Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash 93 tok/s
Gemini 2.5 Pro 53 tok/s Pro
GPT-5 Medium 32 tok/s
GPT-5 High 30 tok/s Pro
GPT-4o 97 tok/s
GPT OSS 120B 473 tok/s Pro
Kimi K2 228 tok/s Pro
2000 character limit reached

Effect of latent space distribution on the segmentation of images with multiple annotations (2304.13476v1)

Published 26 Apr 2023 in cs.CV, cs.LG, and eess.IV

Abstract: We propose the Generalized Probabilistic U-Net, which extends the Probabilistic U-Net by allowing more general forms of the Gaussian distribution as the latent space distribution that can better approximate the uncertainty in the reference segmentations. We study the effect the choice of latent space distribution has on capturing the variation in the reference segmentations for lung tumors and white matter hyperintensities in the brain. We show that the choice of distribution affects the sample diversity of the predictions and their overlap with respect to the reference segmentations. We have made our implementation available at https://github.com/ishaanb92/GeneralizedProbabilisticUNet

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans. Medical Physics, 38(2):915–931, February 2011. ISSN 0094-2405. doi: 10.1118/1.3528204.
  2. Armen Der Kiureghian and Ove Ditlevsen. Aleatory or epistemic? Does it matter? Structural Safety, 31(2):105–112, March 2009. ISSN 0167-4730. doi: 10.1016/j.strusafe.2008.06.020.
  3. Ensemble learning for multi-layer networks. In M. Jordan, M. Kearns, and S. Solla, editors, Advances in Neural Information Processing Systems, volume 10, pages 395 – 401. MIT Press, 1997. URL https://proceedings.neurips.cc/paper/1997/file/e816c635cad85a60fabd6b97b03cbcc9-Paper.pdf.
  4. PHiSeg: Capturing Uncertainty in Medical Image Segmentation. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, Lecture Notes in Computer Science, pages 119–127. Springer International Publishing, 2019. ISBN 978-3-030-32245-8. doi: 10.1007/978-3-030-32245-8˙14.
  5. Generalized probabilistic u-net for medical image segementation. In Carole H. Sudre, Christian F. Baumgartner, Adrian Dalca, Chen Qin, Ryutaro Tanno, Koen Van Leemput, and William M. Wells III, editors, Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, pages 113–124, Cham, 2022. Springer Nature Switzerland. ISBN 978-3-031-16749-2. doi: 10.1007/978-3-031-16749-2˙11.
  6. Christopher M. Bishop. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag, 2006. ISBN:978-0-387-31073-2.
  7. Weight uncertainty in neural network. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37, pages 1613–1622. PMLR, 2015. URL https://proceedings.mlr.press/v37/blundell15.html.
  8. Exploring the Relationship Between Segmentation Uncertainty, Segmentation Performance and Inter-observer Variability with Probabilistic Networks. In Large-Scale Annotation of Biomedical Data and Expert Label Synthesis and Hardware Aware Learning for Medical Imaging and Computer Assisted Intervention, volume 11851, pages 51–60. Springer International Publishing, 2019. doi: 10.1007/978-3-030-33642-4˙6.
  9. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Maria Florina Balcan and Kilian Q. Weinberger, editors, Proceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 1050–1059. PMLR, 20–22 Jun 2016. URL https://proceedings.mlr.press/v48/gal16.html.
  10. Approximating the kullback leibler divergence between gaussian mixture models. In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP ’07, volume 4, pages IV–317–IV–320, 2007. doi: 10.1109/ICASSP.2007.366913.
  11. beta-VAE: Learning basic visual concepts with a constrained variational framework. In International Conference on Learning Representations, 2017. URL https://openreview.net/forum?id=Sy2fzU9gl.
  12. Supervised Uncertainty Quantification for Segmentation with Multiple Annotations. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, Lecture Notes in Computer Science, pages 137–145. Springer International Publishing, 2019. ISBN 978-3-030-32245-8. doi: 10.1007/978-3-030-32245-8˙16.
  13. Robust brain extraction across datasets and comparison with publicly available methods. IEEE Transactions on Medical Imaging, 30(9):1617–1634, 2011. doi: 10.1109/TMI.2011.2138152.
  14. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 448–456. PMLR, 2015. URL https://proceedings.mlr.press/v37/ioffe15.html.
  15. Categorical reparameterization with gumbel-softmax. In International Conference on Learning Representations, 2017. URL https://openreview.net/forum?id=rkE3y85ee.
  16. Improving Uncertainty Estimation in Convolutional Neural Networks Using Inter-rater Agreement. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, volume 11767, pages 540–548. Springer International Publishing, 2019. doi: 10.1007/978-3-030-32251-9˙59.
  17. Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, pages 1965–1972. International Joint Conferences on Artificial Intelligence Organization, August 2017. ISBN 978-0-9992411-0-3. doi: 10.24963/ijcai.2017/273.
  18. On the Effect of Inter-observer Variability for a Reliable Estimation of Uncertainty of Medical Image Segmentation. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2018, pages 682–690. Springer International Publishing, 2018. doi: 10.1007/978-3-030-00928-1˙77.
  19. Analyzing the Quality and Challenges of Uncertainty Estimations for Brain Tumor Segmentation. Frontiers in Neuroscience, 14, April 2020. ISSN 1662-453X. doi: 10.3389/fnins.2020.00282.
  20. Ensembles of multiple models and architectures for robust brain tumour segmentation. In Alessandro Crimi, Spyridon Bakas, Hugo Kuijf, Bjoern Menze, and Mauricio Reyes, editors, Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries, pages 450–462, Cham, 2018. Springer International Publishing. ISBN 978-3-319-75238-9. doi: 10.1007/978-3-319-75238-9˙38.
