改进DeepLabv3+网络的肠道息肉分割方法

doi:10.3778/j.issn.1673-9418.1907053

摘要/Abstract

摘要：

为了提高结肠镜下肠道息肉检测率，提出了一种改进DeepLabv3+网络的肠道息肉分割方法。在数据预处理阶段，利用中值滤波的非线性滤波特性去除掉图像反光区域，并结合Grab Cut算法对息肉区域进行预提取，得到息肉位置的粗分割结果，将其与原图叠加以增强息肉位置的信号强度。在网络结构上，将通过神经架构搜索得到的最优密集预测单元引入DeepLabv3+网络，并在解码器部分采用3层深度可分离卷积逐步获取分割结果，减少分割过程中不完全分割的情况。实验通过对CVC-ClinicDB数据集进行训练和测试，以平均交并比、Dice系数、敏感度、精确率以及F1值作为评判标准，其中平均交并比达到0.947，其余4项指标也均高于0.935。实验结果表明提出的方法与现有方法相比，对肠道息肉图像分割在精度上有一定提升，对深度学习在肠道息肉图像的处理和分析具有借鉴意义。

关键词: 改进DeepLabv3+, 肠道息肉, 神经架构搜索, 不完全分割

Abstract:

In order to enhance the detection rate of polyp of intestine under colonoscopy, an improved DeepLabv3+ network method for intestinal polyp segmentation is proposed. In the data preprocessing stage, using the nonlinear filtering characteristics of the median filter to remove the image reflection area, and Grab Cut algorithm is combined to pre-extract the polyp area. Coarse segmentation results of polyp location are obtained, which are superimposed with the original drawing to reinforce the signal strength of polyp location. In terms of network structure, this paper introduces the optimal dense prediction cell obtained through neural architecture search into DeepLabv3+ network, uses 3-layer depth separable convolution to gradually acquire segmentation results in the decoder part, so as to reduce incomplete segmentation in the segmentation process. In the experiment, through training and testing of CVC-ClinicDB data set, the average joining and merging ratio, Dice coefficient, sensitivity, precision and F1 value are used as judgment standard. The mean intersection over union reaches 0.947, and the other 4 indexes are all higher than 0.935. The experimental results show that compared with the existing methods, the proposed method in this paper improves the accuracy of intestinal polyp image segmentation to a certain extent, which can be used for reference in the processing and analysis of intestinal polyp images by deep learning.

Key words: improved DeepLabv3+, intestinal polyp, neural architecture search, incomplete segmentation

王亚刚，郗怡媛，潘晓英. 改进DeepLabv3+网络的肠道息肉分割方法[J]. 计算机科学与探索, 2020, 14(7): 1243-1250.

WANG Yagang, XI Yiyuan, PAN Xiaoying. Method for Intestinal Polyp Segmentation by Improving DeepLabv3+ Network[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(7): 1243-1250.

