Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Semi-weakly-supervised neural network training for medical image registration (2402.10728v1)

Published 16 Feb 2024 in eess.IV and cs.CV

Abstract: For training registration networks, weak supervision from segmented corresponding regions-of-interest (ROIs) have been proven effective for (a) supplementing unsupervised methods, and (b) being used independently in registration tasks in which unsupervised losses are unavailable or ineffective. This correspondence-informing supervision entails cost in annotation that requires significant specialised effort. This paper describes a semi-weakly-supervised registration pipeline that improves the model performance, when only a small corresponding-ROI-labelled dataset is available, by exploiting unlabelled image pairs. We examine two types of augmentation methods by perturbation on network weights and image resampling, such that consistency-based unsupervised losses can be applied on unlabelled data. The novel WarpDDF and RegCut approaches are proposed to allow commutative perturbation between an image pair and the predicted spatial transformation (i.e. respective input and output of registration networks), distinct from existing perturbation methods for classification or segmentation. Experiments using 589 male pelvic MR images, labelled with eight anatomical ROIs, show the improvement in registration performance and the ablated contributions from the individual strategies. Furthermore, this study attempts to construct one of the first computational atlases for pelvic structures, enabled by registering inter-subject MRs, and quantifies the significant differences due to the proposed semi-weak supervision with a discussion on the potential clinical use of example atlas-derived statistics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. “Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration” In Neuroimage 46.3 Elsevier, 2009, pp. 786–802
  2. “Longitudinal image registration with temporal-order and subject-specificity discrimination” In International Conference on Medical Image Computing and Computer-Assisted Intervention, 2020 Springer
  3. “MR to ultrasound registration for image-guided prostate interventions” In Medical image analysis 16.3 Elsevier, 2012, pp. 687–703
  4. Grant Haskins, Uwe Kruger and Pingkun Yan “Deep learning in medical image registration: a survey” In Machine Vision and Applications 31 Springer, 2020, pp. 1–18
  5. “Deep learning in medical image registration: a review” In Physics in Medicine & Biology 65.20 IOP Publishing, 2020, pp. 20TR01
  6. Nicholas J Tustison, Brian B Avants and James C Gee “Learning image-based spatial transformations via convolutional neural networks: A review” In Magnetic resonance imaging 64 Elsevier, 2019, pp. 142–153
  7. “Neurreg: Neural registration and its application to image segmentation” In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2020
  8. “Weakly-supervised convolutional neural networks for multimodal image registration” In Medical image analysis 49 Elsevier, 2018, pp. 1–13
  9. “Label-driven weakly-supervised learning for multimodal deformable image registration” In 2018 IEEE 15th International Symposium on Biomedical Imaging, 2018 IEEE
  10. “Enhancing label-driven deep deformable image registration with local distance metrics for state-of-the-art cardiac motion tracking” In Bildverarbeitung für die Medizin 2019 Springer, 2019, pp. 309–314
  11. “MONAI: An open-source framework for deep learning in healthcare” In arXiv preprint arXiv:2211.02701, 2022
  12. Yipeng Hu “Registration of magnetic resonance and ultrasound images for guiding prostate cancer interventions”, 2013
  13. “On the opportunities and risks of foundation models” In arXiv preprint arXiv:2108.07258, 2021
  14. “Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision” In arXiv preprint arXiv:2310.18689, 2023
  15. “Visual Foundation Models for Medical Image Analysis”, 2023
  16. “A foundation model for generalizable disease detection from retinal images” In Nature Nature Publishing Group UK London, 2023, pp. 1–8
  17. Gary E Christensen, Richard D Rabbitt and Michael I Miller “3D brain mapping using a deformable neuroanatomy” In Physics in Medicine & Biology 39.3 IOP Publishing, 1994, pp. 609
  18. Rainer Sprengel, Karl Rohr and H Siegfried Stiehl “Thin-plate spline approximation for image registration” In Proceedings of 18th annual international conference of the IEEE Engineering in Medicine and Biology Society 3, 1996 IEEE
