Skip to main content
SpringerLink
Log in

An automatic cascaded approach for pancreas segmentation via an unsupervised localization using 3D CT volumes

  • Regular Paper
  • Published:
Multimedia Systems Aims and scope Submit manuscript

Abstract

Automatic organ segmentation using computed tomography (CT) images can support radiologists while carrying out quantitative and qualitative analyses of various types of cancer in their early stages. This work is aimed at automating the segmentation of the pancreas using CT images, which would ultimately aid in the early detection of pancreatic cancer. The pancreas is a small and challenging organ for automatic segmentation due to its variability in shape, size, and position. The state-of-the-art convolution neural networks (CNNs) based approaches have reported acceptable outcomes for stable large organs, but limited results for small organs like the pancreas. Although CNNs based results are promising, they utilized the supervised approach for localization, which required annotations. Hence, to avoid the need for annotations during localization, a novel unsupervised localization approach is proposed. The proposed approach localizes the pancreas from 3D CT volume using the spatial locations of stable large organs such as the liver and spleen. However, their spatial locations are detected in an unsupervised way. Furthermore, a 2D multi-view fusion deep learning model is used to extract the boundaries of the pancreas using the small bounding box around the pancreas region. The segmentation results are very encouraging and motivating to use an unsupervised localization approach instead of a supervised approach. A large number of experiments are performed using the NIH-82 CT dataset, which reveals that the proposed localization approach can achieve good segmentation results.

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

Similar content being viewed by others

Notes

  1. https://keras.io/.

References

  1. Ghaneh, P., et al.: Biology and management of pancreatic cancer. Gut 56(8), 1134–52 (2007). https://doi.org/10.1136/gut.2006.103333

    Article  Google Scholar 

  2. Sung, H., et al.: Global Cancer Statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA A Cancer J Clin 71(3), 209–249 (2021). https://doi.org/10.3322/caac.21660

    Article  Google Scholar 

  3. Prevedello, L.M., et al.: Challenges related to artificial intelligence research in medical imaging and the importance of image analysis competitions. Radiol Artif Intell 1(1), e180031 (2019)

    Article  Google Scholar 

  4. Kobatake, Hidefumi: Future CAD in multi-dimensional medical images-project on multi-organ, multi-disease CAD system. Comput Med Imaging Graph 31(4–5), 258–66 (2007). https://doi.org/10.1016/j.compmedimag.2007.02.016

    Article  Google Scholar 

  5. Takahashi, N.: Pancreas computed tomography. In: Hamm, B., Ros, P.R. (eds.) Abdominal imaging. Springer, Berlin, Heidelberg (2013). https://doi.org/10.1007/978-3-642-13327-5_186

    Chapter  Google Scholar 

  6. Farag, A., et al.: A bottom–up approach for pancreas segmentation using cascaded superpixels and (deep) image patch labeling. IEEE Trans Image Process 26(1), 386–399 (2016)

    Article  MathSciNet  MATH  Google Scholar 

  7. Erdt, M, et al.: Automatic pancreas segmentation in contrast enhanced CT data using learned spatial anatomy and texture descriptors. In: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro. IEEE, (2011)

  8. Shimizu, A.: Pancreas segmentation in three-phase abdominal CT volume data. Int J Comput Assist Rad Surg 3, s393–s394 (2008)

    Google Scholar 

  9. Shimizu, A., et al.: Automated pancreas segmentation from three-dimensional contrast-enhanced computed tomography. Int J Comput Assist Radiol Surg 5(1), 85–98 (2010)

    Article  Google Scholar 

  10. Krizhevsky, Alex, Sutskever, Ilya, Hinton, Geoffrey E.: Imagenet classification with deep convolutional neural networks. Commun ACM 60(6), 84–90 (2017)

    Article  Google Scholar 

  11. He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2016)

  12. Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2015)

  13. Chen, L.-C., et al.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2017)

    Article  Google Scholar 

  14. Fang, Y., et al.: 3d deep shape descriptor. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)

  15. Li, Xiaomeng, et al.: H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE transactions on medical imaging 37(12), 2663–2674 (2018)

    Article  Google Scholar 

  16. Wenjian, Q., et al.: Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation. Phys. Med. Biol. 63(9), 095017 (2018)

    Article  Google Scholar 

  17. Ngo, T.A., Lu, Z., Carneiro, G.: Combining deep learning and level set for the automated segmentation of the left ventricle of the heart from cardiac cine magnetic resonance. Med. Image Anal. 35, 159–171 (2017)

