Abstract: Accurate detection of abnormal cells is essential for early screening and precise diagnosis of cervical cancer. Despite the recent advances in deep learning-based methods for cervical cancer detection, their broad clinical applications are hindered by several technical challenges. On the one hand, gradually evolved abnormal cells are visually similar to normal cells. On the other hand, single cells and cell clusters exhibit significant appearance variations, overlooking those between normal and abnormal cells. In order to overcome these challenges, we propose a novel dual-branch multi-granularity hierarchical contrast and cross attention network, called DMCA-Net. Specifically, DMCA-Net utilizes dual branches to detect abnormal and normal cells, respectively. Meanwhile, an inter-c

Abstract: Vascular channels embedded within tissue-engineered hydrogels play a crucial role in replicating natural physiological environments and facilitating the delivery of nutrients and removal of metabolic byproducts. Although present techniques provide diverse strategies to create vascular channels, the flexible and scalable construction of these channels within hydrogels remains a challenge. Here, inspired by Lego assembly, an innovative modular construction strategy is introduced for developing perfusable vascular channels within hydrogels. This approach involves the customized design and fabrication of individual modules featuring diverse vascular channel architectures, which can be flexibly assembled into large-scale hydrogel constructs with hierarchical vascular channels through

Abstract: Background: Stroke presents a substantial health burden, emphasizing the crucial necessity for robust screening tools to gauge its severity and assess associated biomarkers. The identification of retinal biomarkers for stroke is a pivotal pursuit, enabling both early-stage risk and subsequent prognosis prediction for personalized intervention strategies. This study aims to analyze retinal blood vessel oxygen saturation (SO2) and structure across ischemic and hemorrhagic stroke subtypes compared to healthy controls. Additionally, it seeks to examine adjusted odds ratios between retinal vascular features and two stroke subtypes, employing these metrics for the classification of stroke.Methods: This study assessed retinal images from 29 ischemic stroke patients, 23 hemorrhagic strok

Abstract: The incidence and burden of skin wounds, especially chronic and complex wounds, have a profound impact on healthcare. Effective wound healing strategies require a multidisciplinary approach, and advances in materials science and bioengineering have paved the way for the development of novel wound healing dressing. In this context, electrospun nanofibers can mimic the architecture of the natural extracellular matrix and provide new opportunities for wound healing. Inspired by the bioelectric phenomena in the human body, electrospun nanofibrous scaffolds with electroactive characteristics are gaining widespread attention and gradually emerging. To this end, this review first summarizes the basic process of wound healing, the causes of chronic wounds, and the current status of clini

Abstract: Vascularization is a critical component of tissue engineering research and is essential for enhancing the success rate of tissue construction and function. Over the past decade, researchers have explored various methods to construct in vitro vascular networks, including 3D printing, cell sphere technology, and microfluidics. Microfluidic technology has garnered significant attention due to its notable advantages in precision, controllability, flexibility, and applicability. It can be primarily classified into two modes: (i) the pre-designed mode, which involves creating vascular networks by pre-designing vascular channels and seeding endothelial cells, encompassing microfluidic chips and microfluidic spinning technologies; and (ii) the self-assembly mode, where cell spheres are f

Abstract: Effective vascularization is crucial for the success of tissue engineering and is influenced by numerous factors. The present work focuses on investigating the effect of a substance, cyanobacteria-loaded oxygen-releasing hydrogel, on vascularization and verifying the effect of photosynthetic-oxygen-releasing biomaterials containing a cyanobacteria hydrogel on angiogenesis, using the chick chorioallantoic membrane (CAM) as a model system. On the eighth day of embryonic development, cyanobacterial microspheres were placed on the CAM and maintained in a light incubator under appropriate growth and photosynthesis conditions. The effect of cyanobacterial microspheres on vascularization was evaluated from the eighth day of embryonic development. The carrier material used to prepare the

Abstract: Unsupervised Domain Adaptation aims to leverage a source domain with ample labeled data to tackle tasks on an unlabeled target domain. However, this poses a significant challenge, particularly in scenarios exhibiting significant disparities between the two domains. Prior methods often fall short in challenging domains due to the impact of incorrect pseudo-labeling noise and the limits of handcrafted domain alignment rules. In this paper, we propose a novel method called DCST (Dual Cross-Supervision Transformer), which improves upon existing methods in two key aspects. Firstly, vision transformer is combined with dual cross-supervision learning strategy to enforce consistency learning from different domains. The network accomplishes domain-specific self-training and cross-domain f

Abstract: The UNet architecture, based on convolutional neural networks (CNN), has demonstrated its remarkable performance in medical image analysis. However, it faces challenges in capturing long-range dependencies due to the limited receptive fields and inherent bias of convolutional operations. Recently, numerous transformer-based techniques have been incorporated into the UNet architecture to overcome this limitation by effectively capturing global feature correlations. However, the integration of the Transformer modules may result in the loss of local contextual information during the global feature fusion process. In this work, we propose a 2D medical image segmentation model called multi-scale cross perceptron attention network (MCPA). The MCPA consists of three main components: an