  19. Paul Viola and William M Wells III “Alignment by maximization of mutual information” In International journal of computer vision 24.2 Springer, 1997, pp. 137–154
  20. J-P Thirion “Image matching as a diffusion process: an analogy with Maxwell’s demons” In Medical image analysis 2.3 Elsevier, 1998, pp. 243–260
  21. John Ashburner and Karl J Friston “Nonlinear spatial normalization using basis functions” In Human brain mapping 7.4 Wiley Online Library, 1999, pp. 254–266
  22. “Nonrigid registration using free-form deformations: application to breast MR images” In IEEE transactions on medical imaging 18.8 IEEE, 1999, pp. 712–721
  23. Smadar Gefen, Oleh Tretiak and Jonathan Nissanov “Elastic 3-D alignment of rat brain histological images” In IEEE transactions on medical imaging 22.11 IEEE, 2003, pp. 1480–1489
  24. “Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain” In Medical image analysis 12.1 Elsevier, 2008, pp. 26–41
  25. Stefan Klein “Optimisation methods for medical image registration” Utrecht University, 2008
  26. “End-to-end unsupervised deformable image registration with a convolutional neural network” In Deep learning in medical image analysis and multimodal learning for clinical decision support Springer, 2017
  27. “Deep deformable registration: enhancing accuracy by fully convolutional neural net” In Pattern Recognition Letters 94 Elsevier, 2017, pp. 81–86
  28. “Non-rigid image registration using fully convolutional networks with deep self-supervision” In arXiv preprint arXiv:1709.00799, 2017
  29. “Linear and deformable image registration with 3d convolutional neural networks” In Image Analysis for Moving Organ, Breast, and Thoracic Images Springer, 2018
  30. “Unsupervised deformable image registration with fully connected generative neural network”, 2018
  31. Nasim Souly, Concetto Spampinato and Mubarak Shah “Semi supervised semantic segmentation using generative adversarial network” In Proceedings of the IEEE international conference on computer vision, 2017
  32. “Adversarial learning for semi-supervised semantic segmentation” In arXiv preprint arXiv:1802.07934, 2018
  33. “Semi-supervised semantic segmentation via dynamic self-training and classbalanced curriculum”, 2020
  34. “Guided collaborative training for pixel-wise semi-supervised learning” In Proceedings of ECCV, Part XIII 16, 2020 Springer
  35. “Semi-supervised semantic segmentation with cross pseudo supervision” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
  36. “Perturbed and strict mean teachers for semi-supervised semantic segmentation” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
  37. “Semi-supervised semantic segmentation needs strong, varied perturbations” In arXiv preprint arXiv:1906.01916, 2019
  38. “Structured consistency loss for semi-supervised semantic segmentation” In arXiv preprint arXiv:2001.04647, 2020
  39. “Pseudoseg: Designing pseudo labels for semantic segmentation” In arXiv preprint arXiv:2010.09713, 2020
  40. “Semi-supervised deep learning of brain tissue segmentation” In Neural Networks 116 Elsevier, 2019, pp. 25–34
  41. “DeepAtlas: Joint semi-supervised learning of image registration and segmentation” In Medical Image Computing and Computer Assisted Intervention–MICCAI 2019, Proceedings, Part II 22, 2019 Springer
  42. “Coupling deep deformable registration with contextual refinement for semi-supervised medical image segmentation” In 2022 IEEE 19th International Symposium on Biomedical Imaging, 2022 IEEE
  43. “Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registration” In Medical Image Analysis 90 Elsevier, 2023, pp. 102935
  44. “Global image registration using a symmetric block-matching approach” In Journal of medical imaging 1.2 Society of Photo-Optical Instrumentation Engineers, 2014, pp. 024003–024003
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (14)
  1. Yiwen Li (20 papers)
  2. Yunguan Fu (20 papers)
  3. Iani J. M. B. Gayo (3 papers)
  4. Qianye Yang (24 papers)
  5. Zhe Min (12 papers)
  6. Wen Yan (37 papers)
  7. Yipei Wang (20 papers)
  8. J. Alison Noble (48 papers)
  9. Mark Emberton (17 papers)
  10. Matthew J. Clarkson (39 papers)
  11. Victor A. Prisacariu (8 papers)
  12. Yipeng Hu (80 papers)
  13. Shaheer U. Saeed (23 papers)
  14. Dean C. Barratt (32 papers)

Summary

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

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