Objective To predict the potential targets of Qingfu Juanbi Decoction(青附蠲痹汤,QFJBD)in treating rheumatoid arthritis(RA)using an improved Transformer model and investigate the network pharmacological mechanisms und...Objective To predict the potential targets of Qingfu Juanbi Decoction(青附蠲痹汤,QFJBD)in treating rheumatoid arthritis(RA)using an improved Transformer model and investigate the network pharmacological mechanisms underlying QFJBD’s therapeutic effects on RA.Methods First,a traditional Chinese medicine herb-target interaction(TCMHTI)model was constructed to predict herb-target interactions based on Transformer improvement.The per-formance of the TCMHTI model was evaluated against baseline models using three metrics:area under the receiver operating characteristic curve(AUC),precision-recall curve(PRC),and accuracy.Subsequently,a protein-protein interaction(PPI)network was built based on the predicted targets,with core targets identified as the top nine nodes ranked by degree val-ues.Gene Ontology(GO)functional and Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway enrichment analyses were performed using the targets predicted by TCMHTI and the targets identified through network pharmacology method for comparison.Then,the re-sults were compared.Finally,the core targets predicted by TCMHTI were validated through molecular docking and literature review.Results The TCMHTI model achieved an AUC of 0.883,PRC of 0.849,and accuracy of 0.818,predicting 49 potential targets for QFJBD in RA treatment.Nine core targets were identified:tumor necrosis factor(TNF)-α,interleukin(IL)-1β,IL-6,IL-10,IL-17A,cluster of differentia-tion 40(CD40),cytotoxic T-lymphocyte-associated protein 4(CTLA4),IL-4,and signal trans-ducer and activator of transcription 3(STAT3).The enrichment analysis demonstrated that the TCMHTI model predicted 49 targets and enriched more pathways directly associated with RA,whereas classical network pharmacology identified 64 targets but enriched pathways showing weaker relevance to RA.Molecular docking demonstrated that the active molecules in QFJBD exhibit favorable binding energy with RA targets,while literature research further revealed that QFJBD can treat RA through 9 core targets.Conclusion The TCMHTI model demonstrated greater accuracy than traditional network pharmacology methods,suggesting QFJBD exerts therapeutic effects on RA by regulating tar-gets like TNF-α,IL-1β,and IL-6,as well as multiple signaling pathways.This study provides a novel framework for bridging traditional herbal knowledge with precision medicine,offering actionable insights for developing targeted TCM therapies against diseases.展开更多
Automatic pancreas segmentation plays a pivotal role in assisting physicians with diagnosing pancreatic diseases,facilitating treatment evaluations,and designing surgical plans.Due to the pancreas’s tiny size,signifi...Automatic pancreas segmentation plays a pivotal role in assisting physicians with diagnosing pancreatic diseases,facilitating treatment evaluations,and designing surgical plans.Due to the pancreas’s tiny size,significant variability in shape and location,and low contrast with surrounding tissues,achieving high segmentation accuracy remains challenging.To improve segmentation precision,we propose a novel network utilizing EfficientNetV2 and multi-branch structures for automatically segmenting the pancreas fromCT images.Firstly,an EfficientNetV2 encoder is employed to extract complex and multi-level features,enhancing the model’s ability to capture the pancreas’s intricate morphology.Then,a residual multi-branch dilated attention(RMDA)module is designed to suppress irrelevant background noise and highlight useful pancreatic features.And re-parameterization Visual Geometry Group(RepVGG)blocks with amulti-branch structure are introduced in the decoder to effectively integrate deep features and low-level details,improving segmentation accuracy.Furthermore,we apply re-parameterization to the model,reducing computations and parameters while accelerating inference and reducing memory usage.Our approach achieves average dice similarity coefficient(DSC)of 85.59%,intersection over union(IoU)of 75.03%,precision of 85.09%,and recall of 86.57%on the NIH pancreas dataset.Compared with other methods,our model has fewer parameters and faster inference speed,demonstrating its enormous potential in practical applications of pancreatic segmentation.展开更多
The collection and extraction of tongue images has always been an important part of intelligent tongue diagnosis.At present,the collection of tongue images generally needs to be completed in a sealed,stable light envi...The collection and extraction of tongue images has always been an important part of intelligent tongue diagnosis.At present,the collection of tongue images generally needs to be completed in a sealed,stable light environment,which is not conducive to the promotion of extensive tongue image and intelligent tongue diagnosis.In response to the problem,a newalgorithm named GCYTD(GELU-CA-YOLO Tongue Detection)is proposed to quickly detect and locate the tongue in a natural environment,which can greatly reduce the restriction of the tongue image collection environment.The algorithm is based on the YOLO(You Only Look Once)V4-tiny network model to detect the tongue.Firstly,the GELU(Gaussian Error Liner Units)activation function is integrated into the model to improve the training speed and reduce the number of model parameters;then,the CA(Coordinate Attention)mechanism is integrated into the model to enhance the detection precision and improve the failure tolerance of the model.Compared with the other classical algorithms,Experimental results show thatGCYTD algorithm has a better performance on the tongue images of all types in terms of training speed,tongue detection speed and detection precision,etc.The lighter model can contribute on deploying the tongue detection model on small mobile terminals.展开更多
