COVIDSeg:新冠肺炎肺部CT图像轻量化分割模型

谢娟英; 夏琴

doi:10.15983/j.cnki.jsnu.2022108

陕西师范大学学报(自然科学版) >

2022 , Vol. 50 >Issue 3: 65 - 78

DOI: https://doi.org/10.15983/j.cnki.jsnu.2022108

人工智能专题

COVIDSeg:新冠肺炎肺部CT图像轻量化分割模型

谢娟英 ,
夏琴

展开

陕西师范大学计算机科学学院, 陕西西安 710119

收稿日期: 2021-10-07

网络出版日期: 2022-05-10

基金资助

国家自然科学基金(62076159,12031010,61673251);中央高校基本科研业务费专项资金(GK202105003, GK201701006, 2018TS078)

收起

COVIDSeg: the lightweight segmentation model for the lung CT images of COVID-19 patients

XIE Juanying ,
XIA Qin

Expand

School of Computer Science, Shaanxi Normal University, Xi'an 710119, Shaanxi, China

Received date: 2021-10-07

Online published: 2022-05-10

Fold

摘要

新型冠状病毒肺炎(COVID-19)严重威胁人类健康,计算机自动分割患者肺部CT(computed tomography)图像是辅助医生进行快速准确诊断的重要手段。为此,提出针对新冠肺炎肺部CT图像分割的轻量化模型COVIDSeg。模型采用编码器-解码器结构,提出压缩-扩展通道注意力模块(squeeze and extend channel attention block,SECA)和残差多尺度注意力模块(residual multi-scale channel attention block,RMSCA)构成编码子网络主要组成模块,提出双通路结构连接编码子网络的各模块,通路内特征逐层传递,通路之间多级特征信息交互,促进不同层级有效信息的传递和表达;采用特征聚合模块作为解码子网络的主要组成模块,通过多尺度特征解码实现多路径解码器。在4个公开使用的COVID-19 CT图像数据集的实验测试表明,提出的轻量化新冠肺炎CT图像分割模型COVIDSeg在多项指标上优于当前主流的医学图像分割模型。通过消融实验分析主要模块对模型性能的影响,验证了提出的缩减-扩展通道注意力模块SECA和残差多尺度注意力模块RMSCA的有效性。分割结果可视化显示,模型对新冠肺炎肺部CT图像的分割结果与图像的真实Mask标记基本相同。

关键词： 新型冠状病毒肺炎; 计算机辅助诊断; CT图像; 分割; 注意力机制

本文引用格式

谢娟英 , 夏琴 . COVIDSeg:新冠肺炎肺部CT图像轻量化分割模型[J]. 陕西师范大学学报(自然科学版), 2022 , 50(3) : 65 -78 . DOI: 10.15983/j.cnki.jsnu.2022108

Abstract

COVID-19 has severely been threatening human being. The computer aided automatic segmentation of lung CT (computed tomography) images is an important way to help medicine doctors to make fast and accurate diagnostic decisions. Therefore, a lightweight model referred to as COVIDSeg is proposed in this paper for segmenting the lung CT images of COVID-19 patients. This model adopts encoder-decoder structure. The squeeze and extend channel attention block (SECA) and the residual multi-scale channel attention block (RMSCA) are proposed to compose the main components of the encoder subnetwork. The dual-path structure is proposed to connect each module of the encoder network. The features are transferred layer by layer along the path, and features from different layers interact between pathways, so that the feature information can be transferred and expressed between different layers. The feature aggregation module is used as the main component of the decoder network, so as to realize the multipath decoder via multiscale feature decoding. This COVIDSeg model is tested on four public COVID-19 CT image datasets. The experimental results show that the proposed lightweight model COVIDSeg for segmenting the COVID-19 CT images outperforms the current main medical image segmentation models in terms of several popular metrics, and it is so far the best model for segmenting the lung CT images of COVID-19 patients. Furthermore, the ablation experiment was carried out to test the influence over the COVIDSeg model performance from its main modules. The experimental results show that the proposed SECA module and RMSCA module are effective to advance the performance of the COVIDSeg model.The segmentation results are visualized for this COVIDSeg model for the lung CT images of COVID-19 patients, and it is found that the segmentation results are basically identical to the real Mask of the images.

