典型文献
Improved Medical Image Segmentation Model Based on 3D U-Net
文献摘要：
With the widespread application of deep learning in the field of computer vision, gradually allowing medical image technology to assist doctors in making diagnoses has great practical and research significance. Aiming at the shortcomings of the traditional U-Net model in 3D spatial information extraction, model over-fitting, and low degree of semantic information fusion, an improved medical image segmentation model has been used to achieve more accurate segmentation of medical images. In this model, we make full use of the residual network (ResNet) to solve the over-fitting problem. In order to process and aggregate data at different scales, the inception network is used instead of the traditional convolutional layer, and the dilated convolution is used to increase the receptive field. The conditional random field(CRF) can complete the contour refinement work. Compared with the traditional 3D U-Net network, the segmentation accuracy of the improved liver and tumor images increases by 2.89％ and 7.66％, respectively. As a part of the image processing process, the method in this paper not only can be used for medical image segmentation, but also can lay the foundation for subsequent image 3D reconstruction work.
文献关键词：
中图分类号：
作者姓名：
LIN Wei;FAN Hong;HU Chenxi;YANG Yi;YU Suping;NI Lin
作者机构：
College of Information Science and Technology,Donghua University,Shanghai 201620,China
文献出处：
引用格式：
[1]LIN Wei;FAN Hong;HU Chenxi;YANG Yi;YU Suping;NI Lin-.Improved Medical Image Segmentation Model Based on 3D U-Net)[J].东华大学学报（英文版）,2022(04):311-316
A类：
B类：
Improved,Medical,Image,Segmentation,Model,Based,With,widespread,application,deep,learning,field,computer,vision,gradually,allowing,medical,technology,assist,doctors,making,diagnoses,has,great,practical,research,significance,Aiming,shortcomings,traditional,model,spatial,information,extraction,over,fitting,degree,semantic,fusion,improved,segmentation,been,used,achieve,more,accurate,images,In,this,we,make,full,residual,network,ResNet,solve,problem,order,aggregate,data,different,scales,inception,instead,convolutional,layer,dilated,receptive,conditional,random,CRF,complete,contour,refinement,Compared,accuracy,liver,tumor,increases,by,respectively,part,processing,method,paper,not,only,but,also,foundation,subsequent,reconstruction
AB值：
0.56873
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