    Article  Google Scholar 

  18. Park, J., et al.: Fully automated lung lobe segmentation in volumetric chest CT with 3D U-Net: validation with intra-and extra-datasets. J. Dig. imaging 33(1), 221–230 (2020)

    Article  Google Scholar 

  19. Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2014)

  20. Heinrich, M.P., Oktay, O.: BRIEFnet: deep pancreas segmentation using binary sparse convolutions. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham (2017)

  21. Roth, H. R., et al.: Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation. Med. Image Anal. 45, 94–107 (2018)

    Article  Google Scholar 

  22. Jain, S., Gupta, S., Gulati, A.: An adaptive hybrid technique for pancreas segmentation using CT image sequences. In: 2015 International Conference on Signal Processing, Computing and Control (ISPCC). IEEE, (2015)

  23. Liu, X., et al.: Organ pose distribution model and an MAP framework for automated abdominal multi-organ localization. In: International Workshop on Medical Imaging and Virtual Reality. Springer, Berlin, Heidelberg (2010)

  24. Huang, M.-L., Yi-Zhen, W.: Semantic segmentation of pancreatic medical images by using convolutional neural network. Biomed. Signal Process. Control 73, 103458 (2022)

    Article  Google Scholar 

  25. Li, M., Lian, F., Guo, S.: Multi-scale selection and multi-channel fusion model for pancreas segmentation using adversarial deep convolutional nets. J. Dig. Imaging 35(1), 47–55 (2022)

    Article  Google Scholar 

  26. Li, J., et al.: Pancreas segmentation with probabilistic map guided bi-directional recurrent UNet. Phys. Med. Biol. 66(11), 115010 (2021)

    Article  Google Scholar 

  27. Oda, Masahiro., et al.: “Regression forest-based atlas localization and direction specific atlas generation for pancreas segmentation.” International conference on medical image computing and computer-assisted intervention. Springer, Cham, (2016)

  28. Zhu, Z., et al. A 3d coarse-to-fine framework for automatic pancreas segmentation. arXiv preprint arXiv:1712.00201 2 (2017)

  29. Roth, H. R., et al.: An application of cascaded 3D fully convolutional networks for medical image segmentation. Comput. Med. Imaging Graph. 66, 90–99 (2018)

    Article  Google Scholar 

  30. Zhao, N., et al.: Fully automated pancreas segmentation with two-stage 3D convolutional neural networks. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, (2019)

  31. Xue, J., et al.: Cascaded multitask 3-D fully convolutional networks for pancreas segmentation. IEEE Trans. Cybern. 51(4), 2153–2165 (2019)

    Article  Google Scholar 

  32. Tian, M., et al.: MCMC guided CNN training and segmentation for pancreas extraction. IEEE Access 9, 90539–90554 (2021)

    Article  Google Scholar 

  33. Zheng, H., et al.: Improving the slice interaction of 2.5 D CNN for automatic pancreas segmentation. Med. Phys. 47(11), 5543–5554 (2020)

    Article  Google Scholar 

  34. Karasawa, K., et al.: Pancreas segmentation from 3D abdominal CT images using patient-specific weighted subspatial probabilistic atlases. In: Medical Imaging 2015: Image Processing. Vol. 9413. SPIE (2015)

  35. Karasawa, K., et al.: Multi-atlas pancreas segmentation: atlas selection based on vessel structure. Med Image Anal 39, 18–28 (2017)

    Article  Google Scholar 

  36. Zhang, L., et al.: An improved method for pancreas segmentation using SLIC and interactive region merging. In: Medical Imaging 2017: Computer-Aided Diagnosis. Vol. 10134. SPIE (2017)

  37. Zhang, Y., et al.: A deep learning framework for pancreas segmentation with multi-atlas registration and 3D level-set. Med. Image Anal. 68, 101884 (2021)

    Article  Google Scholar 

  38. Qiu, C., et al.: Pancreas segmentation based on an optimized coarse-to-fine method. In: 2020 International Conference on Internet of Things and Intelligent Applications (ITIA). IEEE (2020)

  39. Hu, P., et al.: Automatic pancreas segmentation in CT images with distance-based saliency-aware DenseASPP network. IEEE J. Biomed. Health Inform. 25(5), 1601–1611 (2020)

    Article  Google Scholar 

  40. Dogan, R. O., et al.: A two-phase approach using mask R-CNN and 3D U-Net for high-accuracy automatic segmentation of pancreas in CT imaging. Comput. Methods Prog. Biomed. 207, 106141 (2021)

