Heading date in rice is a typical quantitative trait controlled by multiple quantitative trait loci （QTLs）. It is mainly regulated by environmental factors such as photoperiod and temperature （Izawa, 2007）. Many Q...Heading date in rice is a typical quantitative trait controlled by multiple quantitative trait loci （QTLs）. It is mainly regulated by environmental factors such as photoperiod and temperature （Izawa, 2007）. Many QTLs for heading date have been identified using different mapping populations and methods （http：// www.gramene.org/qtl）. Up to date, several major heading date QTLs have been cloned by map-based cloning strategy （Yano et al., 2000; Takahashi et al., 2001; Kojima et al., 2002; Doi et al., 2004; Xue et al., 2008; Wei et al., 2010; Yan et al.,展开更多
Objective:To comprehensively evaluate popular medical segmentation networks on the CSTRO dataset for head and neck organs at risk(H&N OARs)segmentation,identify top performers,and integrate them into a robust hybr...Objective:To comprehensively evaluate popular medical segmentation networks on the CSTRO dataset for head and neck organs at risk(H&N OARs)segmentation,identify top performers,and integrate them into a robust hybrid network(Attention W-Net)for superior performance.Methods:U-Net,Attention U-Net,R2U-Net,UNet-plusplus,and CE-Net were selected and two novel architectures W-Net and SE-U-Net were developed.Using U-Net as the baseline,a first-stage experiment was conducted to evaluate the segmentation performance of these networks.Following initial evaluations,Attention U-Net,SE-UNet,and W-Net achieved notably strong performance.Representative blocks were identified and extracted from these three networks to construct three hybrid architectures:Attention W-Net,SEW-Net,and Attention SEU-Net.Subsequently,a second-stage experiment was conducted to determine the optimal hybrid architecture.Results:In the first stage,U-Net,Attention U-Net,R2U-Net,UNet-plusplus,CE-Net,W-Net and SEU-Net were tested and achieved 0.712,0.755,0.706,0.710,0.702,0.708,0.767,0.749 of average dice similarity coefficient(DSC),respectively.Then the best three networks Attention U-Net,SEU-Net,W-Net were selected out.The hybrid networks Attention W-Net,Attention SEU-Net,SEW-Net were tested,and achieved 0.776,0.768,0.743 of average(DSC),respectively.In terms of the metric,Attention W-Net is the most effective networks for H&N OAR segmentation.Conclusion:The Attention W-Net and SEW-Net are the better networks which achieve better results than the popular state-of-the-arts networks for head and neck OARs segmentation.展开更多
基金supported by grants from the Ministry of Science and Technology of China(No. 2010CB125901)the National Natural Science Foundation of China(No.31271315)the Bill & Melinda Gates Foundation
文摘Heading date in rice is a typical quantitative trait controlled by multiple quantitative trait loci （QTLs）. It is mainly regulated by environmental factors such as photoperiod and temperature （Izawa, 2007）. Many QTLs for heading date have been identified using different mapping populations and methods （http：// www.gramene.org/qtl）. Up to date, several major heading date QTLs have been cloned by map-based cloning strategy （Yano et al., 2000; Takahashi et al., 2001; Kojima et al., 2002; Doi et al., 2004; Xue et al., 2008; Wei et al., 2010; Yan et al.,
基金supported by Beijing Xisike Clinical Oncology Research Foundation(Y-Young2024-0538,Y-Young2023-0156)United Laboratory of Frontier Radiotherapy Technology Fund(HT-99982024-0350)+1 种基金Scientific Research Cooperation Projects of UIH&SYSUCC(ZDZL-UIH-2022006)Guangdong Province College Student Innovation and Entrepreneurship Training Program(No.s202513902038),China.
文摘Objective:To comprehensively evaluate popular medical segmentation networks on the CSTRO dataset for head and neck organs at risk(H&N OARs)segmentation,identify top performers,and integrate them into a robust hybrid network(Attention W-Net)for superior performance.Methods:U-Net,Attention U-Net,R2U-Net,UNet-plusplus,and CE-Net were selected and two novel architectures W-Net and SE-U-Net were developed.Using U-Net as the baseline,a first-stage experiment was conducted to evaluate the segmentation performance of these networks.Following initial evaluations,Attention U-Net,SE-UNet,and W-Net achieved notably strong performance.Representative blocks were identified and extracted from these three networks to construct three hybrid architectures:Attention W-Net,SEW-Net,and Attention SEU-Net.Subsequently,a second-stage experiment was conducted to determine the optimal hybrid architecture.Results:In the first stage,U-Net,Attention U-Net,R2U-Net,UNet-plusplus,CE-Net,W-Net and SEU-Net were tested and achieved 0.712,0.755,0.706,0.710,0.702,0.708,0.767,0.749 of average dice similarity coefficient(DSC),respectively.Then the best three networks Attention U-Net,SEU-Net,W-Net were selected out.The hybrid networks Attention W-Net,Attention SEU-Net,SEW-Net were tested,and achieved 0.776,0.768,0.743 of average(DSC),respectively.In terms of the metric,Attention W-Net is the most effective networks for H&N OAR segmentation.Conclusion:The Attention W-Net and SEW-Net are the better networks which achieve better results than the popular state-of-the-arts networks for head and neck OARs segmentation.
