Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism_Journal of Biomedical Engineering

Authors：

DONG Ting ¹ , WEI Long ² , YE Xiaodan ³ , CHEN Yang ¹ , HOU Xuewen ¹ ,  NIE Shengdong ¹

1. School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, P. R. China;
2. School of Computer Science and Technology, Shandong Jianzhu University, JiNan 250101, P. R. China;
3. Shanghai Chest Hospital, Shanghai 200030, P. R. China;

Corresponding author：

NIE Shengdong, Email: nsd4647@163.com

Keywords：

Ground glass nodule segmentation; Residual network; Atrous convolution; Attention mechanism; Computed tomography image

DOI：

10.7507/1001-5515.202010051

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Accurate segmentation of ground glass nodule (GGN) is important in clinical. But it is a tough work to segment the GGN, as the GGN in the computed tomography images show blur boundary, irregular shape, and uneven intensity. This paper aims to segment GGN by proposing a fully convolutional residual network, i.e., residual network based on atrous spatial pyramid pooling structure and attention mechanism (ResAANet). The network uses atrous spatial pyramid pooling (ASPP) structure to expand the feature map receptive field and extract more sufficient features, and utilizes attention mechanism, residual connection, long skip connection to fully retain sensitive features, which is extracted by the convolutional layer. First, we employ 565 GGN provided by Shanghai Chest Hospital to train and validate ResAANet, so as to obtain a stable model. Then, two groups of data selected from clinical examinations (84 GGN) and lung image database consortium (LIDC) dataset (145 GGN) were employed to validate and evaluate the performance of the proposed method. Finally, we apply the best threshold method to remove false positive regions and obtain optimized results. The average dice similarity coefficient (DSC) of the proposed algorithm on the clinical dataset and LIDC dataset reached 83.46%, 83.26% respectively, the average Jaccard index (IoU) reached 72.39%, 71.56% respectively, and the speed of segmentation reached 0.1 seconds per image. Comparing with other reported methods, our new method could segment GGN accurately, quickly and robustly. It could provide doctors with important information such as nodule size or density, which assist doctors in subsequent diagnosis and treatment.

Citation： DONG Ting, WEI Long, YE Xiaodan, CHEN Yang, HOU Xuewen, NIE Shengdong. Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism. Journal of Biomedical Engineering, 2022, 39(3): 441-451. doi: 10.7507/1001-5515.202010051 Copy

