Advertisement

Combining Deep Learning and Multi-atlas Label Fusion for Automated Placenta Segmentation from 3DUS

  • Baris U. Oguz
  • Jiancong Wang
  • Natalie Yushkevich
  • Alison Pouch
  • James Gee
  • Paul A. Yushkevich
  • Nadav Schwartz
  • Ipek Oguz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11076)

Abstract

In recent years there is growing interest in studying the placenta in vivo. However, 3D ultrasound images (3DUS) are typically very noisy, and the placenta shape and position are highly variable. As such, placental segmentation efforts to date have focused on interactive methods that require considerable user input, or automated methods with relatively low performance and various limitations. We propose a novel algorithm using a combination of deep learning and multi-atlas joint label fusion (JLF) methods for automated segmentation of the placenta in 3DUS images. We extract 2D cross-sections of the ultrasound cone beam with a variety of orientations from the 3DUS images and train a convolutional neural network (CNN) on these slices. We use the prediction by the CNN to initialize the multi-atlas JLF algorithm. The posteriors obtained by the CNN and JLF models are combined to enhance the overall segmentation performance. The method is evaluated on a dataset of 47 patients in the first trimester. We perform 4-fold cross-validation and achieve a mean Dice coefficient of \(86.3 \pm 5.3\) for the test folds. This is a substantial increase in accuracy compared to existing automated methods and is comparable to the performance of semi-automated methods currently considered the bronze standard in placenta segmentation.

Notes

Acknowledgments

This work was funded by the NICHD Human Placenta Project (U01 HD087180) and NIH grants R01 EB017255, R01 NS094456 and F32 HL119010.

References

  1. 1.
    Baptiste-Roberts, K., Salafia, C.M., Nicholson, W.K., Duggan, A., Wang, N.Y., Brancati, F.L.: Gross placental measures and childhood growth. J. Matern.-Fetal Neonatal Med. 22(1), 13–23 (2009)CrossRefGoogle Scholar
  2. 2.
    Barker, D.J., Bull, A.R., Osmond, C., Simmonds, S.J.: Fetal and placental size and risk of hypertension in adult life. BMJ 301(6746), 259–262 (1990)CrossRefGoogle Scholar
  3. 3.
    Biswas, S., Ghosh, S.K.: Gross morphological changes of placentas associated with intrauterine growth restriction of fetuses: a case control study. Early Hum. Dev. 84(6), 357–362 (2008)CrossRefGoogle Scholar
  4. 4.
    Collins, S.L., Stevenson, G.N., Noble, J.A., Impey, L.: Rapid calculation of standardized placental volume at 11 to 13 weeks and the prediction of small for gestational age babies. Ultrasound Med. Biol. 39(2), 253–260 (2013)CrossRefGoogle Scholar
  5. 5.
    Iglesias, J.E., Sabuncu, M.R.: Multi-atlas segmentation of biomedical images: a survey. Med. Image Anal. 24(1), 205–219 (2015)CrossRefGoogle Scholar
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 1097–1105 (2012)Google Scholar
  7. 7.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: IEEE CVPR, pp. 3431–3440 (2015)Google Scholar
  8. 8.
    Looney, P., et al.: Automatic 3D ultrasound segmentation of the first trimester placenta using deep learning. In: IEEE ISBI, pp. 279–282 (2017)Google Scholar
  9. 9.
    Looney, P., et al.: Fully automated, real-time 3D ultrasound segmentation to estimate first trimester placental volume using deep learning. JCI Insight (2018)Google Scholar
  10. 10.
    Oguz, I., et al.: Fully automated placenta segmentation from 3D ultrasound images. In: Perinatal, Preterm and Paediatric Image Analysis, PIPPI Workshop, MICCAI (2016)Google Scholar
  11. 11.
    Oguz, I., et al.: Semi-automated 3DUS placental volume measurements with minimal user interaction. The American Institute of Ultrasound in Medicine (2018)Google Scholar
  12. 12.
    Prasoon, A., Petersen, K., Igel, C., Lauze, F., Dam, E., Nielsen, M.: Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 246–253. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-40763-5_31CrossRefGoogle Scholar
  13. 13.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  14. 14.
    Schwartz, N., Quant, H.S., Sammel, M.D., Parry, S.: Macrosomia has its roots in early placental development. Placenta 35(9), 684–690 (2014)CrossRefGoogle Scholar
  15. 15.
    Schwartz, N., Wang, E., Parry, S.: Two-dimensional sonographic placental measurements in the prediction of small-for-gestational-age infants. Ultrasound Obstet. Gynecol. 40(6), 674–679 (2012)CrossRefGoogle Scholar
  16. 16.
    Schwartz, N., et al.: Placental volume measurements early in pregnancy predict adverse perinatal outcomes. Am. J. Obstet. Gynecol. 201(6), S142–S143 (2009)CrossRefGoogle Scholar
  17. 17.
    Stevenson, G.N., Collins, S.L., Ding, J., Impey, L., Noble, J.A.: 3-D ultrasound segmentation of the placenta using the random walker algorithm: reliability and agreement. Ultrasound Med. Biol. 41(12), 3182–3193 (2015)CrossRefGoogle Scholar
  18. 18.
    Wang, H., Yushkevich, P.: Multi-atlas segmentation with joint label fusion and corrective learning–an open source implementation. Front. in Neuroinf. 7, 27 (2013)Google Scholar
  19. 19.
    Yang, X., et al.: Towards automatic semantic segmentation in volumetric ultrasound. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10433, pp. 711–719. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66182-7_81CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Baris U. Oguz
    • 1
  • Jiancong Wang
    • 1
  • Natalie Yushkevich
    • 1
  • Alison Pouch
    • 1
  • James Gee
    • 1
  • Paul A. Yushkevich
    • 1
  • Nadav Schwartz
    • 2
  • Ipek Oguz
    • 1
  1. 1.Penn Image Computing and Science Laboratory (PICSL), Department of RadiologyUniversity of PennsylvaniaPhiladelphiaUSA
  2. 2.Maternal and Child Health Research Program, Department of OBGYNUniversity of PennsylvaniaPhiladelphiaUSA

Personalised recommendations