Background Pulmonary arterial hypertension (PAH) is a progressive condition with a poorprognosis in children. Lung transplantation (Ltx) remains the ultimate option when patients are refractory toPAH-speciffc therapy....Background Pulmonary arterial hypertension (PAH) is a progressive condition with a poorprognosis in children. Lung transplantation (Ltx) remains the ultimate option when patients are refractory toPAH-speciffc therapy. Reverse Potts shunt (RPS) has been introduced to treat suprasystemic PAH. This studyaims to investigate the clinical outcomes of suprasystemic PAH in children. Methods Embase, Pubmed,and the Cochrane Library databases were searched for related studies that reported the clinical outcomes ofsuprasystemic PAH following RPS in children. To investigate the clinical outcomes of RPS, meta-analyses ofthe early and overall mortalities were performed. Results Nine studies were included in this study. Theestimated early mortality was 14.4% (95% CI, 7.1% to 23.1%), and the overall mortality/Ltx was 23.2% (95%CI, 14.4% to 32.9%). The estimated 1-year survival was 86.3% (95% CI, 75.9% to 88.7%). A qualitative reviewshowed that the median value of 5-year survival free from Ltx of patients undergoing RPS was 68.6% (range:65% to 92.3%). Compared to Ltx, RPS did not signiffcantly increase the early mortality (OR, 2.48, 95% CI0.75 to 8.24, p = 0.14). RPS also signiffcantly improved the New York Heart Association/World HealthOrganization functional class, reduced the BNP/NT-pro BNP levels, decreased the PAH-speciffc therapy,and increased the six-minute-walking distance. Conclusions RPS may serve as an alternative treatmentfor suprasystemic drug-refractory PAH. Further large-scale and prospective cohort studies are needed tovalidate these ffndings.展开更多
深度学习驱动的图像分割在医学影像和自动驾驶等领域成效显著,但其黑箱决策机制导致模型选择与超参数调整缺乏理论指导,依赖大数据和高算力支撑。相较之下,基于变分模型的方法虽多受限于局部特征提取,易忽略全局上下文关联,但其通过融...深度学习驱动的图像分割在医学影像和自动驾驶等领域成效显著,但其黑箱决策机制导致模型选择与超参数调整缺乏理论指导,依赖大数据和高算力支撑。相较之下,基于变分模型的方法虽多受限于局部特征提取,易忽略全局上下文关联,但其通过融合全局统计规律与局部平滑约束的特性,在数学可解释性和抗噪声伪影方面展现优势。因此,本文提出了一种基于Potts模型展开的与U-Net相似的架构,旨在提升图像分割的准确性和鲁棒性。与传统U-Net不同,本文在下采样和上采样过程中引入了基于Potts模型的正则化块,以增强分割过程中的区域一致性和边缘保留能力。通过HQS (半二次分裂)方法求解Potts模型,并结合FoE正则化项,使用可训练的离散余弦变换(DCT)-高斯卷积实现了梯度算子的学习,激活函数采用软阈值公式(STF)。此外,为了捕获全局上下文信息并处理远距离依赖,在网络的最底层加入了Transformer结构,进一步改善分割效果。实验结果表明,本文提出的模型在少量参数和数据集上能够有效学习特征,提高分割精度。本研究为图像分割任务提供了新的视角,展示了结合深度神经网络与传统变分模型架构的广阔潜力。Deep learning-driven image segmentation has demonstrated significant efficacy in fields such as medical imaging and autonomous driving. However, its black-box decision-making mechanisms lead to a lack of theoretical guidance for model selection and hyperparameter tuning, with heavy reliance on large datasets and high computational resources. In contrast, variational model-based methods, though often limited by local feature extraction and neglect of global contextual relationships, exhibit advantages in mathematical interpretability and noise/artifact resistance through their integration of global statistical patterns and local smoothness constraints. This paper proposes a U-Net-inspired architecture based on the Potts model unfolding framework to enhance segmentation accuracy and robustness. Unlike traditional U-Net, our method introduces Potts model-derived regularization blocks during downsampling and upsampling to strengthen region consistency and edge preservation capabilities. The Potts model is solved via the Half-Quadratic Splitting (HQS) method, combined with a Fields of Experts (FoE) regularization term. Trainable Discrete Cosine Transform (DCT)-Gaussian convolutions are employed to learn gradient operators, with activation functions adopting the Soft Thresholding Formula (STF). Additionally, a Transformer structure is integrated at the network’s deepest layer to capture global contextual information and address long-range dependencies, further refining segmentation performance. Experimental results demonstrate that our model effectively learns features with limited parameters and datasets while improving segmentation precision. This study offers a novel perspective for image segmentation tasks, highlighting the vast potential of hybrid architectures that combine deep neural networks with classical variational models.展开更多
为改善三维晶粒组织可视化模型的统计性,采用Monte Carlo Potts方法建立了材料多晶体组织的一种大尺度三维数字化模型,并实现了其定量表征和三维可视化.逾万晶粒的统计结果表明,该模型的平均晶粒面数为13.8±0.1,晶粒尺寸分布和晶...为改善三维晶粒组织可视化模型的统计性,采用Monte Carlo Potts方法建立了材料多晶体组织的一种大尺度三维数字化模型,并实现了其定量表征和三维可视化.逾万晶粒的统计结果表明,该模型的平均晶粒面数为13.8±0.1,晶粒尺寸分布和晶粒面数分布均可用Log-normal函数近似拟合,与实际材料晶粒组织情况相近.展开更多
基金Chongqing Medical University Program for Youth Innovation in Future Medicine(W0204)Natural Science Foundation Project of Chongqing,Chongqing Science and Technology Commission(CSTB2023NSCQ-BHX0010)+1 种基金Chongqing Postdoctoral Research Project Special Support(2023CQBSHTB3074)Science and Technology Research Program of Chongqing Municipal Education Commission(KJQN202400421).
