Advertisement

Automatic Nasopharyngeal Carcinoma Segmentation Using Fully Convolutional Networks with Auxiliary Paths on Dual-Modality PET-CT Images

  • Lijun Zhao
  • Zixiao Lu
  • Jun Jiang
  • Yujia Zhou
  • Yi Wu
  • Qianjin FengEmail author
Article
  • 17 Downloads

Abstract

Nasopharyngeal carcinoma (NPC) is prevalent in certain areas, such as South China, Southeast Asia, and the Middle East. Radiation therapy is the most efficient means to treat this malignant tumor. Positron emission tomography–computed tomography (PET-CT) is a suitable imaging technique to assess this disease. However, the large amount of data produced by numerous patients causes traditional manual delineation of tumor contour, a basic step for radiotherapy, to become time-consuming and labor-intensive. Thus, the demand for automatic and credible segmentation methods to alleviate the workload of radiologists is increasing. This paper presents a method that uses fully convolutional networks with auxiliary paths to achieve automatic segmentation of NPC on PET-CT images. This work is the first to segment NPC using dual-modality PET-CT images. This technique is identical to what is used in clinical practice and offers considerable convenience for subsequent radiotherapy. The deep supervision introduced by auxiliary paths can explicitly guide the training of lower layers, thus enabling these layers to learn more representative features and improve the discriminative capability of the model. Results of threefold cross-validation with a mean dice score of 87.47% demonstrate the efficiency and robustness of the proposed method. The method remarkably outperforms state-of-the-art methods in NPC segmentation. We also validated by experiments that the registration process among different subjects and the auxiliary paths strategy are considerably useful techniques for learning discriminative features and improving segmentation performance.

Keywords

Nasopharyngeal carcinoma Segmentation PET-CT Fully convolutional neural networks 

Notes

Funding information

This work was supported by the National Natural Science Foundation Joint Fund Key Support Project under Grant U1501256 and the Applied Science and Technology Research and Development Special Project in Guangdong Province (No. 2015B010131011).

