当前位置>主页 > 期刊在线 > 计算机技术 >

计算机技术22年19期

基于 V-Net 模型的肺结节分割研究
梁富娥,张伟,吕珊珊,顾旋,刘东华
(甘肃中医药大学 信息工程学院,甘肃 兰州 730000)

摘  要:由于肺部结节的形状多样,特征复杂,在人工进行处理的过程中会存在诸多问题,例如提取肺结节的过程困难和结节分割的精确度不高以及消耗大量人力财力等。文章采用了一种深度学习的模型——V-Net 模型,对肺结节进行分割,接着使用大型公开肺结节数据集 LUNA16 进行了实验,通过分割结果可以直观看到,该文所用深度学习方法在对辅助医师进行肺结节诊断治疗有一定的参考价值。


关键词:深度学习;肺结节分割;V-Net 模型;辅助诊断



DOI:10.19850/j.cnki.2096-4706.2022.19.018


基金项目:甘肃中医药大学科学创新基金资助项(KCYB2018-6)


中图分类号:TP391.4                                        文献标识码:A                                文章编号:2096-4706(2022)19-0071-04


Research on Lung Nodule Segmentation Based on V-Net Model

LIANG Fu’e, ZHANG Wei, LYU Shanshan, GU Xuan , LIU Donghua

(School of Information Engineering, Gansu University of Chinese Medicine, Lanzhou 730000, China)

Abstract: Due to the diverse shapes and complex characteristics of pulmonary nodules, there are many problems in the process of manual processing, such as the difficult process of extracting pulmonary nodules, the low accuracy of nodule segmentation, the consumption of a lot of human and financial resources and so on. In this paper, a deep learning model, the V-Net model, is used to segment lung nodules, and then the large-scale public lung nodule data set LUNA16 is used for experiments. The segmentation results can be intuitively seen. The deep learning method used in this paper has a certain reference value in assisting physicians in the diagnosis and treatment of pulmonary nodules.

Keywords: deep learning; lung nodule segmentation; V-Net model; auxiliary diagnosis


参考文献:

[1] DHARA A K,MUKHOPADHYAY S,KHANDELWAL N. Computer-aided detection and analysis of pulmonary nodule from CT images:a survey [J].IETE Technical Review,2012,29(4):265-275.

[2] 徐峰,郑斌,郭进祥,等 . 基于 U-Net 的结节分割方法 [J].软件导刊,2018,17(8):161-164.

[3] RONNEBERGER O,FISCHER P,BROX T. U-net: Convolutional networks for biomedical image segmentation [C]// International Conference on Medical image computing and computerassisted intervention. Springer,Cham,2015:234-241.

[4] 张佳 . 肺结节分割的 V-Net 模型改进研究 [D]. 上海:东华大学,2021.

[5] 苗语,丰振航,杨华民,等 . 基于改进的 U-Net 肺结节分割方法研究 [J]. 计算机应用与软件,2021,38(12):213-219.

[6] 钟思华,王梦璐,郭兴明,等 . 基于改进 VNet 的肺结节分割方法研究 [J]. 仪器仪表学报,2020,41(9):206-215.

[7] ARMATO S G,MCLENNAN G,BIDAUT L,et al. The lung image database consortium (lidc) and image database resource initiative (idri):a completed reference database of lung nodules on ct scans [J].Med Phys,2011,38(2):915-31.

[8] 王磐,强彦,杨晓棠,等 . 基于双注意力 3D-UNet 的肺结节分割网络模型 [J]. 计算机工程,2021,47(2):307-313.

[9] MILLETARI F,NAVAB N,AHMADI S A. V-net:Fully convolutional neural networks for volumetric medical image segmentation [C]//2016 fourth international conference on 3D vision (3DV). Stanford:IEEE,2016:565-571.

[10] ZHANG H,QIU D W,FU Y B,et al. Improved U-Net Models and Its Applications in Medical Image Segmentation: A Review [J/OL].Laser & Optoelectronics Progress,2022,59(2):0200005[2022-04-02].https: //www.opticsjournal.net/Articles/ OJ9b27bbb26bf64f83/Abstract.

[11] 吴菲 . 基于改进的 V-Net 模型的肝肿瘤分割算法 [J]. 现代计算机,2021,27(27):64-70.


作者简介:梁富娥(1997—),女,汉族,甘肃会宁人,硕士在读,研究方向:深度学习、医学图像处理;张伟(1981—),男,汉族,甘肃庆阳人,副教授,硕士生导师,主要研究方向:虚拟仿真教学、医院信息化建设和中药方剂的数据挖掘。