  21. What uncertainties do we need in bayesian deep learning for computer vision? In I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL https://proceedings.neurips.cc/paper/2017/file/2650d6089a6d640c5e85b2b88265dc2b-Paper.pdf.
  22. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations, 2015. URL https://hdl.handle.net/11245/1.505367.
  23. Auto-Encoding Variational Bayes. In International Conference on Learning Representations, 2014. URL https://hdl.handle.net/11245/1.434281.
  24. An Introduction to Variational Autoencoders. Foundations and Trends® in Machine Learning, 12(4):307–392, 2019. ISSN 1935-8237, 1935-8245. doi: 10.1561/2200000056.
  25. Variational Dropout and the Local Reparameterization Trick. In C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper/2015/hash/bc7316929fe1545bf0b98d114ee3ecb8-Abstract.html.
  26. Elastix : a toolbox for intensity-based medical image registration. IEEE Transactions on Medical Imaging, 29(1):196–205, 2010. ISSN 0278-0062. doi: 10.1109/TMI.2009.2035616.
  27. A Probabilistic U-Net for Segmentation of Ambiguous Images. In Advances in Neural Information Processing Systems, volume 31. Curran Associates, Inc., 2018. URL https://papers.nips.cc/paper/2018/hash/473447ac58e1cd7e96172575f48dca3b-Abstract.html.
  28. Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations on single cell data. PLOS Computational Biology, 17(6):e1009086, June 2021. ISSN 1553-7358. doi: 10.1371/journal.pcbi.1009086.
  29. Standardized assessment of automatic segmentation of white matter hyperintensities and results of the wmh segmentation challenge. IEEE Transactions on Medical Imaging, 38(11):2556–2568, 2019. doi: 10.1109/TMI.2019.2905770.
  30. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. In Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL https://proceedings.neurips.cc/paper/2017/file/9ef2ed4b7fd2c810847ffa5fa85bce38-Paper.pdf.
  31. The concrete distribution: A continuous relaxation of discrete random variables. In International Conference on Learning Representations, 2017. URL https://openreview.net/forum?id=S1jE5L5gl.
  32. Confidence calibration and predictive uncertainty estimation for deep medical image segmentation. IEEE Transactions on Medical Imaging, 39(12):3868–3878, 2020. doi: 10.1109/TMI.2020.3006437.
  33. Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty. In H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin, editors, Advances in Neural Information Processing Systems, volume 33, pages 12756–12767. Curran Associates, Inc., 2020. URL https://proceedings.neurips.cc/paper/2020/file/95f8d9901ca8878e291552f001f67692-Paper.pdf.
  34. Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché-Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 8024–8035. Curran Associates, Inc., 2019. URL https://papers.nips.cc/paper/2019/hash/bdbca288fee7f92f2bfa9f7012727740-Abstract.html.
  35. Variational inference with normalizing flows. In Francis Bach and David Blei, editors, Proceedings of the 32nd International Conference on Machine Learning, volume 37 of Proceedings of Machine Learning Research, pages 1530–1538. PMLR, 2015. URL https://proceedings.mlr.press/v37/rezende15.html.
  36. Stochastic backpropagation and approximate inference in deep generative models. In Eric P. Xing and Tony Jebara, editors, Proceedings of the 31st International Conference on Machine Learning, volume 32 of Proceedings of Machine Learning Research, pages 1278–1286. PMLR, 2014. URL https://proceedings.mlr.press/v32/rezende14.html.
  37. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, pages 234–241. Springer International Publishing, 2015. ISBN 978-3-319-24574-4. doi: 10.1007/978-3-319-24574-4˙28.
  38. Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 3611–3620, October 2017. doi: 10.1109/ICCV.2017.388.
  39. Uncertainty quantification in medical image segmentation with normalizing flows. In Mingxia Liu, Pingkun Yan, Chunfeng Lian, and Xiaohuan Cao, editors, Machine Learning in Medical Imaging, pages 80–90, Cham, 2020. Springer International Publishing. ISBN 978-3-030-59861-7. doi: 10.1007/978-3-030-59861-7˙9.
  40. Learning Structured Output Representation using Deep Conditional Generative Models. In Advances in Neural Information Processing Systems, volume 28. Curran Associates, Inc., 2015. URL https://proceedings.neurips.cc/paper/2015/file/8d55a249e6baa5c06772297520da2051-Paper.pdf.
  41. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15(56):1929–1958, 2014. URL http://jmlr.org/papers/v15/srivastava14a.html.
  42. Bayesian uncertainty estimation for batch normalized deep networks. In Jennifer Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning, volume 80 of Proceedings of Machine Learning Research, pages 4907–4916. PMLR, 2018. URL https://proceedings.mlr.press/v80/teye18a.html.
  43. Graphical Models, Exponential Families, and Variational Inference. Foundations and Trends® in Machine Learning, 1(1–2):1–305, 2007. ISSN 1935-8237, 1935-8245. doi: 10.1561/2200000001.
  44. Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks. Neurocomputing, 338:34 – 45, 2019. ISSN 0925-2312. doi: https://doi.org/10.1016/j.neucom.2019.01.103.
  45. Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Transactions on Medical Imaging, 23(7):903–921, July 2004. ISSN 1558-254X. doi: 10.1109/TMI.2004.828354.
  46. Peter M. Williams. Using neural networks to model conditional multivariate densities. Neural Comput., 8(4):843–854, may 1996. ISSN 0899-7667. doi: 10.1162/neco.1996.8.4.843.
Citations (5)
View on Semantic Scholar
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Summary

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

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

Follow-up Questions

We haven't generated follow-up questions for this paper yet.

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