计算机科学 ›› 2025, Vol. 52 ›› Issue (11A): 240900072-7.doi: 10.11896/jsjkx.240900072
宋磊1, 王宝会1, 杜辉2
SONG Lei1, WANG Baohui1, DU Hui2
摘要： 在机器人辅助下肢截骨术中,置针和截骨等操作的位置规划依赖于高精度的骨骼模型,而准确分离CT影像中的骨骼组织是实现建模的关键。对此,提出了一种改进的U-Net卷积神经网络模型,创新性地引入了动态滑动窗口机制,即在处理连续切片数据时,通过动态调整窗口大小,以增强对不同截面变化的适应性,从而提升分割的准确度。基于北京积水潭医院下肢骨CT影像数据集进行验证,得到改进后模型的Dice系数为84.948%,而U-Net为80.353%,Attention U-Net为83.580%,结果表明,改进后模型的分割效果有显著提升。
中图分类号:
| [1]LIU J H,TONG J,NI J J,et al.Improved U-Net-based segmentation of lower limb skeletal CT images [J].Computer Systems &Applications,2022,31(10):134-141. [2]ZHU H D,CHEN Y,ZHANG L.Research on Grayscale Normalization Methods for Medical Images [J].International Journal of Biomedical Engineering,2006(3):148-151. [3]OTSU N.A Threshold Selection Method from Gray-Level Histograms[J].IEEE Transactions on Systems,Man,and Cybernetics,1979,9(1):62-66. [4]ADAMS R,BISCHOF L.Seeded region growing[J].IEEETransactions on Pattern Analysis and Machine Intelligence,1994,16(6):641-647. [5]CANNY J.A Computational Approach to Edge Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(6):679-698. [6]MARR D,HILDRETH E.Theory of edge detection[C]//Proceedings of the Royal Society of London.1980:187-217. [7]WEN Y.Research on Semantic Segmentation Technology of Medical Images Based on Deep Learning [D].Chengdu:University of Electronic Science and Technology of China,2024. [8]RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Compu-ting and Computer-Assisted Intervention.Springer,2015. [9]MILLETARI F,NAVAB N,AHMADI S A.V-Net:Fully Con-volutional Neural Networks for Volumetric Medical Image Segmentation[J].arXiv:1606.04797,2016. [10]NIYAS S,PAWAN S J,ANAND KUMAR M,et al.Medicalimage segmentation with 3D convolutional neural networks:A survey[J].Neurocomputing,2022,493:397-413. [11]CHEN L C,ZHU Y,PAPANDREOU G,et al.Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation[C]//Proceedings of the European Conference on Computer Vision(ECCV).Springer,2018:833-851. [12]WANG H.Research on Medical Image Segmentation MethodsBased on Deep Learning [D].Guilin:Guilin University of Electronic Technology,2022. [13]ZHOU Z,SIDDIQUEE M M R,TAJBAKHSH N,et al.UNet++:Redesigning Skip Connections to Exploit Multiscale Fea-tures in Image Segmentation[C]//Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention(MICCAI).Springer,2018:3-11. [14]OKTAY O,SCHLEMPER J,FOLGOC L L,et al.Attention U-Net:Learning Where to Look for the Pancreas[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention(MICCAI).2018:605-613. [15]ALOM Z,TAHA T M,ASARI V K.Recurrent Residual Con-volutional Neural Network based on U-Net(R2U-Net) for Me-dical Image Segmentation[J].Neurocomputing,2018,275:406-417. [16]HE C E,XU H J,WANG Z,et al.Research on Automatic Seg-mentation Algorithm of Multimodal Magnetic Resonance Brain Tumor Images [J].Acta Optica Sinica,2020,40(6):66-75. |
|
||
首页