1.	Siegel R L, Miller K D, Jemal A. Cancer statistics, 2020. CA Cancer J Clin, 2020, 70(1): 7-30.
2.	Henschke C, Yip R, Ma T, et al. CT screening for lung cancer: comparison of three baseline screening protocols. Eur Radiol, 2019, 29(10): 5217-5226.
3.	Fan L, Liu S Y, Li Q C, et al. Multidetector CT features of pulmonary focal ground-glass opacity: differences between benign and malignant. Br J Radiol, 2012, 85(115): 897-904.
4.	Liu H, Zhang C M, Su Z Y, et al. Research on a pulmonary nodule segmentation method combining fast self-adaptive FCM and classification. Comput Math Methods Med, 2015, 2015: 185726.
5.	Liu Hui, Geng Fenghuan, Guo Qiang, et al. A fast weak-supervised pulmonary nodule segmentation method based on modified self-adaptive FCM algorithm. Soft comput, 2018, 22(12): 3983-3995.
6.	Shakibapour E, Cunha A, Aresta G, et al. An unsupervised metaheuristic search approach for segmentation and volume measurement of pulmonary nodules in lung CT scans. Expert Syst Appl, 2019(119): 415-428.
7.	Nithila E E, Kumar S S. Segmentation of lung nodule in CT data using active contour model and fuzzy C-mean clustering. Alexandria Engineering Journal, 2016, 55(3): 2583-2588.
8.	Li B, Chen K, Peng G M, et al. Segmentation of ground glass opacity pulmonary nodules using an integrated active contour model with wavelet energy-based adaptive local energy and posterior probability-based speed function. Materials Express, 2016, 6(4): 317-327.
9.	Jung J, Hong H, Goo J M. Ground-glass nodule segmentation in chest CT images using asymmetric multi-phase deformable model and pulmonary vessel removal. Comput Biol Med, 2018, 92: 128-138.
10.	Farhangi M M, Frigui H, Seow A, et al. 3-D active contour segmentation based on sparse linear combination of training shapes (Scots). IEEE Trans Med Imaging, 2017, 36(11): 2239-2249.
11.	Zhang S, Chen X, Zhu Z, et al. Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference. Biomed Eng Online, 2020, 19(1): 51.
12.	Wang Shuo, Zhou Mu, Liu Zaiyi, et al. Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal, 2017, 40(40): 172-183.
13.	Liu H, Cao H, Song E, et al. A cascaded dual-pathway residual network for lung nodule segmentation in CT images. Phys Med, 2019, 63: 112-121.
14.	Cao H, Liu H, Song E, et al. Dual-branch residual network for lung nodule segmentation. Appl Soft Comput, 2020, 2020(86): 105934-105945.
15.	Wu Wenhao, Gao Lei, Duan Huihong, et al. Segmentation of pulmonary nodules in CT images based on 3D-UNET combined with three-dimensional conditional random field optimization. Med Phys, 2020, 47(9): 4054-4063.
16.	Meyer C R, Johnson T D, Mclennan G, et al. Evaluation of lung MDCT nodule annotation across radiologists and methods. Acad Radiol, 2006, 13(10): 1254-1265.
17.	Wang Wenzhe, Feng Ruiwei, Chen Jintai, et al. Nodule-plus R-CNN and deep self-paced active learning for 3D instance segmentation of pulmonary nodules. IEEE Access, 2019, 7(99): 128796-128805.
18.	Cai Linqin, Long Tao, Dai Yuhan, et al. Mask R-CNN-based detection and segmentation for pulmonary nodule 3D visualization diagnosis. IEEE Access, 2020, 8: 44400-44409.
19.	Li Xiangxia, Li Bin, Liu Fang, et al. Segmentation of pulmonary nodules using a GMM fuzzy C-means algorithm. IEEE Access, 2020, 8(99): 37541-37556.
20.	He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks// European Conference on Computer Vision, Cham: Springer, 2016: 630-645.
21.	Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions// International Conference on Learning Representations, Computer Vision and Pattern Recognition. New York: Academic Press, 2015: 255.
22.	Roy A G, Navab N, Wachinger C. Concurrent spatial and channel squeeze & excitation in fully convolutional networks//Medical Image Computing and Computer Assisted Intervention (MICCAI), Cham: Springer, 2018: 421-429.
23.	Jiang J, Hu Y C, Liu C J, et al. Multiple resolution residually connected feature streams for automatic lung tumor segmentation from CT images. IEEE Trans Med Imaging, 2019, 38(1): 134-144.
24.	Esteves T, Quelhas P, Mendonca A M, et al. Gradient convergence filters and a phase congruency approach for in vivo cell nuclei detection. Machine Vision Applications, 2012, 23(4): 623-638.
25.	Dhara A K, Mukhopadhyay S, Das Gupta R, et al. Erratum to: a segmentation framework of pulmonary nodules in lung CT images. J Digit Imaging, 2016, 29(1): 148-148.
26.	Song Jiangdian, Yang Caiyun, Fan Li, et al. Lung lesion extraction using a toboggan based growing automatic segmentation approach. IEEE Trans Med Imaging, 2016, 35(1): 337-353.