参考文献

[1] Torre L A, Bray F, Siegel R L, et al. Global cancer statistics, 2012[J]. CA: A Cancer Journal for Clinicians, 2015, 65(2): 87-108.
[2] Ciuti G, Caliò R, Camboni D, et al. Frontiers of robotic endo-scopic capsules: a review[J]. Journal of Micro-Bio Robotics, 2016, 11: 1-18.
[3] Lieberman D A, Rex D K, Winawer S J, et al. Guidelines for colonoscopy surveillance after screening and polypectomy: a consensus update by the US multi-society task force on colorectal cancer[J]. Gastroenterology, 2012, 143(3): 844-857.
[4] Corley D A, Jensen C D, Marks A R, et al. Adenoma detec-tion rate and risk of colorectal cancer and death[J]. New England Journal of Medicine, 2014, 370(14): 1298-1306.
[5] Leufkens A M, Van Oijen M G H, Vleggaar F P, et al. Factors influencing the miss rate of polyps in a back-to-back colo-noscopy study[J]. Endoscopy, 2012, 44(5): 470-475.
[6] Brandao P, Mazomenos E B, Ciuti G, et al. Fully convolu-tional neural networks for polyp segmentation in colonoscopy[C]//Proceedings of the Medical Imaging 2017: Computer-Aided Diagnosis，Orlando, Feb 13-16, 2017. San Francisco: SPIE, 2017: 101340F.
[7] Bernal J, Sánchez F J, Fernández-Esparrach G, et al. WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians[J]. Computerized Medical Imaging and Graphics, 2015, 43: 99-111.
[8] Sasmal P, Iwahori Y, Bhuyan M K, et al. Active contour seg-mentation of polyps in capsule endoscopic images[C]//Pro-ceedings of the 2018 International Conference on Signals and Systems, Bali, May 1-3, 2018. Piscataway: IEEE, 2018: 201-204.
[9] Wang L S, Qian Y, Hu Y X. Segmentation of intestinal polyps via a deep learning algorithm[J]. Gut, 2018, 67(S2).
[10] Nguyen Q, Lee S W. Colorectal segmentation using multiple encoder-decoder network in colonoscopy images[C]//Pro-ceedings of the IEEE 1st International Conference on Arti-ficial Intelligence and Knowledge Engineering, Laguna Hills, Sep 26-28, 2018: 208-211.
[11] Wang P, Xiao X, Brown J R G, et al. Development and valida-tion of a deep-learning algorithm for the detection of polyps during colonoscopy[J]. Nature Biomedical Engineering, 2018, 2(10): 741-748.
[12] Park S, Lee M, Kwak N. Polyp detection in colonoscopy videos using deeply-learned hierarchical features[R]. Seoul National University, 2015.
[13] Xiao W T, Chang L J, Liu W M. Semantic segmentation of colorectal polyps with DeepLab and LSTM networks[C]//Proceedings of the 2018 IEEE International Conference on Consumer Electronics, Taiwan, China, May 19-21, 2018. Piscataway: IEEE, 2018: 1-2.
[14] Elsken T, Metzen J H, Hutter F. Neural architecture search: a survey[J]. Journal of Machine Learning Research, 2019, 20(55): 1-21.
[15] Rother C, Kolmogorov V, Blake A. Interactive foreground extraction using iterated graph cuts[J]. ACM Transactions on Graphics, 2004, 23(3): 309-314.
[16] Yang X P, He X H, Wang Z Y, et al. Non-interaction image segmentation algorithm based on GrabCut[J]. Science Tech-nology and Engineering, 2018, 18(26): 207-212.杨小鹏, 何小海, 王正勇, 等. 基于GrabCut的免交互图像分割算法[J]. 科学技术与工程, 2018, 18(26): 207-212.
[17] Liu C, Xiao Z Y, Du N M. Application of improved convo-lutional neural network in medical image segmentation[J]. Journal of Frontiers of Computer Science and Technology, 2019, 13(9): 1593-1603.刘辰, 肖志勇, 杜年茂. 改进的卷积神经网络在医学图像分割上的应用[J]. 计算机科学与探索, 2019, 13(9): 1593-1603.
[18] Chen L C, Collins M, Zhu Y, et al. Searching for efficient multi-scale architectures for dense image prediction[C]//Pro-ceedings of the 2018 Annual Conference on Neural Infor-mation Processing Systems, Montréal, Dec 3-8, 2018. Cam-bridge: MIT Press, 2018: 8699-8710.
[19] Chollet F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Jul 21-26, 2017. Washington: IEEE Computer Society, 2017: 1800-1807.
[20] Zhang X H. Technical study on image processing of laparos-copic scanning[D]. Changchun: Changchun University of Science and Technology, 2010.张晓晖. 腹腔镜扫描图像处理技术性研究[D]. 长春: 长春理工大学, 2010.
[21] Loupas T, McDicken W N, Allan P L. An adaptive weighted median filter for speckle suppression in medical ultrasonic images[J]. IEEE Transactions on Circuits and Systems, 1989, 36(1): 129-135.