Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Shape-aware Segmentation of the Placenta in BOLD Fetal MRI Time Series (2312.05148v1)

Published 8 Dec 2023 in eess.IV and cs.CV

Abstract: Blood oxygen level dependent (BOLD) MRI time series with maternal hyperoxia can assess placental oxygenation and function. Measuring precise BOLD changes in the placenta requires accurate temporal placental segmentation and is confounded by fetal and maternal motion, contractions, and hyperoxia-induced intensity changes. Current BOLD placenta segmentation methods warp a manually annotated subject-specific template to the entire time series. However, as the placenta is a thin, elongated, and highly non-rigid organ subject to large deformations and obfuscated edges, existing work cannot accurately segment the placental shape, especially near boundaries. In this work, we propose a machine learning segmentation framework for placental BOLD MRI and apply it to segmenting each volume in a time series. We use a placental-boundary weighted loss formulation and perform a comprehensive evaluation across several popular segmentation objectives. Our model is trained and tested on a cohort of 91 subjects containing healthy fetuses, fetuses with fetal growth restriction, and mothers with high BMI. Biomedically, our model performs reliably in segmenting volumes in both normoxic and hyperoxic points in the BOLD time series. We further find that boundary-weighting increases placental segmentation performance by 8.3% and 6.0% Dice coefficient for the cross-entropy and signed distance transform objectives, respectively. Our code and trained model is available at https://github.com/mabulnaga/automatic-placenta-segmentation.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Spatiotemporal alignment of in utero BOLD-MRI series. Journal of Magnetic Resonance Imaging, 46(2):403–412, 2017.
  2. Placental MRI: Developing accurate quantitative measures of oxygenation. Topics in Magnetic Resonance Imaging, 28(5):285–297, 2019.
  3. Placental MRI: Effect of maternal position and uterine contractions on placental BOLD MRI measurements. Placenta, 95:69 – 77, 2020.
  4. Placental flattening via volumetric parameterization. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, pages 39–47, 2019.
  5. Volumetric parameterization of the placenta to a flattened template. IEEE Transactions on Medical Imaging, 41(4):925–936, 2022a.
  6. Automatic segmentation of the placenta in BOLD MRI time series. In MICCAI International Workshop on Preterm, Perinatal and Paediatric Image Analysis, pages 1–12. Springer Nature Switzerland, 2022b.
  7. Fast fully automatic segmentation of the human placenta from motion corrupted MRI. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 589–597. Springer, 2016.
  8. Voxelmorph: a learning framework for deformable medical image registration. IEEE transactions on medical imaging, 38(8):1788–1800, 2019.
  9. Distance map loss penalty term for semantic segmentation. arXiv preprint arXiv:1908.03679, 2019.
  10. Disentangle, align and fuse for multimodal and semi-supervised image segmentation. IEEE transactions on medical imaging, 40(3):781–792, 2020.
  11. Dynamic neural fields for learning atlases of 4d fetal mri time-series. arXiv preprint arXiv:2311.02874, 2023.
  12. Anystar: Domain randomized universal star-convex 3d instance segmentation. arXiv preprint arXiv:2307.07044, 2023.
  13. Synthstrip: skull-stripping for any brain image. NeuroImage, 260:119474, 2022.
  14. Dual-term loss function for shape-aware medical image segmentation. In 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), pages 1798–1802, 2021.
  15. A surprisingly effective perimeter-based loss for medical image segmentation. In Medical Imaging with Deep Learning, pages 158–167. PMLR, 2021.
  16. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Transactions on medical imaging, 39(2):499–513, 2019.
  17. Boundary loss for highly unbalanced segmentation. Medical image analysis, 67:101851, 2021.
  18. Focal loss for dense object detection. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2999–3007, 2017.
  19. In vivo quantification of placental insufficiency by BOLD MRI: a human study. Scientific Reports, 7(1):3713, 2017.
  20. Loss odyssey in medical image segmentation. Medical Image Analysis, 71:102035, 2021.
  21. Placenta maps: in utero placental health assessment of the human fetus. IEEE Transactions on Visualization and Computer Graphics, 23(6):1612–1623, 2017.
  22. V-net: Fully convolutional neural networks for volumetric medical image segmentation. 2016 Fourth International Conference on 3D Vision (3DV), pages 565–571, 2016.
  23. Star shape prior in fully convolutional networks for skin lesion segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 737–745. Springer, 2018.
  24. APPLAUSE: Automatic prediction of placental health via U-net segmentation and statistical evaluation. Medical Image Analysis, 72:102145, 2021. ISSN 1361-8415.
  25. Torchio: A python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Computer Methods and Programs in Biomedicine, 208:106236, 2021.
  26. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241, 2015.
  27. Automatic segmentation of twin regions in Mo-Di placentae based on geometric analysis of spatiotemporal BOLD MRI signals. In Proceedings of the International Society for Magnetic Resonance in Medicine, 2022.
  28. Reduced placental oxygenation during subclinical uterine contractions as assessed by BOLD MRI. Placenta, 39:16–20, 2016.
  29. Placental baseline conditions modulate the hyperoxic BOLD-MRI response. Placenta, 61:17–23, 2018.
  30. Changes in human fetal oxygenation during maternal hyperoxia as estimated by BOLD MRI. Prenatal Diagnosis, 33(2):141–145, 2013.
  31. Placental oxygen transport estimated by the hyperoxic placental BOLD MRI response. Physiological reports, 3(10):e12582, 2015.
  32. A bootstrap self-training method for sequence transfer: State-of-the-art placenta segmentation in fetal MRI. In Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Perinatal Imaging, Placental and Preterm Image Analysis, pages 189–199. Springer, 2021.
  33. T2* placental MRI in pregnancies complicated with fetal congenital heart disease. Placenta, 108:23–31, 2021.
  34. Fully automatic 3D reconstruction of the placenta and its peripheral vasculature in intrauterine fetal MRI. Medical image analysis, 54:263–279, 2019a.
  35. Segmentation and classification in mri and us fetal imaging: Recent trends and future prospects. Medical Image Analysis, 51:61–88, 2019b.
  36. Antsx: A dynamic ecosystem for quantitative biological and medical imaging. medRxiv, 2020.
  37. Deformable slice-to-volume registration for motion correction of fetal body and placenta MRI. IEEE transactions on medical imaging, 39(9):2750–2759, 2020.
  38. Slic-seg: slice-by-slice segmentation propagation of the placenta in fetal mri using one-plane scribbles and online learning. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 29–37. Springer, 2015.
  39. Deepatlas: Joint semi-supervised learning of image registration and segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22, pages 420–429. Springer, 2019.
  40. Robust motion correction and outlier rejection of in vivo functional MR images of the fetal brain and placenta during maternal hyperoxia. In SPIE Medical Imaging, volume 9417, pages 177–189. SPIE, 2015.
  41. Hemodynamic responses of the placenta and brain to maternal hyperoxia in fetuses with congenital heart disease by using blood oxygen–level dependent MRI. Radiology, 294(1):141–148, 2020.
  42. Supervision by denoising. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  43. Deep active contour network for medical image segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part IV 23, pages 321–331. Springer, 2020.
  44. Data augmentation using learned transformations for one-shot medical image segmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8543–8553, 2019.
Citations (3)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now