文摘Background Pulmonary arterial hypertension (PAH) is a progressive condition with a poorprognosis in children. Lung transplantation (Ltx) remains the ultimate option when patients are refractory toPAH-speciffc therapy. Reverse Potts shunt (RPS) has been introduced to treat suprasystemic PAH. This studyaims to investigate the clinical outcomes of suprasystemic PAH in children. Methods Embase, Pubmed,and the Cochrane Library databases were searched for related studies that reported the clinical outcomes ofsuprasystemic PAH following RPS in children. To investigate the clinical outcomes of RPS, meta-analyses ofthe early and overall mortalities were performed. Results Nine studies were included in this study. Theestimated early mortality was 14.4% (95% CI, 7.1% to 23.1%), and the overall mortality/Ltx was 23.2% (95%CI, 14.4% to 32.9%). The estimated 1-year survival was 86.3% (95% CI, 75.9% to 88.7%). A qualitative reviewshowed that the median value of 5-year survival free from Ltx of patients undergoing RPS was 68.6% (range:65% to 92.3%). Compared to Ltx, RPS did not signiffcantly increase the early mortality (OR, 2.48, 95% CI0.75 to 8.24, p = 0.14). RPS also signiffcantly improved the New York Heart Association/World HealthOrganization functional class, reduced the BNP/NT-pro BNP levels, decreased the PAH-speciffc therapy,and increased the six-minute-walking distance. Conclusions RPS may serve as an alternative treatmentfor suprasystemic drug-refractory PAH. Further large-scale and prospective cohort studies are needed tovalidate these ffndings.
文摘深度学习驱动的图像分割在医学影像和自动驾驶等领域成效显著,但其黑箱决策机制导致模型选择与超参数调整缺乏理论指导,依赖大数据和高算力支撑。相较之下,基于变分模型的方法虽多受限于局部特征提取,易忽略全局上下文关联,但其通过融合全局统计规律与局部平滑约束的特性,在数学可解释性和抗噪声伪影方面展现优势。因此,本文提出了一种基于Potts模型展开的与U-Net相似的架构,旨在提升图像分割的准确性和鲁棒性。与传统U-Net不同,本文在下采样和上采样过程中引入了基于Potts模型的正则化块,以增强分割过程中的区域一致性和边缘保留能力。通过HQS (半二次分裂)方法求解Potts模型,并结合FoE正则化项,使用可训练的离散余弦变换(DCT)-高斯卷积实现了梯度算子的学习,激活函数采用软阈值公式(STF)。此外,为了捕获全局上下文信息并处理远距离依赖,在网络的最底层加入了Transformer结构,进一步改善分割效果。实验结果表明,本文提出的模型在少量参数和数据集上能够有效学习特征,提高分割精度。本研究为图像分割任务提供了新的视角,展示了结合深度神经网络与传统变分模型架构的广阔潜力。Deep learning-driven image segmentation has demonstrated significant efficacy in fields such as medical imaging and autonomous driving. However, its black-box decision-making mechanisms lead to a lack of theoretical guidance for model selection and hyperparameter tuning, with heavy reliance on large datasets and high computational resources. In contrast, variational model-based methods, though often limited by local feature extraction and neglect of global contextual relationships, exhibit advantages in mathematical interpretability and noise/artifact resistance through their integration of global statistical patterns and local smoothness constraints. This paper proposes a U-Net-inspired architecture based on the Potts model unfolding framework to enhance segmentation accuracy and robustness. Unlike traditional U-Net, our method introduces Potts model-derived regularization blocks during downsampling and upsampling to strengthen region consistency and edge preservation capabilities. The Potts model is solved via the Half-Quadratic Splitting (HQS) method, combined with a Fields of Experts (FoE) regularization term. Trainable Discrete Cosine Transform (DCT)-Gaussian convolutions are employed to learn gradient operators, with activation functions adopting the Soft Thresholding Formula (STF). Additionally, a Transformer structure is integrated at the network’s deepest layer to capture global contextual information and address long-range dependencies, further refining segmentation performance. Experimental results demonstrate that our model effectively learns features with limited parameters and datasets while improving segmentation precision. This study offers a novel perspective for image segmentation tasks, highlighting the vast potential of hybrid architectures that combine deep neural networks with classical variational models.
文摘为改善三维晶粒组织可视化模型的统计性,采用Monte Carlo Potts方法建立了材料多晶体组织的一种大尺度三维数字化模型,并实现了其定量表征和三维可视化.逾万晶粒的统计结果表明,该模型的平均晶粒面数为13.8±0.1,晶粒尺寸分布和晶粒面数分布均可用Log-normal函数近似拟合,与实际材料晶粒组织情况相近.
