基于ResNeXt和改进nnU-Net的新冠感染早期诊断方法

doi:10.3969/j.issn.1006-2475.2023.06.004

计算机与现代化 ›› 2023, Vol. 0 ›› Issue (06): 21-26.doi: 10.3969/j.issn.1006-2475.2023.06.004

基于ResNeXt和改进nnU-Net的新冠感染早期诊断方法

徐皓¹, 田振宇¹, 李超凡², 崔欣欣¹, 杨建兰³

1.甘肃中医药大学信息工程学院,甘肃兰州 730000;
2.盐城市第三人民医院数据管理办公室,江苏盐城 224008;
3.福建省泉州市正骨医院,福建泉州 362019

收稿日期:2022-07-19 修回日期:2022-08-18 出版日期:2023-06-28 发布日期:2023-06-28
通讯作者: 杨建兰（1974—）,男,福建宁德人,副教授,硕士,研究方向：医学影像识别与应用,E-mail： FJYJL@gszy.edu.cn。
作者简介:徐皓（1999—）,男,江苏泰州人,硕士研究生,研究方向：医学图像处理,E-mail： 1597562722@qq.com; 田振宇（1997—）,女,河北张家口人,硕士研究生,研究方向：医院信息化系统,E-mail： tin17472316@163.com; 李超凡（1995—）,男,江苏徐州人,硕士,研究方向：医学信息处理,E-mail： lichaofanautism@163.com; 崔欣欣（2000—）,女,甘肃天水人,硕士研究生,研究方向：医学影像学,E-mail： taracx0907@163.com。
基金资助:
国家重点研发计划项目（2020YFC200660）; 江苏省高校自然科学面上项目（20KJB510025）

An Early Diagnosis Method of COVID-19 Infection Based on ResNeXt and Improved nnU-Net

XU Hao¹, TIAN Zhen-yu¹, LI Chao-fan², CUI Xin-xin¹, YANG Jian-lan³

1. School of Information Engineering, Gansu University of Chinese Medicine, Lanzhou 730000, China;
2. Data Management Office Yancheng Third People’s Hospial,Yancheng 224008, China;
3. Quanzhou Bonesetting Hospital of Fujian Province, Quanzhou 362019, China

Received:2022-07-19 Revised:2022-08-18 Online:2023-06-28 Published:2023-06-28

摘要/Abstract

摘要： 新型冠状病毒感染早期感染表现为肺浑浊程度和密度增加等特征,为了解决早期患者电子计算机断层扫描（Computed Tomogra, CT）诊断与肺部病灶定位困难这一问题,提出一种ResNeXt和改进型nnU-Net（no-new-Net）的COVID-19（Corona Virus Disease 2019）诊断与肺部病灶分割实验方案。ResNeXt模型分类平均准确率Accuracy为0.8554,AUC面积为0.8951,精确率Precision为0.8321,F1得分为0.8132,改进型nnU-Net模型病灶分割平均Dice系数达到0.7663,相较其他模型分割能力综合提高16.4%。实验结果表明该方案能够增强新冠早期肺部CT图像感染特征提取能力,高效实现疾病分型和精准分割病灶。

关键词: ResNeXt, 改进型nnU-Net, 新冠感染早期诊断, 肺部分割

Abstract: The early infection of novel coronavirus pneumonia is characterized by increased lung turbidity and density. In order to solve the problem of difficulty in diagnosing and locating lung lesions in early patients with computed tomography, an experimental protocol for the diagnosis of COVID-19 （Corona Virus Disease 2019） with lung lesion segmentation by ResNeXt and a modified nnU-Net （no-new-Net） is proposed. The mean accuracy of ResNeXt model classification is 0.8554, the AUC area is 0.8951, the Precision is 0.8321, the F1 score is 0.8132, and the mean Dice coefficient of improved nnU-Net model lesion segmentation reaches 0.7663, which is a combined improvement of 16.4% compared with other models segmentation ability. The experimental results show that this scheme can enhance the ability to extract infection features from the early lung CT images of new crowns, and achieve efficient disease typing and accurate lesion segmentation.

Key words: ResNeXt, improved nnU-Net, early diagnosis of neoconiosis, lung segmentation

中图分类号:

TP391.4

徐皓, 田振宇, 李超凡, 崔欣欣, 杨建兰. 基于ResNeXt和改进nnU-Net的新冠感染早期诊断方法[J]. 计算机与现代化, 2023, 0(06): 21-26.

XU Hao, TIAN Zhen-yu, LI Chao-fan, CUI Xin-xin, YANG Jian-lan. An Early Diagnosis Method of COVID-19 Infection Based on ResNeXt and Improved nnU-Net[J]. Computer and Modernization, 2023, 0(06): 21-26.

