Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 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

Quantifying Topology In Pancreatic Tubular Networks From Live Imaging 3D Microscopy (2105.09737v2)

Published 20 May 2021 in cs.CV and cs.LG

Abstract: Motivated by the challenging segmentation task of pancreatic tubular networks, this paper tackles two commonly encountered problems in biomedical imaging: Topological consistency of the segmentation, and expensive or difficult annotation. Our contributions are the following: a) We propose a topological score which measures both topological and geometric consistency between the predicted and ground truth segmentations, applied to model selection and validation. b) We provide a full deep-learning methodology for this difficult noisy task on time-series image data. In our method, we first use a semisupervised U-net architecture, applicable to generic segmentation tasks, which jointly trains an autoencoder and a segmentation network. We then use tracking of loops over time to further improve the predicted topology. This semi-supervised approach allows us to utilize unannotated data to learn feature representations that generalize to test data with high variability, in spite of our annotated training data having very limited variation. Our contributions are validated on a challenging segmentation task, locating tubular structures in the fetal pancreas from noisy live imaging confocal microscopy. We show that our semi-supervised model outperforms not only fully supervised and pre-trained models but also an approach which takes topological consistency into account during training. Further, our approach achieves a mean loop score of 0.808 for detecting loops in the fetal pancreas, compared to a U-net trained with clDice with mean loop score 0.762.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. soft-matter/trackpy: Trackpy v0.5.0, April 2021. URL https://doi.org/10.5281/zenodo.4682814.
  2. Skeletonization via local separators. arXiv preprint arXiv:2007.03483, 2020.
  3. Feedback control of growth, differentiation, and morphogenesis of pancreatic endocrine progenitors in an epithelial plexus niche. Genes & development, 29(20):2203–2216, 2015.
  4. Fusing unsupervised and supervised deep learning for white matter lesion segmentation. In International Conference on Medical Imaging with Deep Learning, pages 63–72, 2019.
  5. Curriculum learning. In Proceedings of the 26th annual international conference on machine learning, pages 41–48, 2009.
  6. Andreas Bærentzen and et al. The GEL library. http://www2.compute.dtu.dk/projects/GEL/, 2020.
  7. Semi-supervised semantic segmentation with cross pseudo supervision. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2613–2622, 2021.
  8. 3d u-net: learning dense volumetric segmentation from sparse annotation. In International conference on medical image computing and computer-assisted intervention, pages 424–432. Springer, 2016.
  9. A topological loss function for deep-learning based image segmentation using persistent homology. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
  10. Semi-supervised brain lesion segmentation with an adapted mean teacher model. In International Conference on Information Processing in Medical Imaging, pages 554–565. Springer, 2019.
  11. Semi-supervised semantic segmentation via dynamic self-training and classbalanced curriculum. arXiv preprint arXiv:2004.08514, 1(2):5, 2020.
  12. Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Lab.(LANL), Los Alamos, NM (United States), 2008.
  13. Rethinking imagenet pre-training. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4918–4927, 2019.
  14. Topology-preserving deep image segmentation. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 5658–5669, 2019.
  15. Topology-aware segmentation using discrete morse theory. In International Conference on Learning Representations, 2020.
  16. Adversarial learning for semi-supervised semantic segmentation. arXiv preprint arXiv:1802.07934, 2018.
  17. Cdc42-mediated tubulogenesis controls cell specification. Cell, 139(4):791–801, 2009.
  18. Tetris: Template transformer networks for image segmentation with shape priors. IEEE Transactions on Medical Imaging, 38(11):2596–2606, 2019. doi: 10.1109/TMI.2019.2905990.
  19. Precise segmentation of densely interweaving neuron clusters using g-cut. Nature communications, 10(1):1–12, 2019.
  20. Hota: A higher order metric for evaluating multi-object tracking. International journal of computer vision, 129(2):548–578, 2021.
  21. Semi-supervised semantic segmentation with high-and low-level consistency. IEEE transactions on pattern analysis and machine intelligence, 2019.
  22. Andriy Myronenko. 3d mri brain tumor segmentation using autoencoder regularization. In International MICCAI Brainlesion Workshop, pages 311–320. Springer, 2018.
  23. Anatomically constrained neural networks (acnns): Application to cardiac image enhancement and segmentation. IEEE Transactions on Medical Imaging, 37(2):384–395, 2018. doi: 10.1109/TMI.2017.2743464.
  24. Semi-supervised semantic segmentation with cross-consistency training. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12674–12684, 2020.
  25. Cardiac segmentation with strong anatomical guarantees. IEEE Transactions on Medical Imaging, 39(11):3703–3713, 2020. doi: 10.1109/TMI.2020.3003240.
  26. Pancreas organogenesis: from bud to plexus to gland. Developmental Dynamics, 240(3):530–565, 2011.
  27. Airwaynet: A voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 212–220. Springer, 2019.
  28. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015.
  29. cldice-a novel topology-preserving loss function for tubular structure segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16560–16569, 2021.
  30. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv preprint arXiv:1703.01780, 2017.
  31. Epithelial dynamics of pancreatic branching morphogenesis. Development, 137(24):4295–4305, 2010.
  32. Topogan: A topology-aware generative adversarial network. In European Conference on Computer Vision, volume 2, 2020a.
  33. Deep distance transform for tubular structure segmentation in ct scans. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 3833–3842, 2020b.
  34. Attention guided network for retinal image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 797–805. Springer, 2019.
  35. Deep adversarial networks for biomedical image segmentation utilizing unannotated images. In International conference on medical image computing and computer-assisted intervention, pages 408–416. Springer, 2017.
  36. Rethinking pre-training and self-training. arXiv preprint arXiv:2006.06882, 2020.
Citations (2)
View on Semantic Scholar

Summary

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

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