References

  1. 1.
    Tang LL, Chen WQ, Xue WQ: Global trends in incidence and mortality of nasopharyngeal carcinoma. Cancer Lett 374(1):22–30, 2016CrossRefGoogle Scholar
  2. 2.
    Wu HB, Wang QS, Wang MF: Preliminary study of 11C-choline PET/CT for T staging of locally advanced nasopharyngeal carcinoma: comparison with 18F-FDG PET/CT. J Nucl Med 52(3):341–346, 2011CrossRefGoogle Scholar
  3. 3.
    Huang W, Chan KL, Zhou JY: Region-Based Nasopharyngeal Carcinoma Lesion Segmentation from MRI Using Clustering- and Classification-Based Methods with Learning. J Digit Imaging 26(3):472–482, 2013CrossRefGoogle Scholar
  4. 4.
    Han DF, Bayouth J, Song Q: Globally Optimal Tumor Segmentation in PET-CT Images: A Graph-Based Co-Segmentation Method. International Conference on Information Processing in Medical Imaging, 2011, pp 245–256Google Scholar
  5. 5.
    Song Q, Bai J, Han D: Optimal co-segmentation of tumor in PET-CT images with context information. IEEE Trans Med Imaging 32(9):1685–1697, 2013CrossRefGoogle Scholar
  6. 6.
    Ju W, Xiang D, Zhang B: Random Walk and Graph Cut for Co-Segmentation of Lung Tumor on PET-CT Images. IEEE Trans Image Process 24(12):5854–5867, 2015CrossRefGoogle Scholar
  7. 7.
    Éloïse C, Talbot H, Passat N: Automated 3D lymphoma lesion segmentation from PET/CT characteristic. IEEE International Symposium on Biomedical Imaging, 2017, pp 174–178Google Scholar
  8. 8.
    Wang Y, Zu C, Hu GL: Automatic Tumor Segmentation with Deep Convolutional Neural Networks for Radiotherapy Applications. Neural Process Lett 10:1–12, 2018Google Scholar
  9. 9.
    Tatanun C, Ritthipravat P, Bhongmakapat T: Automatic segmentation of nasopharyngeal carcinoma from CT images: Region growing based technique. 2010 2nd International Conference on Signal Processing System, 2010, pp 18–22Google Scholar
  10. 10.
    Chanapai W, Bhongmakapat T, Tuntiyatorn L: Nasopharyngeal carcinoma segmentation using a region growing technique. Int J Comput Assist Radiol Surg 7(3):413–422, 2012CrossRefGoogle Scholar
  11. 11.
    Huang KW, Zhao ZY, Gong Q: Nasopharyngeal carcinoma segmentation via HMRF-EM with maximum entropy. Eng Med Biol Soc:2968–2972, 2015Google Scholar
  12. 12.
    Fitton I, Cornelissen SA, Duppen JC: Semi-automatic delineation using weighted CT-MRI registered images for radiotherapy of nasopharyngeal cancer. Med Phys 38(8):4662–4666, 2011CrossRefGoogle Scholar
  13. 13.
    Wu PX, Khong PL, Chan T: Automatic detection and classification of nasopharyngeal carcinoma on PET/CT with support vector machine. Int J Comput Assist Radiol Surg 7(4):635–646, 2012CrossRefGoogle Scholar
  14. 14.
    Mohammed MA, Ghani MKA, Hamed RI: Artificial neural networks for automatic segmentation and identification of nasopharyngeal carcinoma. J Comput Sci 21:263–274, 2017CrossRefGoogle Scholar
  15. 15.
    Men K, Chen X, Zhang Y: Deep Deconvolutional Neural Network for Target Segmentation of Nasopharyngeal Cancer in Planning Computed Tomography Images. Front Oncol 7:315–323, 2017CrossRefGoogle Scholar
  16. 16.
    Ronneberger O, Fischer P, Brox T: U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, 2015, pp 234–241Google Scholar
  17. 17.
    Brosch T, Tang L, Yoo YJ: Deep 3D Convolutional Encoder Networks with Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation. IEEE Trans Med Imaging 35(5):1229–1239, 2016CrossRefGoogle Scholar
  18. 18.
    Milletari F, Navab N, Ahmadi S: V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. Fourth International Conference on 3d Vision, 2016, pp 565–571Google Scholar
  19. 19.
    Dong H, Yang G, Liu F D: Automatic Brain Tumor Detection and Segmentation Using U-Net Based Fully Convolutional Networks. Conference on Medical Image Understanding and Analysis, 2017, pp 506–517Google Scholar
  20. 20.
    Christ PF, Ettlinger F, Grün F: Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks. arXiv preprint (arXiv:1702.05970v2), 2017Google Scholar
  21. 21.
    Kamnitsas K, Ledig C, Newcombe VFJ: Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal 36:61–78, 2017CrossRefGoogle Scholar
  22. 22.
    Ioffe S, Szegedy C: Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on International Conference on Mach Learn, 2015, pp 448–456Google Scholar
  23. 23.
    Dou Q, Yu L, Chen H: 3D deeply supervised network for automated segmentation of volumetric medical images. Med Image Anal 41:40–54, 2017CrossRefGoogle Scholar
  24. 24.
    Tseng K L, Lin Y L, Hus W: Joint Sequence Learning and Cross-Modality Convolution for 3D Biomedical Segmentation. arXiv preprint (arXiv:1704.07754), 2017Google Scholar
  25. 25.
    Pereira S, Pinto A, Alves V: Brain Tumor Segmentation Using Convolutional Neural Networks in MRI Images. IEEE Trans Med Imaging 35(5):1240–1251, 2016CrossRefGoogle Scholar
  26. 26.
    He KM, Zhang XY, Ren SQ: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision, 2015, pp 1026–1034Google Scholar
  27. 27.
    Dice LR: Measures of the Amount of Ecologic Association Between Species. Ecology 26(3):297–302, 1945CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2019

Authors and Affiliations

  • Lijun Zhao
    • 1
  • Zixiao Lu
    • 1
  • Jun Jiang
    • 1
  • Yujia Zhou
    • 1
  • Yi Wu
    • 1
  • Qianjin Feng
    • 1
    Email author
  1. 1.School of Biomedical EngineeringSouthern Medical UniversityGuangzhouChina

Personalised recommendations