参考文献 28

[1]	FAN D, ZHOU T, JI G, et al.Inf-Net: Automatic COVID-19 lung infection segmentation from CT images[J]. IEEE Transactions on Medical Imaging, 2020,39(8):2626-2637.
[2]	MÜLLER D, SOTO-REY I, KRAMER F. Robust chest CT image segmentation of COVID-19 lung infection based on limited data[J]. Informatics in Medicine Unlocked, 2021,25. DOI: 10.1016/j.imu.2021.100681.
[3]	JIANG Y, CHEN H, LOEW M, et al.COVID-19 CT image synthesis with a conditional generative adversarial network[J]. IEEE Journal of Biomedical and Health Informatics, 2021,25(2):441-452.
[4]	RAJAMANI K, SIEBERT H, HEINRICH M P.Dynamic deformable attention (DDANet) for semantic segmentation[J]. IEEE Journal of Biomedical and Health Informatics,2021. DOI:10.1101/2020.08.25.20181834.
[5]	WANG B, JIN S, YAN Q, et al.AI-assisted CT imaging analysis for COVID-19 screening: Building and deploying a medical AI system[J]. Applied Soft Computing, 2020,98. DOI: 10.1016/j.asoc.2020.106897.
[6]	LV F, WANG J, YU X, et al.Chinese expert consensus on critical care ultrasound applications at COVID-19 pandemic[J]. Advanced Ultrasound in Diagnosis and Therapy, 2020,4(2):27-42.
[7]	GOZES O, FRID-ADAR M, GREENSPAN H, et al.Rapid AI development cycle for the coronavirus (COVID-19) pandemic: Initial results for automated detection & patient monitoring using deep learning CT image analysis[J]. arXiv preprint arXiv:2003.05037, 2020.
[8]	TIAN S, HU W, NIU L, et al.Pulmonary pathology of early-phase 2019 novel coronavirus (COVID-19) pneumonia in two patients with lung cancer[J]. Journal of Thoracic Oncology, 2020,15(5):700-704.
[9]	SHEN D G, WU G R, SUK H.Deep learning in medical image analysis[J]. Annual Review of Biomedical Engineering, 2017,19:221-248.
[10]	JIN C, CHEN W, CAO Y, et al.Development and evaluation of an artificial intelligence system for COVID-19 diagnosis[J]. Nature Communications, 2020,11(1):1-14.
[11]	RAHIMZADEH M, ATTAR A.A modified deep convolutional neural network for detecting COVID-19 and pneumonia from chest X-ray images based on the concatenation of Xception and ResNet50V2[J]. Informatics in Medicine Unlocked, 2020,19. DOI: 10.1016/j.imu.2020.100360.
[12]	PENG L, WANG C, TIAN G, et al.Analysis of CT scan images for COVID-19 pneumonia based on a deep ensemble framework with DenseNet, Swin transformer, and RegNet[J]. Frontiers in Microbiology, 2022,13. DOI: 10.3389/fmicb.2022.995323.
[13]	OULEFKI A, AGAIAN S, TRONGTIRAKUL T.Automatic COVID-19 lung infected region segmentation and measurement using CT-scans images[J]. Pattern Recognition, 2021,114. DOI: 10.1016/j.patcog.2020.107747.
[14]	BENMALEK E, ELMHAMDI J, JILBAB A.Comparing CT scan and chest X-ray imaging for COVID-19 diagnosis[J]. Biomedical Engineering Advances, 2021,1. DOI: 10.1016/j.bea.2021.100003.
[15]	SENGUPTA A, YE Y, WANG R, et al.Going deeper in spiking neural networks: VGG and residual architectures[J]. Frontiers in Neuroscience, 2019,13. DOI:10.3389/fnins.2019.00095.
[16]	PANT G, YADAV D P, GAUR A.ResNeXt convolution neural network topology-based deep learning model for identification and classification of Pediastrum[J]. Algal Research, 2020,48. DOI: 10.1016/j.algal.2020.101932.
[17]	ZHOU T, ZHAO Y, WU J.ResNeXt and Res2Net structures for speaker verification[C]// 2021 IEEE Spoken Language Technology Workshop (SLT). 2021:301-307.
[18]	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). 2016:565-571.
[19]	ISENSEE F, JÄGER P F, KOHL S A A, et al. Automated design of deep learning methods for biomedical image segmentation[J]. arXiv preprint arXiv:1904.08128, 2019.
[20]	ISENSEE F, PETERSEN J, KLEIN A, et al. nnU-Net: Self-adapting framework for U-Net-based medical image segmentation[J]. arXiv preprint arXiv:1809.10486, 2018.
[21]	谢娟英,夏琴. 新冠肺炎CXR图像分类新模型COVID-SERA-NeXt[J]. 太原理工大学学报, 2022,53(1):52-62.
[22]	JAVAHERI T, HOMAYOUNFAR M, AMOOZGAR Z, et al.CovidCTNet: An open-source deep learning approach to identify covid-19 using CT image[J]. arXiv preprint arXiv:2005.03059, 2020.
[23]	BIZOPOULOS P, VRETOS N, DARAS P.Comprehensive comparison of deep learning models for lung and COVID-19 lesion segmentation in CT scans[J]. arXiv preprint arXiv:2009.06412, 2020.
[24]	ZHAO R, QIAN B, ZHANG X, et al.Rethinking dice loss for medical image segmentation[C]// 2020 IEEE International Conference on Data Mining (ICDM). 2020:851-860.
[25]	VEIT A, WILBER M, BELONGIE S.Residual networks behave like ensembles of relatively shallow networks[J]. Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016:550-558.
[26]	ZHU X, CHENG D, ZHANG Z, et al.An empirical study of spatial attention mechanisms in deep networks[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). 2019:6687-6696.
[27]	WOO S, PARK J, LEE J, et al.CBAM: Convolutional block attention module[C]// Computer Vision-ECCV 2018. 2018:3-19.
[28]	TAKIKAWA T, ACUNA D, JAMPANI V, et al.Gated-SCNN: Gated shape CNNs for semantic segmentation[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). 2019:5229-5238.

