Abstract
Analysis of the placenta is extremely useful for evaluating health risks of the mother and baby after delivery. In this paper, we tackle the problem of automatic morphological characterization of placentas, including the tasks of placenta image segmentation, umbilical cord insertion point localization, and maternal/fetal side classification. We curated an existing dataset consisting of around 1,000 placenta images taken at Northwestern Memorial Hospital, together with their pixel-level segmentation map. We propose a novel pipeline, PlacentaNet, which consists of three encoder-decoder convolutional neural networks with a shared encoder, to address these morphological characterization tasks by employing a transfer learning training strategy. We evaluated its effectiveness using the curated dataset as well as the pathology reports in the medical record. The system produced accurate morphological characterization, which enabled subsequent feature analysis of placentas. In particular, we show promising results for detection of retained placenta (i.e., incomplete placenta) and umbilical cord insertion type categorization, both of which may possess clinical impact.
This work was supported primarily by the Bill & Melinda Gates Foundation. The computation was support by the NVIDIA Corporation’s GPU Grant Program. Discussions with William Tony Parks have been helpful. Celeste Beck, Dolzodmaa Davaasuren, and Leigh A. Taylor assisted in dataset curation.
A. D. Gernand and J. Z. Wang have equal contributions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The numbers of fetal-side and maternal-side images are uneven because some of the collected images did not meet our image quality standard (e.g. disc occluded by irrelevant object such as scissors) and we had to discard them from the dataset. We plan to release our dataset in the future after substantial expansion.
References
Alansary, A., et al.: Fast fully automatic segmentation of the human placenta from motion corrupted MRI. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9901, pp. 589–597. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46723-8_68
Badrinarayanan, V., et al.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE T-PAMI 39(12), 2481–2495 (2017)
Benirschke, K., Burton, G.J., Baergen, R.N.: Pathology of the Human Placenta, 6th edn. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-23941-0
He, K., et al.: Deep residual learning for image recognition. In: The IEEE CVPR, pp. 770–778 (2016)
Khong, T.Y., et al.: Sampling and definitions of placental lesions: Amsterdam placental workshop group consensus statement. Archiv. Pathol. Lab. Med. 140(7), 698–713 (2016)
Kidron, D., et al.: Automated image analysis of placental villi and syncytial knots in histological sections. Placenta 53, 113–118 (2017)
Long, J., et al.: Fully convolutional networks for semantic segmentation. In: The IEEE CVPR, pp. 3431–3440 (2015)
Milletari, F., et al.: V-Net: fully convolutional neural networks for volumetric medical image segmentation. In: International Conference on 3D Vision (3DV), pp. 565–571. IEEE (2016)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 483–499. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46484-8_29
Pan, J., et al.: A survey on transfer learning. IEEE TKDE 22(10), 1345–1359 (2009)
Payer, C., et al.: Integrating spatial configuration into heatmap regression based cnns for landmark localization. Med. Image Anal. 54, 207–219 (2019)
Roberts, D.J., et al.: Placental pathology, a survival guide. Archiv. Pathol. Lab. Med. 132(4), 641–651 (2008)
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_28
Silver, R.: Abnormal placentation: placenta previa, vasa previa, and placenta accreta. Obstet. Gynecol. 126(3), 654–668 (2015)
Thomas, K.A., Sottile, M.J., Salafia, C.M.: Unsupervised segmentation for inflammation detection in histopathology images. In: Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D., Meunier, J. (eds.) ICISP 2010. LNCS, vol. 6134, pp. 541–549. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13681-8_63
Tompson, J., et al.: Joint training of a convolutional network and a graphical model for human pose estimation. In: NIPS, pp. 1799–1807 (2014)
Yampolsky, M., et al.: Centrality of the umbilical cord insertion in a human placenta influences the placental efficiency. Placenta 30(12), 1058–1064 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Y., Wu, C., Zhang, Z., Goldstein, J.A., Gernand, A.D., Wang, J.Z. (2019). PlacentaNet: Automatic Morphological Characterization of Placenta Photos with Deep Learning. In: Shen, D., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. MICCAI 2019. Lecture Notes in Computer Science(), vol 11764. Springer, Cham. https://doi.org/10.1007/978-3-030-32239-7_54
Download citation
DOI: https://doi.org/10.1007/978-3-030-32239-7_54
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32238-0
Online ISBN: 978-3-030-32239-7
eBook Packages: Computer ScienceComputer Science (R0)
