Automatic lesion segmentation and classification of hepatic echinococcosis using a multiscale-feature convolutional neural network

  • Shenghai Xin
  • Huabei Shi
  • A Jide
  • Mingyu Zhu
  • Cong Ma
  • Hongen LiaoEmail author
Original Article


Hepatic echinococcosis (HE) is a life-threatening liver disease caused by parasites that requires a precise diagnosis and proper treatments. To assess HE lesions accurately, we propose a novel automatic HE lesion segmentation and classification network that contains lesion region positioning (LRP) and lesion region segmenting (LRS) modules. First, we used the LRP module to obtain the probability map of the lesion distribution and the position of the lesion. Then, based on the result of the LRP module, we used the LRS module to precisely segment the HE lesions within the high-probability region. Finally, we classified the HE lesions and identified the lesion types by a convolutional neural network (CNN). The entire dataset was delineated by the hospital’s senior radiologist. We collected CT slices of 160 patients from Qinghai Provincial People’s Hospital. The Dice score of the final segmentation result reached 89.89%. The Dice scores, indicating the classification accuracy, for cystic vs. alveolar echinococcosis and calcified vs. noncalcified lesions were 80.32% and 82.45%, the sensitivities were 72.41% and 75.17%, the specificities were 83.72% and 86.04%, the NPVs were 80.01% and 86.96%, the PPVs were 80.45% and 81.74%, and the areas under the ROC curves were 0.8128 and 0.8205, respectively.

Graphical abstract


Hepatic echinococcosis Computed tomography Convolutional neural network Medical image segmentation Medical image classification 


Funding information

The authors would like to acknowledge the supports of National Natural Science Foundation of China (81771940, 81427803), National Key Research and Development Program of China (2017YFC0108000), and Beijing Municipal Natural Science Foundation (7172122, L172003).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

Human participants or animals

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Informed consent was obtained from all individual participants included in the study.


  1. 1.
    Czermak B, Akhan O, Hiemetzberger R, Zelger B, Vogel W, Jaschke W, Rieger M, Kim SY, Lim JH (2008) Echinococcosis of the liver. Abdom Imaging 33:133–143. CrossRefPubMedGoogle Scholar
  2. 2.
    Bhutania N, Kajal P (2018) Hepatic echinococcosis: a review. Annals of Medicine and Surgery 36:99–105. CrossRefGoogle Scholar
  3. 3.
    Moro P, Schantz PM (2009) Echinococcosis: a review. International Journal of Infectious Diseases 13:125–133. CrossRefPubMedPubMedCentralGoogle Scholar
  4. 4.
    Kammerer S (1993) Echinococcal disease. Infictious Disease Clinics of North America 7:605–618 Google Scholar
  5. 5.
    McManus DP, Zhang W, Li J, Bartley PB (2003) Echinococcosis. Lancet 362:1295–1304. CrossRefPubMedGoogle Scholar
  6. 6.
    Brunetti E, Kern P, Vuitton DA (2010) Writing panel for the WHO-IWGE, expert consensus for the diagnosis and treatment of cystic and alveolar echinococcosis in humans. Acta Trop 114(1):1–16. CrossRefPubMedGoogle Scholar
  7. 7.
    McManus DP, Gray DJ, Zhang W, Yang Y (2012) Diagnosis, treatment, and management of echinococcosis. BMJ 344:e3866. CrossRefPubMedGoogle Scholar
  8. 8.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444 CrossRefGoogle Scholar
  9. 9.
    Jia L, Fang C, Changcun P, Mingyu Z, Xinran Z, & Liwei Z (2018) A cascaded deep convolutional neural network for joint segmentation and genotype prediction of brainstem gliomas. IEEE Trans Biomed Eng 1-1. CrossRefGoogle Scholar
  10. 10.
    Chen F, Liu J, Zhao Z, Zhu M, & Liao H (2017) 3d feature-enhanced network for automatic femur segmentation. IEEE J Biomed Health Informatics 1-1. CrossRefGoogle Scholar
  11. 11.
    Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, pp 234–241. CrossRefGoogle Scholar
  12. 12.
    Hänsch A, Schwier M, Gass T, Morgas T, Haas B, Dicken V, Meine H, Klein J, Hahn HK (2019) Evaluation of deep learning methods for parotid gland segmentation from CT images. J Med Imaging 6(1):011005. CrossRefGoogle Scholar
  13. 13.
    Liu J, Chen F, Pan C, Zhu M, Zhang X, Zhang L, Liao H (2018) A cascaded deep convolutional neural network for joint segmentation and genotype prediction of brainstem gliomas. IEEE Trans Biomed Eng. CrossRefGoogle Scholar
  14. 14.
    Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, Lanczi L (2015) The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imaging 34(10):1993–2024. CrossRefGoogle Scholar
  15. 15.
    Dou Q, Chen H, Jin Y, Yu L, Qin J, Heng PA (2016) 3D deeply supervised network for automatic liver segmentation from CT volumes. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 149–157. CrossRefGoogle Scholar
  16. 16.
    Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118. CrossRefPubMedPubMedCentralGoogle Scholar
  17. 17.
    Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak J, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88. CrossRefPubMedGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2020

Authors and Affiliations

  1. 1.Department of Biomedical Engineering, School of MedicineTsinghua UniversityBeijingChina
  2. 2.Qinghai Provincial People’s HospitalXiningChina

Personalised recommendations