基于ResNeXt和改进nnU-Net的新冠感染早期诊断方法

An Early Diagnosis Method of COVID-19 Infection Based on ResNeXt and Improved nnU-Net

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献 28

相关文章 15

编辑推荐

Metrics

本文评价

[1]	付鸿林, 张太红, 杨雅婷, 艾孜麦提·艾瓦尼尔, 马博. 基于生成对抗网络的维语场景文字修改网络[J]. 计算机与现代化, 2024, 0(01): 41-46.
[2]	李颖颖, 黄文培. 基于优化八叉树的场景视锥体裁剪算法[J]. 计算机与现代化, 2024, 0(01): 103-108.
[3]	马泽宇, 叶宁, 徐康, 王甦, 王汝传, . 基于FMCW雷达和ResNeSt-GRU的行为识别方法[J]. 计算机与现代化, 2023, 0(11): 101-107.
[4]	张嘉琪, 徐啟蕾. 基于NAM-YOLO网络的苹果缺陷检测算法[J]. 计算机与现代化, 2023, 0(10): 53-58.
[5]	李延满, 王必恒, 赵羚焱. 基于轻量化YOLOv5的安全帽检测[J]. 计算机与现代化, 2023, 0(10): 59-64.
[6]	张楠, 李温静, 刘彩, 谢可, 马世乾, 肖钧浩, 邹枫. 基于多源数据的电力作业人员实时行为安全预警[J]. 计算机与现代化, 2023, 0(10): 84-91.
[7]	陈子健, 段春红. 面向在线学习情境的认知情绪面部表情识别[J]. 计算机与现代化, 2023, 0(10): 92-98.
[8]	农皓程, 任德均, 任秋霖, 刘澎笠, 黄德成. 基于改进ConvNeXt的软塑包装表面异常检测算法[J]. 计算机与现代化, 2023, 0(08): 12-17.
[9]	刘昱杉, 刘卫康, 刘庆华, 者甜甜, 王家晨. 基于YOLOX结合DeepSort的船载车辆行人检测算法[J]. 计算机与现代化, 2023, 0(08): 60-67.
[10]	山雨, 张好鹏, 池静. 基于改进YOLOv4的轻量化车牌检测算法[J]. 计算机与现代化, 2023, 0(07): 99-104.
[11]	罗伟, 刘思远, 徐健祥, 董天培. 基于改进YOLOv5s的太阳能电池缺陷检测算法[J]. 计算机与现代化, 2023, 0(07): 119-126.
[12]	李实秋. 一种基于协作表示的判别局部保持投影方法[J]. 计算机与现代化, 2023, 0(06): 43-47.
[13]	彭明康, 冯成德. 基于双目视觉去除附着噪声的改进算法[J]. 计算机与现代化, 2023, 0(06): 62-68.
[14]	周芳宇, 陈淑荣. 一种特征增强的Tri-CNN行人再识别方法[J]. 计算机与现代化, 2020, 0(09): 60-65.
[15]	李运川, 王晓红, 陈思吉, 葛义攀, 李闯. 基于多核并行和动态阈值的点云配准算法[J]. 计算机与现代化, 2020, 0(09): 77-82.