Key words： COVID-19; computer aided diagnosis; CT images; segmentation; attentional mechanism

参考文献

[1] CUCINOTTA D,VANELLI M. WHO declares COVID-19 a pandemic[J]. Acta Bio-Medica:Atenei Parmensis,2020,91(1):157-160.
[2] CHAN J F W,YUAN S F,KOK K H,et al. A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission:a study of a family cluster[J]. The Lancet,2020,395(10223):514-523.
[3] ZHU N,ZHANG D Y,WANG W L,et al. A novel coronavirus from patients with pneumonia in China,2019[J]. The New England Journal of Medicine,2020,382(8):727-733.
[4] 中华人民共和国国家卫生健康委员会. 新型冠状病毒肺炎诊疗方案(试行第七版)[EB/OL].[2021-03-03]. http://www.nhc.gov.cn.
National Health Commission of the People's Republic of China.Diagnosis and treatment protocol for COVID-19(trial version 7)[EB/OL].[2021-03-03]. http://www.nhc.gov.cn.
[5] KANNE J P,LITTLE B P,CHUNG J H,et al. Essentials for radiologists on COVID-19:an update-radiology scientific expert panel[J]. Radiology,2020,296(2):E113-E114.
[6] SHI H S,HAN X Y,JIANG N C,et al. Radiological findings from 81 patients with COVID-19 pneumonia in Wuhan,China:a descriptive study[J]. The Lancet Infectious Diseases,2020,20(4):425-434.
[7] KANNE J P. Chest CT findings in 2019 novel coronavirus (2019-nCoV) infections from Wuhan,China:key points for the radiologist[J]. Radiology,2020,295(1):16-17.
[8] 方旭,边云,刘芳,等.计算机断层扫描对新型冠状病毒肺炎的诊断要点及临床意义[J].第二军医大学学报,2020,41(6):588-591.
FANG X,BIAN Y,LIU F,et al.Computed tomography in coronavirus disease 2019:diagnosis and clinical significance[J].Academic Journal of Second Military Medical University,2020,41(6):588-591.
[9] PENG S T,CHEN W,SUN J W,et al. Multi-scale 3D U-Nets:an approach to automatic segmentation of brain tumor[J]. International Journal of Imaging Systems and Technology,2020,30(1):5-17.
[10] HU H G,GUAN Q,CHEN S Y,et al. Detection and recognition for life state of cell cancer using two-stage cascade CNNs[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics,2020,17(3):887-898.
[11] XIE J Y,LIU R,LUTTRELL J,et al. Deep learning based analysis of histopathological images of breast cancer[J]. Frontiers in Genetics,2019,10:80.
[12] XIE J Y,PENG Y. The head and neck tumor segmentation using NNU-Net with spatial and channel ‘squeeze & excitation’ blocks[M]//Head and Neck Tumor Segmentation.Cham:Springer,2021:28-36.
[13] RAJAMANI K T,SIEBERT H,HEINRICH M P. Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation[J]. Journal of Biomedical Informatics,2021,119:103816.
[14] BUDAK Ü,ÇIBUK M,CÖMERT Z,et al. Efficient COVID-19 segmentation from CT slices exploiting semantic segmentation with integrated attention mechanism[J]. Journal of Digital Imaging,2021,34(2):263-272.
[15] BADRINARAYANAN V,KENDALL A,CIPOLLA R. SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[16] KUMAR SINGH V,ABDEL-NASSER M,PANDEY N,et al. LungINFseg:segmenting COVID-19 infected regions in lung CT images based on a receptive-field-aware deep learning framework[J]. Diagnostics (Basel,Switzerland),2021,11(2):158.
[17] FAN D P,ZHOU T,JI G P,et al. Inf-Net:automatic COVID-19 lung infection segmentation from CT images[J]. IEEE Transactions on Medical Imaging,2020,39(8):2626-2637.
[18] RAZAVIAN A S,AZIZPOUR H,SULLIVAN J,et al. CNN features off-the-shelf:an astounding baseline for recognition[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.Columbus,USA: IEEE,2014:512-519.
[19] SHELHAMER E,LONG J,DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[20] RONNEBERGER O,FISCHER P,BROX T. U-Net:convolutional networks for biomedical image segmentation[C]//Medical Image Computing and Computer-Assisted Intervention.Munich,Germany:MICCAI,2015:234-241.
[21] ZHOU Z W,SIDDIQUEE M M R,TAJBAKHSH N,et al. UNet++:a nested U-Net architecture for medical image segmentation[C]//Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support.Granada,Spain:MICCAI,2018:3-11.
[22] OKTAY O,SCHLEMPER J,FOLGOC L L,et al. Attention U-Net:learning where to look for the pancreas[EB/OL].[2021-04-11]. https://arxiv.org/abs/1804.03999.
[23] CORBETTA M, SHULMAN G L. Control of goal-directed and stimulus-driven attention in the brain[J]. Nature Reviews Neuroscience, 2002, 3(3): 201-215.
[24] HU J,SHEN L,SUN G. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City,USA:IEEE,2018:7132-7141.
[25] WANG Q L,WU B G,ZHU P F,et al. ECA-Net:efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle,USA:IEEE,2020:11531-11539.
