多标签病毒性肺炎图像分割方法的研究

doi:10.3969/j.issn.0258-8021.2023.06.009

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (6559 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要目前,对于病毒性肺炎病灶分割的研究大多是基于单标签分割的,其分割准确率并不是特别理想。为提高病灶分割的准确率,提出了一种基于多标签的病毒性肺炎图像分割方法。本方法结合预先已知的肺部特征知识,将肺部特征信息叠加病灶特征信息形成多标签,并利用One-Hot编码原理和改进的3D-UNet网络模型,结合来源于大挑战比赛中的病毒性肺炎病灶分割挑战-2020公共数据集进行多标签图像分割训练,其中训练集139 例,验证集和预测集同为40 例,共计179 例。在评价指标的选择上,除了常规的Dice评价指标外,本研究还提出了一个新的评估指标,炎肺比(focus-lung ratio),提供了病灶和肺部的比例,结合精度评价指标,可用于衡量模型的鲁棒性。最终,该研究提出的双标签分割方法在公开数据集上的预测集的Dice可达到70.10 %,相较于同网络下的单标签分割方法,提高4.20 %的准确率;该研究还通过3种不同网络(级联Res-UNet,nnUNet-ResUNet,3D-UNet)进行对比试验,实验结果表明在训练集上Dice损失达到最小,为5.00 %;在验证集上Dice达到最大,为75.70 %。所提出的方法改善了肺炎病灶分割的准确率,提高了模型的鲁棒性,对未来相关研究具有一定的临床价值和潜在意义。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	吴怡红
	杨勇
	叶宏伟
	王小状
	孙芳芳

关键词 ：深度学习, 图像分割, CT图像, 多标签, 病毒性肺炎

Abstract：Researches on the segmentation algorithm of COVID-19’s lesion are mostly based on the single-label segmentation algorithm, but the accuracy can’t reach the clinical criteria. In this paper, a new method of COVID-19’s lesion segmentation based on multi-label was proposed, training on COVID-19 Lung CT Lesion Segmentation Challenge-2020 dataset in the Grand Challenge. The dataset contains 179 cases, including 139 cases in the training set and the rest 40 cases in both of the validation and prediction set. We conducted lung regions with existing lung region segmentation model, which generated from LUNA16 dataset. The generated lung region label was incorporated with the lesion label to form the multi-label of training dataset. The One-Hot coding principle and improved 3D-UNet network model is used for training. This paper also proposed a new evaluation index, focus-lung ratio which was used to reflect the proportion of lesion regions in the lung and measured the model’s robustness with other indicators. In the end, the prediction’s Dice reached 70.10 %, which is 4.20 % higher than the single-label segmentation method under the same network. Besides, our results were compared with some published data, and ours displayed better performance, the validation’s accuracy of dataset reached 75.70 %. Experimental results showed that the proposed algorithm improved the accuracy of pneumonia lesion segmentation and the robustness of the model, therefore, is of clinical value and potential significance for future studies.

Key words： deep learning image segmentation computerized tomography multi-label viral pneumonia

收稿日期: 2021-08-25

PACS:

R318

通讯作者: ^*E-mail:sunff511@hdu.edu.cn

作者简介: ^#中国生物医学工程学会会员

引用本文:

吴怡红, 杨勇, 叶宏伟, 王小状, 孙芳芳. 多标签病毒性肺炎图像分割方法的研究[J]. 中国生物医学工程学报, 2023, 42(6): 720-729.
Wu Yihong, Yang Yong, Ye Hongwei, Wang Xiaozhuang, Sun Fangfang. Research on Multi-Label Viral Pneumonia Image Segmentation Method. Chinese Journal of Biomedical Engineering, 2023, 42(6): 720-729.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2023.06.009 或 http://cjbme.csbme.org/CN/Y2023/V42/I6/720

