Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the ima...Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.展开更多
Background and Aims:Hepatic sinusoidal obstruction syndrome(HSOS)is caused by toxic injury to sinusoidal endothelial cells in the liver.The intake of pyrrolizidine alkaloids(PAs)in some Chinese herbal remedies/plants ...Background and Aims:Hepatic sinusoidal obstruction syndrome(HSOS)is caused by toxic injury to sinusoidal endothelial cells in the liver.The intake of pyrrolizidine alkaloids(PAs)in some Chinese herbal remedies/plants remains the major etiology for HSOS in China.Recently,new diagnostic criteria for PA-induced HSOS(i.e.PA-HSOS)have been developed;however,the efficacy has not been clinically validated.This study aimed to assess the performance of the Nanjing criteria for PA-HSOS.Methods:Data obtained from consecutive patients in multiple hospitals,which included 86 PA-HSOS patients and 327 patients with other liver diseases,were retrospectively analyzed.Then,the diagnostic performance of the Nanjing criteria and simplified Nanjing criteria were evaluated and validated.The study is registered in www.chictr.org.cn(ID:ChiCTR1900020784).Results:The Nanjing criteria have a sensitivity and specificity of 95.35%and 100%,respectively,while the simplified Nanjing criteria have a sensitivity and specificity of 96.51%and 96.33%,respectively,for the diagnosis of PA-HSOS.Notably,a proportion of patients with Budd-Chiari syndrome(11/49)was misdiagnosed as PA-HSOS on the basis of the simplified Nanjing criteria,and this was mainly due to the overlapping features in the enhanced computed tomography/magnetic resonance imaging examinations.Furthermore,most of these patients(10/11)had occlusion or thrombosis of the hepatic vein,and communicating vessels in the liver were found in 8/11 patients,which were absent in PA-HSOS patients.Conclusions:The Nanjing criteria and simplified Nanjing criteria exhibit excellent performance in diagnosing PA-HSOS.Thus,both could be valuable diagnostic tools in clinical practice.展开更多
基金This work was jointly supported by the Special Fund for Transformation and Upgrade of Jiangsu Industry and Information Industry-Key Core Technologies(Equipment)Key Industrialization Projects in 2022(No.CMHI-2022-RDG-004):“Key Technology Research for Development of Intelligent Wind Power Operation and Maintenance Mothership in Deep Sea”.
文摘Under the influence of air humidity,dust,aerosols,etc.,in real scenes,haze presents an uneven state.In this way,the image quality and contrast will decrease.In this case,It is difficult to detect the target in the image by the universal detection network.Thus,a dual subnet based on multi-task collaborative training(DSMCT)is proposed in this paper.Firstly,in the training phase,the Gated Context Aggregation Network(GCANet)is used as the supervisory network of YOLOX to promote the extraction of clean information in foggy scenes.In the test phase,only the YOLOX branch needs to be activated to ensure the detection speed of the model.Secondly,the deformable convolution module is used to improve GCANet to enhance the model’s ability to capture details of non-homogeneous fog.Finally,the Coordinate Attention mechanism is introduced into the Vision Transformer and the backbone network of YOLOX is redesigned.In this way,the feature extraction ability of the network for deep-level information can be enhanced.The experimental results on artificial fog data set FOG_VOC and real fog data set RTTS show that the map value of DSMCT reached 86.56%and 62.39%,respectively,which was 2.27%and 4.41%higher than the current most advanced detection model.The DSMCT network has high practicality and effectiveness for target detection in real foggy scenes.
基金This study was funded in full by the National Natural Science Foundation of China,with grant numbers 8157040652 and 81900552the Key Project of Nanjing Health and Technology Development,with grant number ZKX19015。
文摘Background and Aims:Hepatic sinusoidal obstruction syndrome(HSOS)is caused by toxic injury to sinusoidal endothelial cells in the liver.The intake of pyrrolizidine alkaloids(PAs)in some Chinese herbal remedies/plants remains the major etiology for HSOS in China.Recently,new diagnostic criteria for PA-induced HSOS(i.e.PA-HSOS)have been developed;however,the efficacy has not been clinically validated.This study aimed to assess the performance of the Nanjing criteria for PA-HSOS.Methods:Data obtained from consecutive patients in multiple hospitals,which included 86 PA-HSOS patients and 327 patients with other liver diseases,were retrospectively analyzed.Then,the diagnostic performance of the Nanjing criteria and simplified Nanjing criteria were evaluated and validated.The study is registered in www.chictr.org.cn(ID:ChiCTR1900020784).Results:The Nanjing criteria have a sensitivity and specificity of 95.35%and 100%,respectively,while the simplified Nanjing criteria have a sensitivity and specificity of 96.51%and 96.33%,respectively,for the diagnosis of PA-HSOS.Notably,a proportion of patients with Budd-Chiari syndrome(11/49)was misdiagnosed as PA-HSOS on the basis of the simplified Nanjing criteria,and this was mainly due to the overlapping features in the enhanced computed tomography/magnetic resonance imaging examinations.Furthermore,most of these patients(10/11)had occlusion or thrombosis of the hepatic vein,and communicating vessels in the liver were found in 8/11 patients,which were absent in PA-HSOS patients.Conclusions:The Nanjing criteria and simplified Nanjing criteria exhibit excellent performance in diagnosing PA-HSOS.Thus,both could be valuable diagnostic tools in clinical practice.