In view of the complex structure of diabetic retinopathy and the large differences in the scales of different lesions,a novel network which integrates deformable convolution and attention mechanism is proposed for automatic diabetic retinopathy multi-lesion segmentation.Specifically,deformable convolution Haar wavelet transform encoder takes place of the original convolutional downsampling encoder to adapt to the irregular shape changes of lesions and extract effective feature information;a dense feature perception and aggregation module is introduced at the bottleneck layer to extract multi-scale features by aggregating multiple receptive fields,thus enhancing deep semantic information;and finally,in order to fully integrate the decoder output and improve the recognition accuracy of edge information,a multi scale adaptive fusion module is used to weight the decoder output of each layer for obtaining the most accurate segmentation feature map.The validation of hard percolation,bleeding point,and soft percolation segmentations on the DDR-RLS dataset reveals that the proposed network shows increases of 0.026 2,0.051 8 and 0.046 5 in IoU coefficient,0.027 1,0.058 1 and 0.050 4 in Dice coefficient,and 0.0423,0.0691 and 0.0734 in AUPR value,as compared with the original Unet.

In view of the complex structure of diabetic retinopathy and the large differences in the scales of different lesions,a novel network which integrates deformable convolution and attention mechanism is proposed for automatic diabetic retinopathy multi-lesion segmentation.Specifically,deformable convolution Haar wavelet transform encoder takes place of the original convolutional downsampling encoder to adapt to the irregular shape changes of lesions and extract effective feature information;a dense feature perception and aggregation module is introduced at the bottleneck layer to extract multi-scale features by aggregating multiple receptive fields,thus enhancing deep semantic information;and finally,in order to fully integrate the decoder output and improve the recognition accuracy of edge information,a multi scale adaptive fusion module is used to weight the decoder output of each layer for obtaining the most accurate segmentation feature map.The validation of hard percolation,bleeding point,and soft percolation segmentations on the DDR-RLS dataset reveals that the proposed network shows increases of 0.026 2,0.051 8 and 0.046 5 in IoU coefficient,0.027 1,0.058 1 and 0.050 4 in Dice coefficient,and 0.0423,0.0691 and 0.0734 in AUPR value,as compared with the original Unet.

To investigate the effect and mechanism of metformin on intestinal epithelial barrier injury in ulcerative colitis. A cell model of colitis was established by co-culture of human colon cancer cell line Caco-2 and human monocyte cell line THP-1. The colitis model cells were treated with metformin at concentration of for Flow cytometry was used to detect Caco-2 cell apoptosis, and Western blotting was used to detect the protein expression of tight junction proteins and endoplasmic reticulum stress-related proteins. After metformin treatment, the apoptosis rate of Caco-2 cells was decreased from (14.22±2.34)% to 0.61)% (=3.119, <0.05), and the expression levels of tight junction protein-1 and claudin-1 increased (=5.172 and 3.546, both <0.05). In addition, the expression levels of endoplasmic reticulum-related proteins glucose regulated protein (GRP) 78, C/EBP homologous protein (CHOP) and caspase-12, as well as the phosphorylation level of PRKR-like endoplasmic reticulum kinase (PERK) and eukaryotic translation initiation factor 2α (eIF2α) decreased (all <0.05). Metformin may alleviate the intestinal epithelial barrier damage in colitis by reducing intestinal epithelial cell apoptosis and increasing the expression of tight junction proteins, which may be associated with the inhibition of endoplasmic reticulum stress-induced apoptotic pathway.
Apoptosis ; Caco-2 Cells ; Colitis, Ulcerative ; Endoplasmic Reticulum Stress ; Humans ; Metformin/pharmacology*

In this paper, from the concept of acupoint compatibility, it is proposed that acupoint selection is a key factor to influence the compatibility of acupoint, and the nature of acupoint is closely related with the location and dominant meridian of acupoints. Acupoint selection according to the location and meridians is the basic method of acupoint compatibility, while acupoint selection based on the syndrome differentiation and the symptoms is the fundamental requirement of acupoint compatibility. Therefore, understanding the nature of acupoint, knowing the method of acupoint compatibility and selecting analogous acupoint that have identical or similar indications are the keys to improve the clinical efficacy.
Acupuncture Points ; Acupuncture Therapy ; psychology ; Humans ; Knowledge ; Meridians