Chinese Medicine(CM)has been widely used as an important avenue for disease prevention and treatment in China especially in the form of CM prescriptions combining sets of herbs to address patients’symptoms and syndro...Chinese Medicine(CM)has been widely used as an important avenue for disease prevention and treatment in China especially in the form of CM prescriptions combining sets of herbs to address patients’symptoms and syndromes.However,the selection and compatibility of herbs are complex and abstract due to intrinsic relationships between herbal properties and their overall functions.Network analysis is applied to demonstrate the complex relationships between individual herbal efficacy and the overall function of CM prescriptions.To illustrate their connections and correlations,prescription function(PF),prescription herb(PH),and herbal efficacy(HE)intranetworks are proposed based on CM theory to identify relationships between herbs and prescriptions.These three networks are then connected by PF-PH and PH-HE interlayer networks adopting herb dosage to form a multidimensional heterogeneous network,a Prescription-Herb-Function Network(PHFN).The network is applied to 112 classic prescriptions from Treatise on Exogenous Febrile and Miscellaneous Diseases to illustrate the application of PHFN.The PHFN is constructed including 146 functions in PF intra network,89 herbs in the PH intra network,and 163 herbal efficacies in the HE intra network.The results show that herb pairs with synergistic actions have stronger relevance,such as licorice-cassia twig,licorice-Chinese date,fresh ginger-Chinese date,etc.The integration of dosage to the network helps to indicate the main herbs for cluster analysis and automatic formulation.PHFN also reveals the internal relationships between the functions of prescriptions and composed herbal efficacies.展开更多
基金General Program of the National Natural Science Foundation of China (82474352)Natural Science Foundation of Hunan Province (2023JJ60124)。
文摘Objective To predict the potential targets of Qingfu Juanbi Decoction(青附蠲痹汤,QFJBD)in treating rheumatoid arthritis(RA)using an improved Transformer model and investigate the network pharmacological mechanisms underlying QFJBD’s therapeutic effects on RA.Methods First,a traditional Chinese medicine herb-target interaction(TCMHTI)model was constructed to predict herb-target interactions based on Transformer improvement.The per-formance of the TCMHTI model was evaluated against baseline models using three metrics:area under the receiver operating characteristic curve(AUC),precision-recall curve(PRC),and accuracy.Subsequently,a protein-protein interaction(PPI)network was built based on the predicted targets,with core targets identified as the top nine nodes ranked by degree val-ues.Gene Ontology(GO)functional and Kyoto Encyclopedia of Genes and Genomes(KEGG)pathway enrichment analyses were performed using the targets predicted by TCMHTI and the targets identified through network pharmacology method for comparison.Then,the re-sults were compared.Finally,the core targets predicted by TCMHTI were validated through molecular docking and literature review.Results The TCMHTI model achieved an AUC of 0.883,PRC of 0.849,and accuracy of 0.818,predicting 49 potential targets for QFJBD in RA treatment.Nine core targets were identified:tumor necrosis factor(TNF)-α,interleukin(IL)-1β,IL-6,IL-10,IL-17A,cluster of differentia-tion 40(CD40),cytotoxic T-lymphocyte-associated protein 4(CTLA4),IL-4,and signal trans-ducer and activator of transcription 3(STAT3).The enrichment analysis demonstrated that the TCMHTI model predicted 49 targets and enriched more pathways directly associated with RA,whereas classical network pharmacology identified 64 targets but enriched pathways showing weaker relevance to RA.Molecular docking demonstrated that the active molecules in QFJBD exhibit favorable binding energy with RA targets,while literature research further revealed that QFJBD can treat RA through 9 core targets.Conclusion The TCMHTI model demonstrated greater accuracy than traditional network pharmacology methods,suggesting QFJBD exerts therapeutic effects on RA by regulating tar-gets like TNF-α,IL-1β,and IL-6,as well as multiple signaling pathways.This study provides a novel framework for bridging traditional herbal knowledge with precision medicine,offering actionable insights for developing targeted TCM therapies against diseases.
