针对DeepLabv3+在高分辨率遥感图像语义分割中存在的分割目标边界残缺和细节模糊问题,提出了一种图像边界修复语义分割方法。引入多深度卷积头转置注意力(multi-Dconv head transposed attention,MDTA)边界修复模块,将通道注意力机制应...针对DeepLabv3+在高分辨率遥感图像语义分割中存在的分割目标边界残缺和细节模糊问题,提出了一种图像边界修复语义分割方法。引入多深度卷积头转置注意力(multi-Dconv head transposed attention,MDTA)边界修复模块,将通道注意力机制应用于多级低阶特征,获取不同抽象层次的边缘纹理结构;将经过通道权值分配的密集采样空洞空间金字塔池化(atrous spatial pyramid pooling,ASPP)级联模块的输出作为编码器的输出,解码器融合了低阶特征与编码器输出的增强特征,提高了目标边界的清晰度;利用空间上下文信息挖掘模块——上下文转换器(contextual transformer,CoT),增强对图像不同区域之间依赖关系的感知能力。实验证明,该方法在多个公开数据集上的性能取得了显著提升,在VOC2012的验证集上平均交并比(mean intersection over union,mIoU)达到了90.42%。展开更多
In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial netw...In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial network(GAN)was proposed.First,a noise model based on style GAN2 was constructed to estimate the real noise distribution,and the noise information similar to the real noise distribution was generated as the experimental noise data set.Then,a network model with encoder-decoder architecture as the core based on GAN idea was constructed,and the network model was trained with the generated noise data set until it reached the optimal value.Finally,the noise and artifacts in low-dose CT images could be removed by inputting low-dose CT images into the denoising network.The experimental results showed that the constructed network model based on GAN architecture improved the utilization rate of noise feature information and the stability of network training,removed image noise and artifacts,and reconstructed image with rich texture and realistic visual effect.展开更多
为了更加精确地分割出甲状腺结节,本文提出了一种改进的全卷积神经网络(Fully convolutional network,FCN)分割模型。相较于FCN,本文方法加入了空洞空间卷积池化金字塔(Atrousspatialpyramidpooling,ASPP)模块与多层特征传递模块(Featur...为了更加精确地分割出甲状腺结节,本文提出了一种改进的全卷积神经网络(Fully convolutional network,FCN)分割模型。相较于FCN,本文方法加入了空洞空间卷积池化金字塔(Atrousspatialpyramidpooling,ASPP)模块与多层特征传递模块(Featuretransfer,FT),并采用LinkNet模型中Decoder模块进行上采样,VGG16主干网络实现特征提取下采样。实验采用来自斯坦福AIMI(Artificial intelligence in medicine and imaging)共享数据集的17413张超声甲状腺结节图像分别用于训练、验证和测试。实验结果表明,相比于其他多种分割模型,本文模型在平均交并比(mean Intersection over union,mIoU),Dice相似系数,F1分数3个分割指标上分别达到了79.7%,87.6%和98.42%,实现了更好的分割效果,有效地提升了甲状腺结节的分割精确度。展开更多
基金supported by National Natural Science Foundation of China(No.11802272)China Postdoctoral Science Foundation(No.2019M651085)。
文摘In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial network(GAN)was proposed.First,a noise model based on style GAN2 was constructed to estimate the real noise distribution,and the noise information similar to the real noise distribution was generated as the experimental noise data set.Then,a network model with encoder-decoder architecture as the core based on GAN idea was constructed,and the network model was trained with the generated noise data set until it reached the optimal value.Finally,the noise and artifacts in low-dose CT images could be removed by inputting low-dose CT images into the denoising network.The experimental results showed that the constructed network model based on GAN architecture improved the utilization rate of noise feature information and the stability of network training,removed image noise and artifacts,and reconstructed image with rich texture and realistic visual effect.
文摘为了更加精确地分割出甲状腺结节,本文提出了一种改进的全卷积神经网络(Fully convolutional network,FCN)分割模型。相较于FCN,本文方法加入了空洞空间卷积池化金字塔(Atrousspatialpyramidpooling,ASPP)模块与多层特征传递模块(Featuretransfer,FT),并采用LinkNet模型中Decoder模块进行上采样,VGG16主干网络实现特征提取下采样。实验采用来自斯坦福AIMI(Artificial intelligence in medicine and imaging)共享数据集的17413张超声甲状腺结节图像分别用于训练、验证和测试。实验结果表明,相比于其他多种分割模型,本文模型在平均交并比(mean Intersection over union,mIoU),Dice相似系数,F1分数3个分割指标上分别达到了79.7%,87.6%和98.42%,实现了更好的分割效果,有效地提升了甲状腺结节的分割精确度。
