计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240500119-9.doi: 10.11896/jsjkx.240500119
石辛诚, 王宝会, 于利韬, 杜辉
SHI Xincheng, WANG Baohui, YU Litao, DU Hui
摘要： 在医学图像分割领域,下肢骨CT影像的噪声、伪影、对比度低等问题对图像分割的性能和效果提出了更高的要求。针对这一需求场景,提出了基于U-Net卷积神经网络模型,结合三维CT影像输入数据的特点,对分割算法进行针对性改进的图像分割模型,提高了分割的准确度。文中生成的模型基于U-Net卷积神经网络,通过多层卷积池化聚合,结合注意力机制和连续切片间的特征融合,充分挖掘影像中的特征和结构信息,实现了端到端的影像分割方法。基于积水潭医院下肢骨CT影像数据集进行验证,实验结果表明,该模型的平均交并比达到了84.959%,而其他模型的对应数值分别为78.604%(U-Net),80.481%(Nested U-Net),79.877%(Attention U-net),相比其他模型有显著的提高。
中图分类号:
| [1]OLIVEIRA D A,FEITOSA R Q,CORREIA M M.Segmentation of liver,its vessels and lesions from CT images for surgical planning [J].Biomedical Engineering Online,2011,10:30. [2]SEO K S,KIM H B,PARK T,et al.Automatic liver segmentation of contrast enhanced CT images based on histogram processing [C]//WANG L,CHEN K,ONG Y S.Advances in Natural Computation.Berlin:Springer,2005:1027-1030. [3]KENJI S,RYAN K,MARK L,et al.Computer-Aided Measurement of Liver Volumesin CT by Means of Geodesic Active Contour Segmentation Coupled with Level-Set Algorithms [J].Medical Physics,2010,37:2159-2166. [4]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation [C]//Springer International Publishing,2015:234-241. [5]MILLETARI F,NAVAB N,AHMADI S A.V-Net:Fully convolutional neural networks for volumetric medical image segmentation [C]//2016 4th International Conference on 3D Vision(3DV).Stanford,25-28 October 2016:565-571. [6]ZHOU Z,RAHMAN SIDDIQUEE M M,TAJBAKHSH N,et al.UNet++:A nested U-Net architecture for medical image segmentation [C]//Stoyanov D,et al.Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Springer,2018:3-11. [7]OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention U-Net:Learning where to look for the pancreas [J].arXiv:1804.03999,2018. [8]ALOM M Z,YAKOPCIC C,TAHA T M,et al.Nuclei segmentation with recurrent residual convolutional neural networks based U-Net(R2U-Net) [C]//NAECON 2018－IEEE National Aerospace and Electronics Conference.Dayton.OH,2018:228-233. [9]CHEN H,DOU Q,YU L,et al.VoxResNet:Deep voxelwise residual networks for brain segmentation from 3D MR images [J].NeuroImage,2018,170:446-455. [10]SCHLEMPER J,OKTAY O,SCHAAP M,et al.Attention gated networks:Learning to leverage salient regions in medical images [J].Medical Image Analysis,2019,53:197-207. [11]HUANG G,LIU Z,VAN DER MAATEN L,et al.Densely connected convolutional networks [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2017:4700-4708. [12]LITJENS G,TOTH R,VAN DE VEN W,et al.Evaluation of prostate segmentation algorithms for MRI:The PROMISE12 challenge [J].Medical Image Analysis,2014,18(2):359-373. [13]WANG H,LI T,ZHUANG Z,et al.Early stopping for deep image prior [J].arXiv:1901.09335,2021. [14]WANG C,HE Y,LIU Y,et al.ScleraSegNet:An improved U-net model with attention for accurate sclera segmentation [C]//Proceedings of the International Conference on Biometrics,2019:1-8. [15]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-decoder with atrous separable convolution for semantic image segmentation [C]//Ferrari V,Hebert M,Sminchisescu C,Weiss Y.Computer Vision—ECCV 2018.Cham:Springer,2018:833-851. [16]JIN Q G,MENG Z P,PHAM T D,et al.DUNet:A Deformable Network for Retinal Vessel Segmentation [J].Knowledge-Based Systems,2019,178:149-162. [17]ZHANG Z Z,GAO J Y,ZHAO D.MIFNet:A Gastric Cancer Pathology Image Segmentation Method Based on Multi-Scale Input and Feature Fusion [J].Journal of Computer Applications,2019,39(z2):107-113. [18]JIN Q G,MENG Z P,PHAM T D,et al.DUNet:A Deformable Network for Retinal Vessel Segmentation [J].Knowledge-Based Systems,2019,178:149-162. [19]DAI J,QI H,XIONG Y,et al.Deformable ConvolutionalNetworks [C]//Proceedings of the International Conference on Computer Vision.2017:764-773. |
|
||
首页