[1] Payer C, Štern D, Bischof H, et al. Multi-label whole heart segmentation using CNNs and anatomical label configurations [C]// International Workshop on Statistical Atlases and Computational Models of the Heart. Berlin: Springer-Cham, 2017:190-198.
[2] Dina B. Efremova. Automatic segmentation of kidney and liver tumors in CT images [DB/OL]. https://doi.org/10.48550/arXiv.1908.01279, 2019-08-04/2019-09-16.
[3] Kim H, Jung J, Kim J, et al. Abdominal multi-organ auto-segmentation using 3D-patch-based deep convolutional neural network [J]. Scientific Reports, 2020, 10(1):6204.
[4] Pandey P K. Segmentation of Liver Lesions with Reduced Complexity Deep Models [DB/OL]. https://doi.org/10.48550/arXiv.1805.09233, 2018-05-23/2018-05-23.
[5] Wei Yunchao, Xia Wei, Lin Min, et al. HCP: A Flexible CNN Framework for Multi-Label Image Classification [J]. IEEE Transactions on Software Engineering, 2016, 38(9):1901-1907.
[6] Yang Xiaoyun, Ye Xujiong, Slabaugh G. Multilabel region classification and semantic linking for colon segmentation in CT colonography [J]. IEEE Transactions on Biomedical Engineering, 2015, 62(3): 948-959.
[7] Ye Jin, He Junjun, Peng Xiaojiang, et al. Attention-driven dynamic graph convolutional network for multi-label image recognition [C]// European conference on computer vision. Berlin: Springer-Cham, 2020: 649-665.
[8] Yun S, Oh SJ, Heo B, et al. Re-labeling imagenet: from single to multi-labels, from global to localized labels [C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2021: 2340-2350.
[9] Zhang Minling, Zhou Zhihua. A k-nearest neighbor based algorithm for multi-label classification [C]// 2005 IEEE international conference on granular computing. New York: IEEE, 2005, 2: 718-721.
[10] Zhang Minling, Zhou Zhihua. Multilabel neural networks with applications to functional genomics and text categorization [J]. IEEE Transactions on Knowledge & Data Engineering, 2006, 18(10):1338-1351.
[11] 中华医学会放射学分会. 新型冠状病毒肺炎的放射学诊断:中华医学会放射学分会专家推荐意见(第一版)[J] . 中华放射学杂志, 2020, 54(4): 279-285.
[12] Ma Jun, Wang Yixin, An Xingle, et al. Toward data-efficient learning: a benchmark for COVID-19 CT lung and infection segmentation [J]. Medical physics, 2021, 48(3): 1197-1210.
[13] Rajamani KT, Siebert H, Heinrich MP. Dynamic deformable attention network (DDANet) for COVID-19 lesions semantic segmentation [J]. Journal of Biomedical Informatics, 2021, 119: 103816.
[14] Jin Qiangguo, Cui Hui, Sun Changming, et al. Domain adaptation based self-correction model for COVID-19 infection segmentation in CT images [J]. Expert Systems with Applications, 2021, 176: 114848.
[15] Gholamiankhah F. Automated lung segmentation from CT images of normal and COVID-19 pneumonia patients [DB/OL]. https://arxiv. org/abs/2104.02042, 2021-04-05/2021-04-05.
[16] Setio AAA, Traverso A, De Bel T, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge [J]. Medical Image Analysis, 2017, 42: 1-13.
[17] Litjens G, Kooi T, Bejnordi BE, et al. A survey on deep learning in medical image analysis [J]. Medical Image Analysis, 2017, 42: 60-88.
[18] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2015: 3431-3440.
[19] Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, Cham, 2015: 234-241.
[20] Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin: Springer, Cham, 2016:424-432.
[21] Ulyanov D, Vedaldi A, Lempitsky V. Instance normalization: the missing ingredient for fast stylization [DB/OL]. https://doi.org/10.48550/arXiv.1607.08022, 2016-07-27/2017-11-06.
[22] Jadon S. A survey of loss functions for semantic segmentation [C]// 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB). New York: IEEE, 2020:1-7.
[23] Xie Weiyi, Jacobs C, van Ginneken B. Dense regression activation maps for lesion segmentation in CT scans of COVID-19 patients [DB/OL]. https://doi.org/10.48550/arXiv.2105.11748,2021-05-25/2021-11-18.
[24] Yang Dong, Xu Ziyue, Li Wenqi, et al. Federated semi-supervised learning for COVID region segmentation in chest CT using multi-national data from China, Italy, Japan [J]. Medical Image Analysis, 2021, 70: 101992.