[26] CAO Y,XU J R,LIN S,et al. GCNet:non-local networks meet squeeze-excitation networks and beyond[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).Seoul,South Korea:IEEE,2019:1971-1980.
[27] FU J,LIU J,TIAN H J,et al. Dual attention network for scene segmentation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Long Beach,USA:IEEE,2019:3141-3149.
[28] SCHRAUDOLPH N. Accelerated gradient descent by factor-centering decomposition[J]. Technical Report/IDSIA, 1998, 98:1-10.
[29] RAIKO T, VALPOLA H, LECUN Y.Deep learning made easier by linear transformations in perceptrons[C]//Artificial Intelligence and Statistics.Canary Island,Spain:JMLR,2012: 924-932.
[30] SRIVASTAVA R K,GREFF K,SCHMIDHUBER J. Training very deep networks[EB/OL].[2015-07-22].https://arxiv.org/abs/1507.06228.
[31] HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA:IEEE,2016:770-778.
[32] HUANG G,LIU Z,VAN DER MAATEN L,et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,USA:IEEE,2017:2261-2269.
[33] SZEGEDY C,LIU W,JIA Y Q,et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition.Boston,USA:IEEE,2015:1-9.
[34] CHEN L C,PAPANDREOU G,SCHROFF F,et al. Rethinking atrous convolution for semantic image segmentation[EB/OL].[2021-06-17].https://arxiv.org/abs/1706.05587.
[35] ZHAO H S,SHI J P,QI X J,et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.Honolulu,USA:IEEE,2017:6230-6239.
[36] CHEN C F,FAN Q F,MALLINAR N,et al. Big-little net:an efficient multi-scale feature representation for visual and speech recognition[EB/OL].[2021-07-10]. https://arxiv.org/abs/1807.03848.
[37] QIU Y, LIU Y, LI S, et al. Miniseg:an extremely minimum network for efficient covid-19 segmentation[EB/OL]. [2021-03-03].https://arxiv.org/abs/2004.09750.
[38] ZHENG C, DENG X, FU Q, et al. Deep learning-based detection for COVID-19 from chest CT using weak label[EB/OL].[2021-03-03].https://paperswithcode.com/paper/deep-learning-based-detection-for-covid-19.
[39] SHAN F, GAO Y, WANG J, et al.Lung infection quantification of COVID-19 in CT images with deep learning[EB/OL].[2021-03-10].https://arxiv.org/abs/2003/2003.04655.
[40] LI L, QIN L, XU Z, et al. Artificial intelligence distinguishes COVID-19 from community acquired pneumonia on chest CT[J]. Radiology, 2020, 296(2): E65-E72.
[41] MA J,WANG Y X,AN X L,et al.Towards data-efficient learning:a benchmark for COVID-19 CT lung and infection segmentation[EB/OL].[2021-04-27].https://arxiv. org/abs/2004.12537.
[42] WU Y H,GAO S H,MEI J,et al. JCS:an explainable COVID-19 diagnosis system by joint classification and segmentation[J]. IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society,2021,30:3113-3126.
[43] AMYAR A,MODZELEWSKI R,LI H,et al. Multi-task deep learning based CT imaging analysis for COVID-19 pneumonia:classification and segmentation[J]. Computers in Biology and Medicine,2020,126:104037.
[44] ZHOU T X,CANU S,RUAN S. Automatic COVID-19 CT segmentation using U-Net integrated spatial and channel attention mechanism[J]. International Journal of Imaging Systems and Technology,2021,31(1):16-27.
[45] JENSSEN H B. COVID-19 CT segmentation dataset[EB/OL]// [2021-03-03]. https://medicalsegmentation.com/covid19.
[46] MOROZOV S P,ANDREYCHENKO A E,PAVLOV N A,et al. MosMedData:chest CT scans with COVID-19 related findings dataset[EB/OL].[2021-05-13].https://arxiv.org/abs/2005.06465v1.
[47] CHEN L C,ZHU Y K,PAPANDREOU G,et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Computer Vision-ECCV 2018.Munich,Germany:ECCV,2018:801-818.
[48] PASZKE A,CHAURASIA A,KIM S,et al. ENet:a deep neural network architecture for real-time semantic segmentation[EB/OL].[2021-06-07].https://arxiv.org/abs/1606.02147.
[49] MEHTA S,RASTEGARI M,CASPI A,et al. ESPNet:efficient spatial pyramid of dilated convolutions for semantic segmentation[C]//Computer Vision-ECCV 2018.Munich,Germany:ECCV,2018:561-580.
[50] WU T Y,TANG S,ZHANG R,et al. CGNet:a light-weight context guided network for semantic segmentation[J]. IEEE Transactions on Image Processing:A Publication of the IEEE Signal Processing Society,2021,30:1169-1179.
[51] LO S Y,HANG H M,CHAN S W,et al. Efficient dense modules of asymmetric convolution for real-time semantic segmentation[C]//MMAsia,19:Proceedings of the ACM Multimedia Asia.Beijing,China:ACM,2019:1-6.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献