Deep learning to segment pelvic bones: large-scale CT datasets and baseline models

Abstract

Purpose:

Pelvic bone segmentation in CT has always been an essential step in clinical diagnosis and surgery planning of pelvic bone diseases. Existing methods for pelvic bone segmentation are either hand-crafted or semi-automatic and achieve limited accuracy when dealing with image appearance variations due to the multi-site domain shift, the presence of contrasted vessels, coprolith and chyme, bone fractures, low dose, metal artifacts, etc. Due to the lack of a large-scale pelvic CT dataset with annotations, deep learning methods are not fully explored.

Methods:

In this paper, we aim to bridge the data gap by curating a large pelvic CT dataset pooled from multiple sources, including 1184 CT volumes with a variety of appearance variations. Then, we propose for the first time, to the best of our knowledge, to learn a deep multi-class network for segmenting lumbar spine, sacrum, left hip, and right hip, from multiple-domain images simultaneously to obtain more effective and robust feature representations. Finally, we introduce a post-processor based on the signed distance function (SDF).

Results:

Extensive experiments on our dataset demonstrate the effectiveness of our automatic method, achieving an average Dice of 0.987 for a metal-free volume. SDF post-processor yields a decrease of 15.1% in Hausdorff distance compared with traditional post-processor.

Conclusion:

We believe this large-scale dataset will promote the development of the whole community and open source the images, annotations, codes, and trained baseline models at https://github.com/ICT-MIRACLE-lab/CTPelvic1K.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Availability of data and material

Please refer to https://github.com/ICT-MIRACLE-lab/CTPelvic1K.

Notes

  1. 1.

    https://en.wikipedia.org/wiki/Mimics.

  2. 2.

    https://github.com/mic-dkfz/nnunet.

  3. 3.

    https://monai.io/.

References

  1. 1.

    Aguirre-Ramos H, Avina-Cervantes JG, Cruz-Aceves I (2016) Automatic bone segmentation by a gaussian modeled threshold. In: AIP Conference Proceedings, vol. 1747, p. 090009. AIP Publishing LLC

  2. 2.

    Barratt RC, Bernard J, Mundy AR, Greenwell TJ (2018) Pelvic fracture urethral injury in males-mechanisms of injury, management options and outcomes. Trans Androl Urol 7(Suppl 1):S29

    Article  Google Scholar 

  3. 3.

    Bennett L, Zhoubing X, Juan Eugenio I, Martin S, Thomas Robin L, Arno K (2015) 2015 miccai multi-atlas labeling beyond the cranial vault – workshop and challenge. https://doi.org/10.7303/syn3193805

  4. 4.

    Chandar KP, Satyasavithri T (2016) Segmentation and 3d visualization of pelvic bone from CT scan images. In: IACC, pp. 430–433. IEEE

  5. 5.

    Chen C, Zheng G (2013) Fully automatic segmentation of AP pelvis x-rays via random forest regression and hierarchical sparse shape composition. In: International conference on computer analysis of images and patterns, pp. 335–343. Springer

  6. 6.

    Chen LC, Zhu Y, Papandreou G, Schroff F, Adam, H (2018) Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV, pp. 801–818

  7. 7.

    Çiçek Ö, Abdulkadir A, Lienkamp SS, Brox T, Ronneberger O (2016) 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: MICCAI, pp. 424–432. Springer

  8. 8.

    Ding F, Leow WK, Howe TS (2007) Automatic segmentation of femur bones in anterior-posterior pelvis x-ray images. In: International conference on computer analysis of images and patterns, pp. 205–212. Springer

  9. 9.

    Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K, Davidson B, Pereira SP, Clarkson MJ, Barratt DC (2018) Automatic multi-organ segmentation on abdominal CT with dense v-networks. IEEE Trans Med Imaging 37(8):1822–1834

    Article  Google Scholar 

  10. 10.