    Article  Google Scholar 

  41. Chen, H., Liu, Y., Shi, Z.: FPF-Net: feature propagation and fusion based on attention mechanism for pancreas segmentation. In: Multimedia systems, pp 1–14 (2022)

  42. Liu, Z., et al.: Pancreas co-segmentation based on dynamic ROI extraction and VGGU-Net. Expert Syst. Appl. 192, 116444 (2022)

    Article  Google Scholar 

  43. Chen, H., et al.: Pancreas segmentation by two-view feature learning and multi-scale supervision. Biomed. Signal Process. Control 74, 103519 (2022)

    Article  Google Scholar 

  44. Zhang, Dingwen, et al.: Automatic pancreas segmentation based on lightweight DCNN modules and spatial prior propagation. Pattern Recogn. 114, 107762 (2021)

    Article  Google Scholar 

  45. Huang, Q., et al.: Fully automatic liver segmentation in CT images using modified graph cuts and feature detection. Comput. Biol. med. 95, 198–208 (2018)

    Article  Google Scholar 

  46. Roth, H. R., et al.: Deeporgan: Multi-level deep convolutional networks for automated pancreas segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham (2015)

  47. Roth, H., et al.: Data from pancreas-CT. The cancer imaging archive (2016)’

  48. Clark, K., et al.: The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J. Dig. imaging 26(6), 1045–1057 (2013)

    Article  Google Scholar 

  49. Landman, B., et al.: Miccai multi-atlas labeling beyond the cranial vault” workshop and challenge. In: Proc. MICCAI Multi-Atlas Labeling Beyond Cranial Vault-Workshop Challenge. Vol 5 (2015)

  50. Nakaguchi, T., et al.: Pancreas extraction using a deformable model on abdominal CT image. In: International workshop on nonlinear circuits and signal processing (2004)

  51. Okada, T., et al. : Abdominal multi-organ CT segmentation using organ correlation graph and prediction-based shape and location priors. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Berlin, Heidelberg (2013)

  52. Ronneberger, O., Fischer, P., Brox, T: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, (2015)

  53. Xie, S., Tu, Z.: Holistically-nested edge detection. In: Proceedings of the IEEE international conference on computer vision (2015)

  54. Chen, L., et al.: DRINet for medical image segmentation. IEEE Trans. Med. Imaging 37(11), 2453–2462 (2018)

    Article  Google Scholar 

  55. Dice, Lee R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)

    Article  Google Scholar 

  56. Kingma, D. P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)

  57. Man, Y., et al.: Deep Q learning driven CT pancreas segmentation with geometry-aware U-Net. IEEE Trans. Med. Imaging 38(8), 1971–1980 (2019)

    Article  Google Scholar 

  58. Li, J., Chen, T., Qian, X.: Generalizable pancreas segmentation modeling in CT imaging via meta-learning and latent-space feature flow generation. IEEE J. Biomed. Health Inform. (2022). https://doi.org/10.1109/JBHI.2022.3207597

    Article  Google Scholar 

  59. Khosravan, N., et al.: Pan: projective adversarial network for medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention-MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13-17, 2019, Proceedings, Part VI 22. Springer International Publishing (2019)

  60. Li, J., et al.: A 2.5 D semantic segmentation of the pancreas using attention guided dual context embedded U-Net. Neurocomputing 480, 14–26 (2022)

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Dr. B.R. Ambedkar National Institute of Engineering and Technology, Jalandhar for funding to complete the work.

Author information

Author notes

  1. Suchi Jain, Geeta Sikka and Rehu Dhir have contributed equally to this work.

Authors and Affiliations

  1. Computer Science and Engineering Department, Dr. B.R. Ambedkar National Institute of Technology, Jalandhar, Punjab, 144011, India

    Suchi Jain & Renu Dhir

  2. Computer Science and Engineering Department, National Institute of Technology, Delhi, 110036, India

    Geeta Sikka

Authors
  1. Suchi Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Geeta Sikka
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Renu Dhir
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Suchi Jain.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jain, S., Sikka, G. & Dhir, R. An automatic cascaded approach for pancreas segmentation via an unsupervised localization using 3D CT volumes. Multimedia Systems 29, 2337–2349 (2023). https://doi.org/10.1007/s00530-023-01115-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00530-023-01115-9

Keywords

Search

Navigation