1. Siegel R L, Miller K D, Jemal A. Cancer statistics, 2020. CA Cancer J Clin, 2020, 70(1): 7-30.
2. Henschke C, Yip R, Ma T, et al. CT screening for lung cancer: comparison of three baseline screening protocols. Eur Radiol, 2019, 29(10): 5217-5226.
3. Fan L, Liu S Y, Li Q C, et al. Multidetector CT features of pulmonary focal ground-glass opacity: differences between benign and malignant. Br J Radiol, 2012, 85(115): 897-904.
4. Liu H, Zhang C M, Su Z Y, et al. Research on a pulmonary nodule segmentation method combining fast self-adaptive FCM and classification. Comput Math Methods Med, 2015, 2015: 185726.
5. Liu Hui, Geng Fenghuan, Guo Qiang, et al. A fast weak-supervised pulmonary nodule segmentation method based on modified self-adaptive FCM algorithm. Soft comput, 2018, 22(12): 3983-3995.
6. Shakibapour E, Cunha A, Aresta G, et al. An unsupervised metaheuristic search approach for segmentation and volume measurement of pulmonary nodules in lung CT scans. Expert Syst Appl, 2019(119): 415-428.
7. Nithila E E, Kumar S S. Segmentation of lung nodule in CT data using active contour model and fuzzy C-mean clustering. Alexandria Engineering Journal, 2016, 55(3): 2583-2588.
8. Li B, Chen K, Peng G M, et al. Segmentation of ground glass opacity pulmonary nodules using an integrated active contour model with wavelet energy-based adaptive local energy and posterior probability-based speed function. Materials Express, 2016, 6(4): 317-327.
9. Jung J, Hong H, Goo J M. Ground-glass nodule segmentation in chest CT images using asymmetric multi-phase deformable model and pulmonary vessel removal. Comput Biol Med, 2018, 92: 128-138.
10. Farhangi M M, Frigui H, Seow A, et al. 3-D active contour segmentation based on sparse linear combination of training shapes (Scots). IEEE Trans Med Imaging, 2017, 36(11): 2239-2249.
11. Zhang S, Chen X, Zhu Z, et al. Segmentation of small ground glass opacity pulmonary nodules based on Markov random field energy and Bayesian probability difference. Biomed Eng Online, 2020, 19(1): 51.
12. Wang Shuo, Zhou Mu, Liu Zaiyi, et al. Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal, 2017, 40(40): 172-183.
13. Liu H, Cao H, Song E, et al. A cascaded dual-pathway residual network for lung nodule segmentation in CT images. Phys Med, 2019, 63: 112-121.
14. Cao H, Liu H, Song E, et al. Dual-branch residual network for lung nodule segmentation. Appl Soft Comput, 2020, 2020(86): 105934-105945.
15. Wu Wenhao, Gao Lei, Duan Huihong, et al. Segmentation of pulmonary nodules in CT images based on 3D-UNET combined with three-dimensional conditional random field optimization. Med Phys, 2020, 47(9): 4054-4063.
16. Meyer C R, Johnson T D, Mclennan G, et al. Evaluation of lung MDCT nodule annotation across radiologists and methods. Acad Radiol, 2006, 13(10): 1254-1265.
17. Wang Wenzhe, Feng Ruiwei, Chen Jintai, et al. Nodule-plus R-CNN and deep self-paced active learning for 3D instance segmentation of pulmonary nodules. IEEE Access, 2019, 7(99): 128796-128805.
18. Cai Linqin, Long Tao, Dai Yuhan, et al. Mask R-CNN-based detection and segmentation for pulmonary nodule 3D visualization diagnosis. IEEE Access, 2020, 8: 44400-44409.
19. Li Xiangxia, Li Bin, Liu Fang, et al. Segmentation of pulmonary nodules using a GMM fuzzy C-means algorithm. IEEE Access, 2020, 8(99): 37541-37556.
20. He K, Zhang X, Ren S, et al. Identity mappings in deep residual networks// European Conference on Computer Vision, Cham: Springer, 2016: 630-645.
21. Yu F, Koltun V. Multi-scale context aggregation by dilated convolutions// International Conference on Learning Representations, Computer Vision and Pattern Recognition. New York: Academic Press, 2015: 255.
22. Roy A G, Navab N, Wachinger C. Concurrent spatial and channel squeeze & excitation in fully convolutional networks//Medical Image Computing and Computer Assisted Intervention (MICCAI), Cham: Springer, 2018: 421-429.
23. Jiang J, Hu Y C, Liu C J, et al. Multiple resolution residually connected feature streams for automatic lung tumor segmentation from CT images. IEEE Trans Med Imaging, 2019, 38(1): 134-144.
24. Esteves T, Quelhas P, Mendonca A M, et al. Gradient convergence filters and a phase congruency approach for in vivo cell nuclei detection. Machine Vision Applications, 2012, 23(4): 623-638.
25. Dhara A K, Mukhopadhyay S, Das Gupta R, et al. Erratum to: a segmentation framework of pulmonary nodules in lung CT images. J Digit Imaging, 2016, 29(1): 148-148.
26. Song Jiangdian, Yang Caiyun, Fan Li, et al. Lung lesion extraction using a toboggan based growing automatic segmentation approach. IEEE Trans Med Imaging, 2016, 35(1): 337-353.

Journal of Biomedical Engineering

Segmentation of ground glass pulmonary nodules using full convolution residual network based on atrous spatial pyramid pooling structure and attention mechanism

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content