Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detec...Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.展开更多
AIM: To determine the effect of metastatic hepatoma cells on lymphangioma-derived endothelium, and to establish in vitro model systems for assessing metastasis-related response of lymphatic endothelium.METHODS: Benign...AIM: To determine the effect of metastatic hepatoma cells on lymphangioma-derived endothelium, and to establish in vitro model systems for assessing metastasis-related response of lymphatic endothelium.METHODS: Benign lymphangioma, induced by intraperitoneal injection of the incomplete Freund's adjuvant in BALB/c mice, was embedded in fibrin gel or digested and then cultured in the conditioned medium derived from hepatoma H22. Ught and electron microscopy, and the b-answell migration assay were used to determine the effect of H22 on tissue or cell culture. Expressions of Fit-4, c-Fos, proliferating cell nuclear antigen (PCNA), and inducible nitric oxide synthase (iNOS) in cultured cells, and content of nitric oxide in culture medium were also examined.RESULTS: The embedded lymphangioma pieces gave rise to array of capillaries, while separated cells from lymphangioma grew to a cobblestone-like monolayer. H22 activated growth and migration of the capillaries and cells, induced expressions of Flt-4, c-Fos, PCNA and iNOS in cultured cells, and significantly increased the content of NO in the culture medium.CONCLUSION: Lymphangioma-derived cells keep the differentiated phenotypes of lymphatic endothelium, and the models established in this study are feasible for in vitro study of metastasis-related response of lymphatic endothelium.展开更多
AIM: To determine the pathological characteristics of gastric leiomyoblastoma.METHODS: All tissues were obtained during surgery or gastroscopy. Tissue specimens for examination by light microscope were 1 cmxl cmxl cm ...AIM: To determine the pathological characteristics of gastric leiomyoblastoma.METHODS: All tissues were obtained during surgery or gastroscopy. Tissue specimens for examination by light microscope were 1 cmxl cmxl cm in size, fixed in 40 g/L neutral buffered formaldehyde, embedded in paraffin, and stained with hematoxylin and eosin. The fresh tissues obtained for electron microscopy were 1 mmxl mmxl mm in size, and fixed in phosphate buffered 30 g/L glutaraldehyde, postfixed in 10 g/L osmium tetroxide and dehydrated in graded alcohol, embebbed in Epon 812. UItrathin sections of 50 nm were stained with uranyl acetate and lead citrate and examined under a JEM-2000 EX transmission electron microscope.RESULTS: The most important histopathological feature of leiomyoblastoma was the predominance of large, rounded or polygonal cells with characteristic perinuclear clear zone in cytoplasms. The tumor cells arranged in patch, cell junction or junctional complex could be found occasionally between cells under electron microscope. Most of the neoplastic cytoplasms were filled with myofilaments, dense bodies, and dense patches. Rough endoplasmic reticulum dilatated as lakes, and large quantities of protein secretions of intermediate electron density were found in the dilated cisternae. Intracisternal segregation could also be found. The nuclei were round or oval, and anomalous nuclei were found in part of cells.CONCLUSION: The diagnosis of gastric leiomyoblastoma can be confirmed by electron microscopy. The clear appearance of tumor cells is due to the dilation of rough endoplasmic reticulum, not fat droplets, glycogens or mucus in cytoplasm.展开更多
基金The work was supported by the National Natural Science Foundation of China(61972062,62306060)the Basic Research Project of Liaoning Province(2023JH2/101300191)+1 种基金the Liaoning Doctoral Research Start-Up Fund Project(2023-BS-078)the Dalian Academy of Social Sciences(2023dlsky028).
文摘Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.
文摘AIM: To determine the effect of metastatic hepatoma cells on lymphangioma-derived endothelium, and to establish in vitro model systems for assessing metastasis-related response of lymphatic endothelium.METHODS: Benign lymphangioma, induced by intraperitoneal injection of the incomplete Freund's adjuvant in BALB/c mice, was embedded in fibrin gel or digested and then cultured in the conditioned medium derived from hepatoma H22. Ught and electron microscopy, and the b-answell migration assay were used to determine the effect of H22 on tissue or cell culture. Expressions of Fit-4, c-Fos, proliferating cell nuclear antigen (PCNA), and inducible nitric oxide synthase (iNOS) in cultured cells, and content of nitric oxide in culture medium were also examined.RESULTS: The embedded lymphangioma pieces gave rise to array of capillaries, while separated cells from lymphangioma grew to a cobblestone-like monolayer. H22 activated growth and migration of the capillaries and cells, induced expressions of Flt-4, c-Fos, PCNA and iNOS in cultured cells, and significantly increased the content of NO in the culture medium.CONCLUSION: Lymphangioma-derived cells keep the differentiated phenotypes of lymphatic endothelium, and the models established in this study are feasible for in vitro study of metastasis-related response of lymphatic endothelium.
基金Supported by the Foundation of 117 Hospital,No.99008
文摘AIM: To determine the pathological characteristics of gastric leiomyoblastoma.METHODS: All tissues were obtained during surgery or gastroscopy. Tissue specimens for examination by light microscope were 1 cmxl cmxl cm in size, fixed in 40 g/L neutral buffered formaldehyde, embedded in paraffin, and stained with hematoxylin and eosin. The fresh tissues obtained for electron microscopy were 1 mmxl mmxl mm in size, and fixed in phosphate buffered 30 g/L glutaraldehyde, postfixed in 10 g/L osmium tetroxide and dehydrated in graded alcohol, embebbed in Epon 812. UItrathin sections of 50 nm were stained with uranyl acetate and lead citrate and examined under a JEM-2000 EX transmission electron microscope.RESULTS: The most important histopathological feature of leiomyoblastoma was the predominance of large, rounded or polygonal cells with characteristic perinuclear clear zone in cytoplasms. The tumor cells arranged in patch, cell junction or junctional complex could be found occasionally between cells under electron microscope. Most of the neoplastic cytoplasms were filled with myofilaments, dense bodies, and dense patches. Rough endoplasmic reticulum dilatated as lakes, and large quantities of protein secretions of intermediate electron density were found in the dilated cisternae. Intracisternal segregation could also be found. The nuclei were round or oval, and anomalous nuclei were found in part of cells.CONCLUSION: The diagnosis of gastric leiomyoblastoma can be confirmed by electron microscopy. The clear appearance of tumor cells is due to the dilation of rough endoplasmic reticulum, not fat droplets, glycogens or mucus in cytoplasm.
