseases, cost of annotation, privacy and security concerns, data-sharing regulations, and ethical considerations. An emerging approach to overcome the scarcity of labeled data is to augment AI methods with human-like capabilities to leverage past experiences to learn new tasks with limited examples, called few-shot learning. This survey provides a comprehensive review and comparison of few-shot learning methods for biomedical time series applications. The clinical benefits and limitations of such methods are discussed in relation to traditional data-driven approaches. This paper aims to provide insights into the current landscape of few-shot learning for biomedical time series and its implications for future research and applications.
{"title":"A Survey of Few-Shot Learning for Biomedical Time Series","authors":"Chenqi Li;Timothy Denison;Tingting Zhu","doi":"10.1109/RBME.2024.3492381","DOIUrl":"10.1109/RBME.2024.3492381","url":null,"abstract":"Advancements in wearable sensor technologies and the digitization of medical records have contributed to the unprecedented ubiquity of biomedical time series data. Data-driven models have tremendous potential to assist clinical diagnosis and improve patient care by improving long-term monitoring capabilities, facilitating early disease detection and intervention, as well as promoting personalized healthcare delivery. However, accessing extensively labeled datasets to train data-hungry deep learning models encounters many barriers, such as long-tail distribution of rare diseases, cost of annotation, privacy and security concerns, data-sharing regulations, and ethical considerations. An emerging approach to overcome the scarcity of labeled data is to augment AI methods with human-like capabilities to leverage past experiences to learn new tasks with limited examples, called few-shot learning. This survey provides a comprehensive review and comparison of few-shot learning methods for biomedical time series applications. The clinical benefits and limitations of such methods are discussed in relation to traditional data-driven approaches. This paper aims to provide insights into the current landscape of few-shot learning for biomedical time series and its implications for future research and applications.","PeriodicalId":39235,"journal":{"name":"IEEE Reviews in Biomedical Engineering","volume":"18 ","pages":"192-210"},"PeriodicalIF":17.2,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10745649","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142591972","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","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：