Blood vessel segmentation is a crucial aspect of medical image processing, aiding medical professionals in more accurate disease analysis and diagnosis. Manual blood vessel segmentation methods are time-consuming and cumbersome, making the development of automatic segmentation methods essential. The rapid advancements in deep learning technology have introduced new tools and methods for vascular image segmentation. In this review, we provide a comprehensive overview of deep learning-based blood vessel segmentation methods across various fields, including retinal vessel segmentation, cerebrovascular segmentation, and pulmonary vessel segmentation. Several prevalent diseases, such as retinal vascular diseases, cerebrovascular diseases, pulmonary vascular diseases, and tumors, have posed significant health challenges globally. This review also discusses the application of deep learning technology in disease diagnosis within these contexts. Finally, considering the current research landscape, we discuss existing challenges and potential future developments in blood vessel segmentation. We aim to assist researchers in gaining a comprehensive understanding and designing effective blood vessel segmentation models, ultimately offering opportunities for early disease diagnosis and treatment.
Fluorescence imaging (FI) has been instrumental in advancing biological research and enhancing biomedical diagnostics. Despite its widespread applications, FI faces challenges such as efficiently acquiring high signal-to-noise ratio (SNR) images, improving spatiotemporal resolution, and conducting precise quantitative analysis. Deep learning (DL), which emulates the neural network structure of the human brain, excels at learning from complex data patterns, extracting subtle features, and enhancing the SNR and spatiotemporal resolution of fluorescence images. These advancements significantly elevate the quality and usability of imaging data. Additionally, DL technology is adept at handling large datasets efficiently, which is crucial for improving the accuracy and efficiency of image analysis. This article reviews the latest advances in the application of DL to FI methodologies and their subsequent impact on biology and biomedicine. It also explores the future possibilities for DL in FI research, and providing insights and prospects could shape the field’s trajectory.
Colorectal cancer (CRC) ranks as the world’s second most prevalent cancer and third in mortality. Detection and diagnosis are crucial in research and clinical settings. While colonoscopy and computed tomographic colonography are widely used for identifying organic lesions, positron emission tomography (PET) and single-photon emission computed tomography (SPECT) offer superior visualization of molecular changes. These immuno-PET and immuno-SPECT techniques surpass conventional [18F] Fluorodeoxyglucose PET/CT in specificity and sensitivity, improving CRC diagnostics and supporting therapeutic strategies. This review emphasizes the role of immuno-PET/SPECT in CRC diagnosis and establishing a foundation for therapeutic strategies, facilitating hierarchical management through the identification of treatment-responsive populations, prediction of therapeutic outcomes, and support for intraoperative imaging. This review introduces the preclinical and clinical utility of immunoconjugates for detecting colorectal adenomas, and primary, metastatic, or recurrent CRC, focusing on specific CRC cell targets like the epidermal growth factor receptor and carcinoembryonic antigen. The review also covers various mAb-based immunoconjugates and engineered mAb fragments, including diabodies and minibodies. Finally, it looks into the great promise of machine learning in PET or SPECT and it addresses the challenges of translating preclinical successes into clinical practice for colorectal adenoma diagnosis, proposing potential solutions and directions for future research.
Reactive oxygen species (ROS) play pivotal roles in diverse physiological processes, exerting a significant influence on various organ systems within the human body. Recently, there has been a notable upswing in the design of nanomaterials based on natural enzymes with the ability to scavenge ROS. These nanomaterials hold promise as potent alternatives to conventional antioxidants. However, the conventional design of these materials has often relied on empirical and trial-and-error methods, posing challenges in capturing the intricate conformational relationships of nanozymes. This comprehensive review aims to consolidate rational design strategies and applications of nanozymes. Primarily, it advocates for an in-depth exploration of nanozyme mechanisms to facilitate precise design. Four rational design strategies: biomimetic design, experimental laws-driven design, computation-driven design, and data-driven design are scrutinized while considering their respective advantages, disadvantages, and application conditions. The review subsequently delves into the diverse applications of nanozymes across fields such as inflammatory diseases treatment, disease diagnosis, and environmental applications. Finally, the review outlines the challenges and prospects associated with the rational design of nanozymes while providing a comprehensive overview of this burgeoning area of research.
Fluorescence microscopy has emerged as a pivotal tool in biological and medical research, wherein the assessment of penetration depth and imaging resolution serves as crucial indicators of a microscope’s efficacy. However, the intricate interaction between photons and biological tissues gives rise to substantial background noise, presenting a formidable challenge. Fortunately, the near-infrared window (NIR), particularly the NIR-II range (1000–1700 nm), has emerged as a viable solution to mitigate these challenges and attain optimal imaging outcomes. This review centers on the progressive developments in light-sheet microscopy techniques, elucidating their distinctive characteristics and applications in the field of biological imaging. Furthermore, the incorporation of optical design enhancements, encompassing light-sheet microscopy is discussed as a pivotal strategy to augment imaging quality. The discussion extends to include refinements in imaging precision and the integration of deep learning methodologies with NIR imaging, especially for unique applications in NIR clinical exploration. The ensuing discourse endeavors to furnish a comprehensive synthesis of advancements in fluorescence microscopy, emphasizing the significance of the NIR windows, while also elucidating the role of sophisticated optical design and machine learning methodologies in enhancing overall imaging capabilities.
In recent years, motor imagery (MI) based on brain-computer interface (BCI) has gained the attention of researchers and been widely used in many fields, such as medical rehabilitation and entertainment. The temporal and spatial features of electroencephalography (EEG) are very important for MI-BCI classification. This study proposed a better spatiotemporal feature extraction method by combining the common spatial pattern (CSP) with a hybrid spatiotemporal attention convolutional neural network (HSTA-Net) model. The method first intercepts the MI-EEG into multiple time windows and projects them into the feature space and feeds into the HSTA-Net in parallel. Subsequently, the scaled dot product attention module and multi-head attention module are used to extract spatial feature attention. Finally, the features in multiple time windows obtained through HSTA-Net are integrated and used for classification. The proposed method achieves a classification accuracy of 77.3% on the BCI Competition IV2a dataset. The experimental results show that the proposed model has better classification performance. The CSP-HSTA-Net model can quickly adapt to the distribution of MI-EEG data during the training process, which increases the interclass distance of the extracted features and decreases its intraclass distance; it can better accomplish the MI-BCI classification task.