Skip to main content

Advertisement

SpringerLink
Log in

The Invasiveness Classification of Ground-Glass Nodules Using 3D Attention Network and HRCT

  • Original Paper
  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

The early stage lung cancer often appears as ground-glass nodules (GGNs). The diagnosis of GGN as preinvasive lesion (PIL) or invasive adenocarcinoma (IA) is very important for further treatment planning. This paper proposes an automatic GGNs’ invasiveness classification algorithm for the adenocarcinoma. 1431 clinical cases and a total of 1624 GGNs (3–30 mm) were collected from Shanghai Cancer Center for the study. The data is in high-resolution computed tomography (HRCT) format. Firstly, the automatic GGN detector which is composed by a 3D U-Net and a 3D multi-receptive field (multi-RF) network detects the location of GGNs. Then, a deep 3D convolutional neural network (3D-CNN) called Attention-v1 is used to identify the GGNs’ invasiveness. The attention mechanism was introduced to the 3D-CNN. This paper conducted a contract experiment to compare the performance of Attention-v1, ResNet, and random forest algorithm. ResNet is one of the most advanced convolutional neural network structures. The competition performance metrics (CPM) of automatic GGN detector reached 0.896. The accuracy, sensitivity, specificity, and area under curve (AUC) value of Attention-v1 structure are 85.2%, 83.7%, 86.3%, and 92.6%. The algorithm proposed in this paper outperforms ResNet and random forest in sensitivity, accuracy, and AUC value. The deep 3D-CNN’s classification result is better than traditional machine learning method. Attention mechanism improves 3D-CNN’s performance compared with the residual block. The automatic GGN detector with the addition of Attention-v1 can be used to construct the GGN invasiveness classification algorithm to help the patients and doctors in treatment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

References

  1. Qiu Z X, Cheng Y, Liu D, et al. Clinical, pathological, and radiological characteristics of solitary ground-glass opacity lung nodules on high-resolution computed tomography[J]. Ther Clin Risk Manag, 2016, 12: 1445.

    Article  Google Scholar 

  2. Shinohara S, Kuroda K, Shimokawa H, et al. Pleural dissemination of a mixed ground-glass opacity nodule treated as a nontuberculous mycobacterial infection for 6 years without growing remarkably[J]. J Thorac Dis, 2015, 7(9): E370.

    PubMed  PubMed Central  Google Scholar 

  3. Yamaguchi M, Furuya A, Edagawa M, et al. How should we manage small focal pure ground-glass opacity nodules on high-resolution computed tomography? A single institute experience[J]. Surg Oncol, 2015, 24(3): 258-263.

    Article  Google Scholar 

  4. Travis W D, Brambilla E, Noguchi M, et al. International association for the study of lung cancer/American thoracic society/European respiratory society international multidisciplinary classification of lung adenocarcinoma[J]. J Thorac Oncol, 2011, 6(2): 244-285.

    Article  Google Scholar 

  5. Hadji I, Wildes R P. What do we understand about convolutional networks?. arXiv preprint arXiv:1803.08834, 2018.

  6. Wang S, Wang R, Zhang S, et al. 3D convolutional neural network for differentiating pre-invasive lesions from invasive adenocarcinomas appearing as ground-glass nodules with diameters ≤3 cm using HRCT[J]. Quant Imaging Med Surg, 2018, 8(5): 491.

    Article  CAS  Google Scholar 

  7. Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[C]. Advances in neural information processing systems. 2015: 91-99.

    Google Scholar 

  8. Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 3431-3440.

    Google Scholar 

  9. Zhu W, Liu C, Fan W, et al. Deeplung: Deep 3d dual path nets for automated pulmonary nodule detection and classification[C]// 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2018: 673-681.

  10. 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. Springer, Cham, 2015: 234-241.

    Google Scholar 

  11. Dou Q , Chen H , Yu L , et al. Multi-level contextual 3D CNNs for False positive reduction in pulmonary nodule detection[J]. IEEE Trans Biomed Eng, 2016, PP(99):1-1.

    Google Scholar 

  12. Liu J, Li W, Huang Y, et al. Differential diagnosis of the MDCT features between lung adenocarcinoma preinvasive lesions and minimally invasive adenocarcinoma appearing as ground-glass nodules[J]. Zhonghua zhong liu za zhi [Chinese journal of oncology], 2015, 37(8): 611-616.

