Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of...Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.展开更多
Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we ...Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.展开更多
目的 随着人工智能的发展,深度学习技术在医学图像分割中得到广泛应用。但现有方法往往采用自上而下或自下而上的方式进行特征融合,易忽略或丢失中间层特征信息。此外,现有方法对病灶区域分割边界不够精细。针对上述问题,本文提出一种...目的 随着人工智能的发展,深度学习技术在医学图像分割中得到广泛应用。但现有方法往往采用自上而下或自下而上的方式进行特征融合,易忽略或丢失中间层特征信息。此外,现有方法对病灶区域分割边界不够精细。针对上述问题,本文提出一种聚焦全局与中间层特征的细节增强医学图像分割网络(detail-enhanced medical image segmentation network focusing on global and intermediate features,DEMS-GIF)。方法 首先通过进一步关注中间层信息,并利用Transformer提取不同区域之间的长距离依赖关系的能力,设计了一种基于Transformer的桥接特征融合模块(Transformer-based bridge feature fusion module,TBBFF),以提升模型的特征提取能力。其次,通过引入反向注意力机制,并结合腐蚀和膨胀操作,提出一种反向注意下的扩缩区域增强上采样策略(expanded and scaled region enhanced upsampling strategy under reverse attention,ESRU),使得模型能够更好地捕捉边界和细节信息。DEMS-GIF模型通过结合TBBFF模块和ESRU策略,进一步提高了分割的准确性。结果 在CVC-ClinicDB、DDTI(digital database thyroid image)和Kvasir-SEG 3个数据集上进行对比实验和模块消融实验,评估提出的DEMS-GIF模型,并在CVC-ClinicDB数据集上进行参数消融实验,以了解DEMS-GIF中每个模块和结构内部的有效性。实验结果表明,DEMS-GIF模型的mIoU值分别达到94.74%、84.56%和88.46%,Dice值分别达到94.82%、82.95%和87.44%。与原UNet型通道变换网络相比,mIoU值分别提升3.73%、3.4%和5.24%,Dice值分别提升4.84%、5.45%和6.82%。结论 本文提出的DEMS-GIF网络模型较其他先进的分割方法的分割效果更优,表明了其在医学图像分割中的优越性。展开更多
基金The authors received Sichuan Science and Technology Program(No.18YYJC1917)funding for this study.
文摘Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.
基金Supported by the National Natural Science Foundation of China (61901308)。
文摘Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.
文摘目的 随着人工智能的发展,深度学习技术在医学图像分割中得到广泛应用。但现有方法往往采用自上而下或自下而上的方式进行特征融合,易忽略或丢失中间层特征信息。此外,现有方法对病灶区域分割边界不够精细。针对上述问题,本文提出一种聚焦全局与中间层特征的细节增强医学图像分割网络(detail-enhanced medical image segmentation network focusing on global and intermediate features,DEMS-GIF)。方法 首先通过进一步关注中间层信息,并利用Transformer提取不同区域之间的长距离依赖关系的能力,设计了一种基于Transformer的桥接特征融合模块(Transformer-based bridge feature fusion module,TBBFF),以提升模型的特征提取能力。其次,通过引入反向注意力机制,并结合腐蚀和膨胀操作,提出一种反向注意下的扩缩区域增强上采样策略(expanded and scaled region enhanced upsampling strategy under reverse attention,ESRU),使得模型能够更好地捕捉边界和细节信息。DEMS-GIF模型通过结合TBBFF模块和ESRU策略,进一步提高了分割的准确性。结果 在CVC-ClinicDB、DDTI(digital database thyroid image)和Kvasir-SEG 3个数据集上进行对比实验和模块消融实验,评估提出的DEMS-GIF模型,并在CVC-ClinicDB数据集上进行参数消融实验,以了解DEMS-GIF中每个模块和结构内部的有效性。实验结果表明,DEMS-GIF模型的mIoU值分别达到94.74%、84.56%和88.46%,Dice值分别达到94.82%、82.95%和87.44%。与原UNet型通道变换网络相比,mIoU值分别提升3.73%、3.4%和5.24%,Dice值分别提升4.84%、5.45%和6.82%。结论 本文提出的DEMS-GIF网络模型较其他先进的分割方法的分割效果更优,表明了其在医学图像分割中的优越性。
