Background Primary open-angle glaucoma (POAG) is characterized by optic nerve damage and consists of a group of genetically heterogeneous disorders. This study was to investigate the associations of genetic and envir...Background Primary open-angle glaucoma (POAG) is characterized by optic nerve damage and consists of a group of genetically heterogeneous disorders. This study was to investigate the associations of genetic and environmental factors with POAG in a hospital-based Chinese population Methods Thirty-two adult onset POAG patients and 96 age-sex matched control subjects were studied by multivariable logistic regression analysis for the relationships between POAG and its risk factors including family history, diabetes, hypertension, cardiovascular diseases, cigarette smoking, alcohol consumption and polymorphisms of the myocilin and the optineurin genes Results Univariate analysis showed that POAG was related to family history, cardiovascular disease, alcohol consumption and a myocilin sequence alteration (T353I) ( P <0 04) Multivariable logistic regression analysis confirmed that POAG was significantly associated with family history ( OR =20 2), hypertension ( OR =3 58), cigarette smoking ( OR =10 8), alcohol consumption ( OR =0 028) and T353I ( OR =6 03, all P <0 05) Conclusions Family history, hypertension, cigarette smoking and T353I in the myocilin gene are risk factors for POAG Alcohol consumption, however, has a protective effect展开更多
针对SAR图像检测船舶任务中的目标小、近岸样本目标检测困难等问题,文章提出一种名为长短路特征融合网络(Long and Short path Feature Fusion Network,LSFF-Net)的船舶检测网络。该网络通过长短路特征融合模块有效协调了大目标与小目...针对SAR图像检测船舶任务中的目标小、近岸样本目标检测困难等问题,文章提出一种名为长短路特征融合网络(Long and Short path Feature Fusion Network,LSFF-Net)的船舶检测网络。该网络通过长短路特征融合模块有效协调了大目标与小目标检测,避免小目标特征信息的丢失。网络中应用结构重参数化结构提高了模块学习能力。为了满足多尺度目标检测,加入特征金字塔网络,融合多尺度特征。为了应对近岸样本目标检测,设计数据重分配算法,提高了对近岸样本目标的检测精度。实验结果表明:在公开数据集检测时,算法的平均精度(Average Precision,AP)达到97.50%,优于主流目标检测算法。该方法为提高SAR图像中小目标和近岸样本目标检测精度提供了新的实现方案。展开更多
基金ThisstudywassupportedbyagrantfromMedicinePanel,ChineseUniversityofHongKong (No 2 0 40 82 0 )
文摘Background Primary open-angle glaucoma (POAG) is characterized by optic nerve damage and consists of a group of genetically heterogeneous disorders. This study was to investigate the associations of genetic and environmental factors with POAG in a hospital-based Chinese population Methods Thirty-two adult onset POAG patients and 96 age-sex matched control subjects were studied by multivariable logistic regression analysis for the relationships between POAG and its risk factors including family history, diabetes, hypertension, cardiovascular diseases, cigarette smoking, alcohol consumption and polymorphisms of the myocilin and the optineurin genes Results Univariate analysis showed that POAG was related to family history, cardiovascular disease, alcohol consumption and a myocilin sequence alteration (T353I) ( P <0 04) Multivariable logistic regression analysis confirmed that POAG was significantly associated with family history ( OR =20 2), hypertension ( OR =3 58), cigarette smoking ( OR =10 8), alcohol consumption ( OR =0 028) and T353I ( OR =6 03, all P <0 05) Conclusions Family history, hypertension, cigarette smoking and T353I in the myocilin gene are risk factors for POAG Alcohol consumption, however, has a protective effect
文摘针对SAR图像检测船舶任务中的目标小、近岸样本目标检测困难等问题,文章提出一种名为长短路特征融合网络(Long and Short path Feature Fusion Network,LSFF-Net)的船舶检测网络。该网络通过长短路特征融合模块有效协调了大目标与小目标检测,避免小目标特征信息的丢失。网络中应用结构重参数化结构提高了模块学习能力。为了满足多尺度目标检测,加入特征金字塔网络,融合多尺度特征。为了应对近岸样本目标检测,设计数据重分配算法,提高了对近岸样本目标的检测精度。实验结果表明:在公开数据集检测时,算法的平均精度(Average Precision,AP)达到97.50%,优于主流目标检测算法。该方法为提高SAR图像中小目标和近岸样本目标检测精度提供了新的实现方案。