    Guo Q, Zhang L, Zhou S, Zhang Z, Liu H, Zhang L, Talmy T, Li Y (2020) Clinical features and risk factors for mortality in patients with open pelvic fracture: a retrospective study of 46 cases. J Orthop Surg 28(2):2309499020939830

    Article  Google Scholar 

  11. 11.

    Haas B, Coradi T, Scholz M, Kunz P, Huber M, Oppitz U, Andre L, Lengkeek V, Huyskens D, Van Esch A, Reddick R (2008) Automatic segmentation of thoracic and pelvic CT images for radiotherapy planning using implicit anatomic knowledge and organ-specific segmentation strategies. Phys Med Biol 53(6):1751

    CAS  Article  Google Scholar 

  12. 12.

    Heller N, Sathianathen N, Kalapara A, Walczak E, Moore K, Kaluzniak H, Rosenberg J, Blake P, Rengel Z, Oestreich M, Dean J, Tradewell M, Shah A, Tejpaul R, Edgerton Z, Peterson M, Raza S, Regmi S, Papanikolopoulos N, Weight C (2019) The kits19 challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes. arXiv:1904.00445

  13. 13.

    Hemke R, Buckless CG, Tsao A, Wang B, Torriani M (2020) Deep learning for automated segmentation of pelvic muscles, fat, and bone from CT studies for body composition assessment. Skelet Radiol 49(3):387–395

    Article  Google Scholar 

  14. 14.

    Isensee F, Jäger PF, Kohl SA, Petersen J, Maier-Hein KH (2019) Automated design of deep learning methods for biomedical image segmentation. arXiv preprint arXiv:1904.08128

  15. 15.

    Johnson CD, Chen MH, Toledano AY, Heiken JP, Dachman A, Kuo MD, Menias CO, Siewert B, Cheema JI, Obregon RG, Fidler JL, Zimmerman P, Horton KM, Coakley K, Iyer RB, Hara AK, Halvorsen RA, Casola G, Yee J, Herman BA, Burgart LJ, Limburg PJ (2008) Accuracy of CT colonography for detection of large adenomas and cancers. N. Engl J Med 359(12):1207–1217

    CAS  Article  Google Scholar 

  16. 16.

    Kainmueller D, Lamecker H, Zachow S, Hege H.C (2008) Coupling deformable models for multi-object segmentation. In: ISBI,. Springer, pp 69–78

  17. 17.

    Kotlarsky P, Haber R, Bialik V, Eidelman M (2015) Developmental dysplasia of the hip: What has changed in the last 20 years? World J Orthop 6(11):886

    Article  Google Scholar 

  18. 18.

    Lamecker H, Seebass M, Hege HC, Deuflhard P (2004) A 3D statistical shape model of the pelvic bone for segmentation. Int Soc Opt Photonics 5370:1341–1351

    Google Scholar 

  19. 19.

    Lee PY, Lai JY, Hu YS, Huang CY, Tsai YC, Ueng WD (2012) Virtual 3D planning of pelvic fracture reduction and implant placement. Biomed Eng Appl Basis Commun 24(03):245–262

    Article  Google Scholar 

  20. 20.

    Lindner C, Thiagarajah S, Wilkinson JM, Consortium a, Wallis GA, Cootes TF (2012) Accurate fully automatic femur segmentation in pelvic radiographs using regression voting. In: MICCAI, pp. 353–360. Springer

  21. 21.

    Lindner C, Thiagarajah S, Wilkinson JM, Wallis GA, Cootes TF (2013) Fully automatic segmentation of the proximal femur using random forest regression voting. IEEE Trans Med Imag 32(8):1462–1472

  22. 22.

    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR, pp. 3431–3440

  23. 23.

    Pasquier D, Lacornerie T, Vermandel M, Rousseau J, Lartigau E, Betrouni N (2007) Automatic segmentation of pelvic structures from magnetic resonance images for prostate cancer radiotherapy. Int J Radiati Oncol Biol Phys 68(2):592–600

  24. 24.

