IEEE Reviews in Biomedical Engineering最新文献

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. For the latest HFM papers and related resources, please refer to our website.

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.

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.

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.

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.

Cardiac digital twins (CDTs) are personalized virtual representations used to understand complex cardiac mechanisms. A critical component of CDT development is solving the ECG inverse problem, which enables the reconstruction of cardiac sources and the estimation of patient-specific electrophysiology (EP) parameters from surface ECG data. Despite challenges from complex cardiac anatomy, noisy ECG data, and the ill-posed nature of the inverse problem, recent advances in computational methods have greatly improved the accuracy and efficiency of ECG inverse inference, strengthening the fidelity of CDTs. This paper aims to provide a comprehensive review of the methods of solving ECG inverse problem, the validation strategies, the clinical applications, and future perspectives. For the methodologies, we broadly classify state-of-the-art approaches into two categories: deterministic and probabilistic methods, including both conventional and deep learning-based techniques. Integrating physics laws with deep learning models holds promise, but challenges such as capturing dynamic electrophysiology accurately, accessing accurate domain knowledge, and quantifying prediction uncertainty persist. Integrating models into clinical workflows while ensuring interpretability and usability for healthcare professionals is essential. Overcoming these challenges will drive further research in CDTs.

Magnetic Resonance Imaging (MRI) is a pivotal clinical diagnostic tool, yet its extended scanning times often compromise patient comfort and image quality, especially in volumetric, temporal and quantitative scans. This review elucidates recent advances in MRI acceleration via data and physics-driven models, leveraging techniques from algorithm unrolling models, enhancement-based methods, and plug-and-play models to the emerging full spectrum of generative model-based methods. We also explore the synergistic integration of data models with physics-based insights, encompassing the advancements in multi-coil hardware accelerations like parallel imaging and simultaneous multi-slice imaging, and the optimization of sampling patterns. We then focus on domain-specific challenges and opportunities, including image redundancy exploitation, image integrity, evaluation metrics, data heterogeneity, and model generalization. This work also discusses potential solutions and future research directions, with an emphasis on the role of data harmonization and federated learning for further improving the general applicability and performance of these methods in MRI reconstruction.

Breath analysis and monitoring have emerged as pivotal components in both clinical research and daily health management, particularly in addressing the global health challenges posed by respiratory and metabolic disorders. The advancement of breath analysis strategies necessitates a multidisciplinary approach, seamlessly integrating expertise from medicine, biology, engineering, and materials science. Recent innovations in laboratory methodologies and wearable sensing technologies have ushered in an era of precise, real-time, and in situ breath analysis and monitoring. This comprehensive review elucidates the physical and chemical aspects of breath analysis, encompassing respiratory parameters and both volatile and non-volatile constituents. It emphasizes their physiological and clinical significance, while also exploring cutting-edge laboratory testing techniques and state-of-the-art wearable devices. Furthermore, the review delves into the application of sophisticated data processing technologies in the burgeoning field of breathomics and examines the potential of breath control in human-machine interaction paradigms. Additionally, it provides insights into the challenges of translating innovative laboratory and wearable concepts into mainstream clinical and daily practice. Continued innovation and interdisciplinary collaboration will drive progress in breath analysis, potentially revolutionizing personalized medicine through entirely non-invasive breath methodology.

Brain-computer interface (BCI) is a rapidly evolving technology that has the potential to widely influence research, clinical and recreational use. Non-invasive BCI approaches are particularly common as they can impact a large number of participants safely and at a relatively low cost. Where traditional non-invasive BCIs were used for simple computer cursor tasks, it is now increasingly common for these systems to control robotic devices for complex tasks that may be useful in daily life. In this review, we provide an overview of the general BCI framework as well as the various methods that can be used to record neural activity, extract signals of interest, and decode brain states. In this context, we summarize the current state-of-the-art of non-invasive BCI research, focusing on trends in both the application of BCIs for controlling external devices and algorithm development to optimize their use. We also discuss various open-source BCI toolboxes and software, and describe their impact on the field at large.

Searching for similar images in archives of histology and histopathology images is a crucial task that may aid in patient tissue comparison for various purposes, ranging from triaging and diagnosis to prognosis and prediction. Whole slide images (WSIs) are highly detailed digital representations of tissue specimens mounted on glass slides. Matching WSI to WSI can serve as the critical method for patient tissue comparison. In this paper, we report extensive analysis and validation of four search methods bag of visual words (BoVW), Yottixel, SISH, RetCCL, and some of their potential variants. We analyze their algorithms and structures and assess their performance. For this evaluation, we utilized four internal datasets (1269 patients) and three public datasets (1207 patients), totaling more than 200, 000 patches from 38 different classes/subtypes across five primary sites. Certain search engines, for example, BoVW, exhibit notable efficiency and speed but suffer from low accuracy. Conversely, search engines like Yottixel demonstrate efficiency and speed, providing moderately accurate results. Recent proposals, including SISH, display inefficiency and yield inconsistent outcomes, while alternatives like RetCCL prove inadequate in both accuracy and efficiency. Further research is imperative to address the dual aspects of accuracy and minimal storage requirements in histopathological image search.