    Google Scholar 

  13. Hwang I, Park C M, Park S J, et al. Persistent pure ground-glass nodules larger than 5 mm: differentiation of invasive pulmonary adenocarcinomas from preinvasive lesions or minimally invasive adenocarcinomas using texture analysis[J]. Investig Radiol, 2015, 50(11): 798-804.

    Article  CAS  Google Scholar 

  14. Deng J, Dong W, Socher R, et al. Imagenet: A large-scale hierarchical image database[C]// 2009 IEEE conference on computer vision and pattern recognition. Ieee, 2009: 248-255.

  15. Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.

    Google Scholar 

  16. Wang F, Jiang M, Qian C, et al. Residual attention network for image classification[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 3156-3164.

    Google Scholar 

  17. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.

    Google Scholar 

  18. Lin T Y , Goyal P , Girshick R , et al. Focal loss for dense object detection[J]. IEEE Trans Pattern Anal Mach Intell, 2017, PP(99):2999-3007.

    Google Scholar 

  19. Gilbert C D, Wiesel T N. Receptive field dynamics in adult primary visual cortex[J]. Nature, 1992, 356(6365): 150-152.

    Article  CAS  Google Scholar 

  20. Itti L, Koch C. Computational modelling of visual attention[J]. Nat Rev Neurosci, 2001, 2(3): 194-203.

    Article  CAS  Google Scholar 

  21. Fu J, Liu J, Tian H, et al. Dual attention network for scene segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 3146-3154.

    Google Scholar 

  22. Anderson P, He X, Buehler C, et al. Bottom-up and top-down attention for image captioning and visual question answering[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 6077-6086.

    Google Scholar 

  23. Chang J S, Luo Y F, Su K Y. GPSM: a generaized probabilistic semantic model for ambiguity resolution[C]// Proceedings of the 30th annual meeting on Association for Computational Linguistics. Association for Computational Linguistics, 1992: 177-184.

  24. Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection[C]// Ijcai. 1995, 14(2): 1137-1145.

    Google Scholar 

  25. Ling C X, Huang J, Zhang H. AUC: a better measure than accuracy in comparing learning algorithms[C]// Conference of the Canadian society for computational studies of intelligence. Springer, Berlin, 2003: 329-341.

    Google Scholar 

  26. Armato S G, Mclennan G, Bidaut L, et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans [J]. Med Phys, 2011, 38(2): 915-931.

    Article  Google Scholar 

  27. Ding J , Li A , Hu Z , et al. Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks[J]. 2017.

    Book  Google Scholar 

  28. LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature, 2015, 521(7553): 436-444.

    Article  CAS  Google Scholar 

  29. Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.

    Article  Google Scholar 

  30. Lorensen W E, Cline H E. Marching cubes: A high resolution 3D surface construction algorithm[J]. ACM Siggraph Comput Graph, 1987, 21(4): 163-169.

    Article  Google Scholar 

  31. Tetko I V, Livingstone D J, Luik A I. Neural network studies. 1. Comparison of overfitting and overtraining[J]. J Chem Inf Comput Sci, 1995, 35(5): 826-833.

    Article  CAS  Google Scholar 

  32. Keskar N S, Mudigere D, Nocedal J, et al. On large-batch training for deep learning: generalization gap and sharp minima. In The International Conference on Learning Representations (ICLR), 2017.

Download references

Author information

Authors and Affiliations

  1. Laboratory for Medical Imaging Informatics, Shanghai Institute of Technical Physics, Chinese Academy of Science, Shanghai, 200083, China

    Yangfan Ni, Yuanyuan Yang, Dezhong Zheng & Zhe Xie

  2. University of Chinese Academy of Sciences, Beijing, 100049, China

    Yangfan Ni, Dezhong Zheng & Zhe Xie

  3. Department of Interventional Radiology, Fudan University Shanghai Cancer Center, Shanghai, 200032, China

    Haozhe Huang

  4. The General Hospital of the People’s Liberation Army, No. 28 Fuxing Road, Haidian District, Beijing, 100039, China

    Weidong Wang

Authors
  1. Yangfan Ni
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuanyuan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dezhong Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhe Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haozhe Huang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Weidong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Weidong Wang.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Statement

Ethical approval was obtained for this retrospective analysis, and informed consent requirement was waived.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ni, Y., Yang, Y., Zheng, D. et al. The Invasiveness Classification of Ground-Glass Nodules Using 3D Attention Network and HRCT. J Digit Imaging 33, 1144–1154 (2020). https://doi.org/10.1007/s10278-020-00355-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-020-00355-9

Keywords

Search

Navigation