    Perera S, Barnes N, He X, Izadi S, Kohli P, Glocker B (2015) Motion segmentation of truncated signed distance function based volumetric surfaces. In: WACV, pp. 1046–1053. IEEE

  25. 25.

    Philbrick KA, Weston AD, Akkus Z, Kline TL, Korfiatis P, Sakinis T, Kostandy P, Boonrod A, Zeinoddini A, Takahashi N, Erickson BJ (2019) Ril-contour: a medical imaging dataset annotation tool for and with deep learning. Jf Digit Imaging 32(4):571–581

    Article  Google Scholar 

  26. 26.

    Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: MICCAI. Springer, pp 234–241

  27. 27.

    Seim H, Kainmueller D, Heller M, Lamecker H, Zachow S, Hege HC (2008) Automatic segmentation of the pelvic bones from CT data based on a statistical shape model. VCBM 8:93–100

    Google Scholar 

  28. 28.

    Simpson AL, Antonelli M, Bakas S, Bilello M, Farahani K, Van Ginneken B, Kopp-Schneider A, Landman BA, Litjens G, Menze B, Ronneberger O, Summers RM, Bilic P, Christ PF, Do RK, Gollub M, Golia-Pernicka J, Heckers SH, Jarnagin WR, McHugo MK, Napel S, Vorontsov E, Maier-Hein L, Cardoso MJ (2019) A large annotated medical image dataset for the development and evaluation of segmentation algorithms. arXiv:1902.09063

  29. 29.

    Truc PT, Lee S, Kim TS (2008) A density distance augmented chan-vese active contour for CT bone segmentation. In: International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 482–485. IEEE

  30. 30.

    Vasilache S, Ward K, Cockrell C, Ha J, Najarian K (2009) Unified wavelet and gaussian filtering for segmentation of CT images; application in segmentation of bone in pelvic CT images. BMC Med Inf Decis Mak 9(1):1–8

    Article  Google Scholar 

  31. 31.

    Wu J, Hargraves RH, Najarian K, Belle A, Ward KR (2016) Segmentation and fracture detection in CT images. US Patent 9,480,439

  32. 32.

    Yu H, Wang H, Shi Y, Xu K, Yu X, Cao Y (2018) The segmentation of bones in pelvic CT images based on extraction of key frames. BMC Med Imaging 18(1):18

    Article  Google Scholar 

  33. 33.

    Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: CVPR, pp. 2881–2890

  34. 34.

    Zhou SK, Greenspan H, Davatzikos C, Duncan JS, van Ginneken B, Madabhushi A, Prince JL, Rueckert D, Summers RM (2021) A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises. Proceedings of the IEEE

  35. 35.

    Zhou SK, Rueckert D, Fichtinger G (2019) Handbook of medical image computing and computer assisted intervention. Academic Press, Cambridge

    Google Scholar 

  36. 36.

    Zhou Y, Xie L, Fishman EK, Yuille AL (2017) Deep supervision for pancreatic cyst segmentation in abdominal CT scans. In: MICCAI, pp. 222–230. Springer

Download references

Funding

This research was supported in part by the Youth Innovation Promotion Association CAS (grant 2018135).

Author information

Affiliations

Authors

Corresponding author

Correspondence to S. Kevin Zhou.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Code availability

Please refer to https://github.com/ICT-MIRACLE-lab/CTPelvic1K.

Ethical approval

We have obtained the approval from the Ethics Committee of clinical hospital.

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

Verify currency and authenticity via CrossMark

Cite this article

Liu, P., Han, H., Du, Y. et al. Deep learning to segment pelvic bones: large-scale CT datasets and baseline models. Int J CARS 16, 749–756 (2021). https://doi.org/10.1007/s11548-021-02363-8

Download citation

Keywords

  • CT dataset
  • Pelvic segmentation
  • Deep learning
  • SDF post-processing