Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 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

Benefit from public unlabeled data: A Frangi filtering-based pretraining network for 3D cerebrovascular segmentation (2312.15273v1)

Published 23 Dec 2023 in cs.CV and cs.AI

Abstract: The precise cerebrovascular segmentation in time-of-flight magnetic resonance angiography (TOF-MRA) data is crucial for clinically computer-aided diagnosis. However, the sparse distribution of cerebrovascular structures in TOF-MRA results in an exceedingly high cost for manual data labeling. The use of unlabeled TOF-MRA data holds the potential to enhance model performance significantly. In this study, we construct the largest preprocessed unlabeled TOF-MRA datasets (1510 subjects) to date. We also provide three additional labeled datasets totaling 113 subjects. Furthermore, we propose a simple yet effective pertraining strategy based on Frangi filtering, known for enhancing vessel-like structures, to fully leverage the unlabeled data for 3D cerebrovascular segmentation. Specifically, we develop a Frangi filtering-based preprocessing workflow to handle the large-scale unlabeled dataset, and a multi-task pretraining strategy is proposed to effectively utilize the preprocessed data. By employing this approach, we maximize the knowledge gained from the unlabeled data. The pretrained model is evaluated on four cerebrovascular segmentation datasets. The results have demonstrated the superior performance of our model, with an improvement of approximately 3\% compared to state-of-the-art semi- and self-supervised methods. Furthermore, the ablation studies also demonstrate the generalizability and effectiveness of the pretraining method regarding the backbone structures. The code and data have been open source at: \url{https://github.com/shigen-StoneRoot/FFPN}.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (49)
  1. Towards a real-time minimally-invasive vascular intervention simulation system. IEEE Transactions on Medical Imaging 26, 128–132.
  2. Self-supervised pretraining for differentially private learning. arXiv preprint arXiv:2206.07125 .
  3. Bidirectional copy-paste for semi-supervised medical image segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 11514–11524.
  4. Generative consistency for semi-supervised cerebrovascular segmentation from tof-mra. IEEE Transactions on Medical Imaging 42, 346–353.
  5. All answers are in the images: A review of deep learning for cerebrovascular segmentation. Computerized Medical Imaging and Graphics , 102229.
  6. Distributionally robust semi-supervised learning for people-centric sensing, in: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3321–3328.
  7. A simple framework for contrastive learning of visual representations, in: International conference on machine learning, PMLR. pp. 1597–1607.
  8. Attention-assisted adversarial model for cerebrovascular segmentation in 3d tof-mra volumes. IEEE Transactions on Medical Imaging 41, 3520–3532.
  9. Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis. Medical image analysis 54, 280–296.
  10. Towards automated brain aneurysm detection in tof-mra: Open data, weak labels, and anatomical knowledge. Neuroinformatics 21, 21–34.
  11. Segmentation of pulmonary vascular tree by incorporating vessel enhancement filter and variational region-growing. Journal of X-ray science and technology 27, 343–360.
  12. Self-supervised representation learning: Introduction, advances, and challenges. IEEE Signal Processing Magazine 39, 42–62. doi:10.1109/MSP.2021.3134634.
  13. Multiscale vessel enhancement filtering, in: Medical Image Computing and Computer-Assisted Intervention—MICCAI’98: First International Conference Cambridge, MA, USA, October 11–13, 1998 Proceedings 1, Springer. pp. 130–137.
  14. Cerebrovascular segmentation from tof using stochastic models. Medical image analysis 10, 2–18.
  15. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images, in: International MICCAI Brainlesion Workshop, Springer. pp. 272–284.
  16. Unetr: Transformers for 3d medical image segmentation, in: Proceedings of the IEEE/CVF winter conference on applications of computer vision, pp. 574–584.
  17. Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 16000–16009.
  18. Geometric visual similarity learning in 3d medical image self-supervised pre-training, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9538–9547.
  19. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digital Medicine 6, 74.
  20. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods 18, 203–211.
  21. Learning with limited annotations: a survey on deep semi-supervised learning for medical image segmentation. arXiv preprint arXiv:2207.14191 .
  22. Self-supervised learning in medicine and healthcare. Nature Biomedical Engineering 6, 1346–1352.
  23. Oasis-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and alzheimer disease. MedRxiv , 2019–12.
  24. Cupre: Cross-domain unsupervised pre-training for few-shot cell segmentation. arXiv preprint arXiv:2310.03981 .
  25. Muscle: Multi-task self-supervised continual learning to pre-train deep models for x-ray images of multiple body parts, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 151–161.
  26. A u-net deep learning framework for high performance vessel segmentation in patients with cerebrovascular disease. Frontiers in neuroscience 13, 97.
  27. Semi-supervised medical image segmentation through dual-task consistency, in: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 8801–8809.
  28. Global channel attention networks for intracranial vessel segmentation. Computers in biology and medicine 118, 103639.
  29. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999 .
  30. A threshold selection method from gray-level histograms. IEEE transactions on systems, man, and cybernetics 9, 62–66.
  31. Mr angiography of the intracranial vessels: technical aspects and clinical applications. Neuroradiology 46, 955–972.
  32. Small data challenges in big data era: A survey of recent progress on unsupervised and semi-supervised methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 2168–2187.
  33. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation. arXiv preprint arXiv:2307.08388 .
  34. U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer. pp. 234–241.
  35. Cerebrovascular network segmentation of mra images with deep learning, in: 2019 IEEE 16th international symposium on biomedical imaging (ISBI 2019), IEEE. pp. 768–771.
  36. Progressive pretraining network for 3d system matrix calibration in magnetic particle imaging. IEEE Transactions on Medical Imaging 42, 3639–3650. doi:10.1109/TMI.2023.3297173.
  37. cldice-a novel topology-preserving loss function for tubular structure segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16560–16569.
  38. Deep learning–based detection of intracranial aneurysms in 3d tof-mra. American Journal of Neuroradiology 40, 25–32.
  39. Self-supervised pre-training of swin transformers for 3d medical image analysis, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20730–20740.
  40. Rethinking bayesian deep learning methods for semi-supervised volumetric medical image segmentation, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 182–190.
  41. Deep semi-supervised multiple instance learning with self-correction for dme classification from oct images. Medical Image Analysis 83, 102673.
  42. Exploring smoothness and class-separation for semi-supervised medical image segmentation, in: International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer. pp. 34–43.
  43. 3d vessel-like structure segmentation in medical images by an edge-reinforced network. Medical Image Analysis 82, 102581.
  44. Unimiss: Universal medical self-supervised learning via breaking dimensionality barrier, in: European Conference on Computer Vision, Springer. pp. 558–575.
  45. A survey on deep semi-supervised learning. IEEE Transactions on Knowledge and Data Engineering .
  46. Drasclr: A self-supervised framework of learning disease-related and anatomy-specific representation for 3d lung ct images. Medical Image Analysis , 103062URL: https://www.sciencedirect.com/science/article/pii/S1361841523003225, doi:https://doi.org/10.1016/j.media.2023.103062.
  47. Dive into the details of self-supervised learning for medical image analysis. Medical Image Analysis , 102879.
  48. nnformer: Interleaved transformer for volumetric segmentation. arXiv preprint arXiv:2109.03201 .
  49. Preservational learning improves self-supervised medical image models by reconstructing diverse contexts, in: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3499–3509.

Summary

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

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

GitHub

  1. GitHub - shigen-StoneRoot/FFPN (4 stars)