基金supported by the Science and Technology Innovation Programof Hunan Province(Grant No.2022RC1021)the Hunan Provincial Natural Science Foundation Project(Grant No.2023JJ60124)+1 种基金the Changsha Natural Science Foundation Project(Grant No.kq2202265)the key project of the Hunan Provincial of Education(Grant No.22A0255).
文摘Automatic pancreas segmentation plays a pivotal role in assisting physicians with diagnosing pancreatic diseases,facilitating treatment evaluations,and designing surgical plans.Due to the pancreas’s tiny size,significant variability in shape and location,and low contrast with surrounding tissues,achieving high segmentation accuracy remains challenging.To improve segmentation precision,we propose a novel network utilizing EfficientNetV2 and multi-branch structures for automatically segmenting the pancreas fromCT images.Firstly,an EfficientNetV2 encoder is employed to extract complex and multi-level features,enhancing the model’s ability to capture the pancreas’s intricate morphology.Then,a residual multi-branch dilated attention(RMDA)module is designed to suppress irrelevant background noise and highlight useful pancreatic features.And re-parameterization Visual Geometry Group(RepVGG)blocks with amulti-branch structure are introduced in the decoder to effectively integrate deep features and low-level details,improving segmentation accuracy.Furthermore,we apply re-parameterization to the model,reducing computations and parameters while accelerating inference and reducing memory usage.Our approach achieves average dice similarity coefficient(DSC)of 85.59%,intersection over union(IoU)of 75.03%,precision of 85.09%,and recall of 86.57%on the NIH pancreas dataset.Compared with other methods,our model has fewer parameters and faster inference speed,demonstrating its enormous potential in practical applications of pancreatic segmentation.
基金This work was supported by the Key Research and Development Plan of China(No.2017YFC1703306)Key Project of Education Department in Hunan Province(No.18A227)Key Project of Traditional Chinese Medicine Scientific Research Plan in Hunan Province(2020002).
文摘The collection and extraction of tongue images has always been an important part of intelligent tongue diagnosis.At present,the collection of tongue images generally needs to be completed in a sealed,stable light environment,which is not conducive to the promotion of extensive tongue image and intelligent tongue diagnosis.In response to the problem,a newalgorithm named GCYTD(GELU-CA-YOLO Tongue Detection)is proposed to quickly detect and locate the tongue in a natural environment,which can greatly reduce the restriction of the tongue image collection environment.The algorithm is based on the YOLO(You Only Look Once)V4-tiny network model to detect the tongue.Firstly,the GELU(Gaussian Error Liner Units)activation function is integrated into the model to improve the training speed and reduce the number of model parameters;then,the CA(Coordinate Attention)mechanism is integrated into the model to enhance the detection precision and improve the failure tolerance of the model.Compared with the other classical algorithms,Experimental results show thatGCYTD algorithm has a better performance on the tongue images of all types in terms of training speed,tongue detection speed and detection precision,etc.The lighter model can contribute on deploying the tongue detection model on small mobile terminals.
文摘Chinese Medicine(CM)has been widely used as an important avenue for disease prevention and treatment in China especially in the form of CM prescriptions combining sets of herbs to address patients’symptoms and syndromes.However,the selection and compatibility of herbs are complex and abstract due to intrinsic relationships between herbal properties and their overall functions.Network analysis is applied to demonstrate the complex relationships between individual herbal efficacy and the overall function of CM prescriptions.To illustrate their connections and correlations,prescription function(PF),prescription herb(PH),and herbal efficacy(HE)intranetworks are proposed based on CM theory to identify relationships between herbs and prescriptions.These three networks are then connected by PF-PH and PH-HE interlayer networks adopting herb dosage to form a multidimensional heterogeneous network,a Prescription-Herb-Function Network(PHFN).The network is applied to 112 classic prescriptions from Treatise on Exogenous Febrile and Miscellaneous Diseases to illustrate the application of PHFN.The PHFN is constructed including 146 functions in PF intra network,89 herbs in the PH intra network,and 163 herbal efficacies in the HE intra network.The results show that herb pairs with synergistic actions have stronger relevance,such as licorice-cassia twig,licorice-Chinese date,fresh ginger-Chinese date,etc.The integration of dosage to the network helps to indicate the main herbs for cluster analysis and automatic formulation.PHFN also reveals the internal relationships between the functions of prescriptions and composed herbal efficacies.
