Objective: Recognizing retinal vessel abnormity is vital to early diagnosis of ophthalmological diseases and cardiovascular events. However, segmentation results are highly influenced by elusive vessels, especially in low-contrast background and lesion region. In this work, we present an end-to-end synthetic neural network, containing a symmetric equilibrium generative adversarial network (SEGAN), multi-scale features refine blocks (MSFRB), and attention mechanism (AM) to enhance the performance on vessel segmentation. Method: The proposed network is granted powerful multi-scale representation capability to extract detail information. First, SEGAN constructs a symmetric adversarial architecture, which forces generator to produce more realistic images with local details. Second, MSFRB are devised to prevent high-resolution features from being obscured, thereby merging multi-scale features better. Finally, the AM is employed to encourage the network to concentrate on discriminative features. Results: On public dataset DRIVE, STARE, CHASEDB1, and HRF, we evaluate our network quantitatively and compare it with state-of-the-art works. The ablation experiment shows that SEGAN, MSFRB, and AM both contribute to the desirable performance. Conclusion: The proposed network outperforms the mature methods and effectively functions in elusive vessels segmentation, achieving highest scores in Sensitivity, G-Mean, Precision, and F1-Score while maintaining the top level in other metrics. Significance: The appreciable performance and computational efficiency offer great potential in clinical retinal vessel segmentation application. Meanwhile, the network could be utilized to extract detail information in other biomedical issues
Utilizing computed tomography (CT) images to quickly estimate the severity of cases with COVID-19 is one of the most straightforward and efficacious methods. Two tasks were studied in this present paper. One was to segment the mask of intact lung in case of pneumonia. Another was to generate the masks of regions infected by COVID-19. The masks of these two parts of images then were converted to corresponding volumes to calculate the physical proportion of infected region of lung. A total of 129 CT image set were herein collected and studied. The intrinsic Hounsfiled value of CT images was firstly utilized to generate the initial dirty version of labeled masks both for intact lung and infected regions. Then, the samples were carefully adjusted and improved by two professional radiologists to generate the final training set and test benchmark. Two deep learning models were evaluated: UNet and 2.5D UNet. For the segment of infected regions, a deep learning based classifier was followed to remove unrelated blur-edged regions that were wrongly segmented out such as air tube and blood vessel tissue etc. For the segmented masks of intact lung and infected regions, the best method could achieve 0.972 and 0.757 measure in mean Dice similarity coefficient on our test benchmark. As the overall proportion of infected region of lung, the final result showed 0.961 (Pearson's correlation coefficient) and 11.7% (mean absolute percent error). The instant proportion of infected regions of lung could be used as a visual evidence to assist clinical physician to determine the severity of the case. Furthermore, a quantified report of infected regions can help predict the prognosis for COVID-19 cases which were scanned periodically within the treatment cycle.
Epithelium, a highly dynamic system, plays a key role in the homeostasis of the intestine. However, thus far a human intestinal epithelial cell line has not been established in many countries. Fetal tissue was selected to generate viable cell cultures for its sterile condition, effective generation, and differentiated character. The purpose of the present study was to culture human intestinal epithelial cells by a relatively simple method. Thermolysin was added to improve the yield of epithelial cells, while endothelin-3 was added to stimulate their growth. By adding endothelin-3, the achievement ratio (viable cell cultures/total cultures) was enhanced to 60% of a total of 10 cultures (initiated from 8 distinct fetal small intestines), allowing the generation of viable epithelial cell cultures. Western blot, real-time PCR and immunofluorescent staining showed that cytokeratins 8, 18 and mouse intestinal mucosa-1/39 had high expression levels in human intestinal epithelial cells. Differentiated markers such as sucrase-isomaltase, aminopeptidase N and dipeptidylpeptidase IV also showed high expression levels in human intestinal epithelial cells. Differentiated human intestinal epithelial cells, with the expression of surface markers (cytokeratins 8, 18 and mouse intestinal mucosa-1/39) and secretion of cytokines (sucrase-isomaltase, aminopeptidase N and dipeptidylpeptidase IV), may be cultured by the thermolysin and endothelin-3 method and maintained for at least 20 passages. This is relatively simple, requiring no sophisticated techniques or instruments, and may have a number of varied applications.
Exosomes are nanosized extracellular vesicles which are emerging as novel therapeutic nanoparticles. This paper reports a novel concept of engineering exosomes using nanomaterial inside the vascular endothelial cells (ECs). Gold nanorods (GNRs) could inhibit EC division and internalized GNRs located in endosomes of binucleated ECs. The GNRs could alter the composition of bioactive molecules loaded in exosomes. The engineered EC‐derived exosomes could inhibit tumor cell proliferation, migration, and invasion in vitro and suppress tumor growth in vivo. miRNA sequencing showed that the engineered exosomes contained various miRNAs that could disrupt the TGF β pathway. Further data suggested that the engineered exosomes could suppress the expression of TGF β 1 and TGF β 2, thus inhibiting the activation of SMAD2 and SMAD3. These data highlighted the therapeutic potential of engineering exosomes using nanomaterials.
Objective To investigate the effects and mechanism of the surface adhesive protein of Lactobacillus plantarum CGMCC NO.1258 on adhering to the gut epithelial cell.Method On the basis of the preparation and identification of the polyclonal antibody of IMP2,the role of IMP2 in the adhesion of Lactobacillus plantarum CGMCC NO.1258 was tested by blocking the protein with the antibody in the competitive adhesion to the gut epithelial cell with the EPEC.Result The adhering role of the Lactobacillus plantarum CGMCC NO.1258 was inhibited by the polyclonal antibody,which resulted in the increase of the adhesion of the EPEC to the epithelial cell.Conclusion IMP2 played important roles in the adhesion of Lactobacillus plantarum CGMCC NO.1258 to the gut epithelial cell.
Foundation models represent a paradigm shift in artificial intelligence (AI), evolving from narrow models designed for specific tasks to versatile, generalisable models adaptable to a myriad of diverse applications. Ophthalmology as a specialty has the potential to act as an exemplar for other medical specialties, offering a blueprint for integrating foundation models broadly into clinical practice. This review hopes to serve as a roadmap for eyecare professionals seeking to better understand foundation models, while equipping readers with the tools to explore the use of foundation models in their own research and practice. We begin by outlining the key concepts and technological advances which have enabled the development of these models, providing an overview of novel training approaches and modern AI architectures. Next, we summarise existing literature on the topic of foundation models in ophthalmology, encompassing progress in vision foundation models, large language models and large multimodal models. Finally, we outline major challenges relating to privacy, bias and clinical validation, and propose key steps forward to maximise the benefit of this powerful technology.
'%3e%3cpath fill='%23012169' d='M0 0v30h60V0z'/%3e%3cpath stroke='%23fff' stroke-width='6' d='m0 0 60 30m0-30L0 30'/%3e%3cpath stroke='%23C8102E' stroke-width='4' d='m0 0 60 30m0-30L0 30' clip-path='url(%23b)'/%3e%3cpath stroke='%23fff' stroke-width='10' d='M30 0v30M0 15h60'/%3e%3cpath stroke='%23C8102E' stroke-width='6' d='M30 0v30M0 15h60'/%3e%3c/g%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)