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

Towards an accurate and generalizable multiple sclerosis lesion segmentation model using self-ensembled lesion fusion (2312.01460v1)

Published 3 Dec 2023 in eess.IV and cs.CV

Abstract: Automatic multiple sclerosis (MS) lesion segmentation using multi-contrast magnetic resonance (MR) images provides improved efficiency and reproducibility compared to manual delineation. Current state-of-the-art automatic MS lesion segmentation methods utilize modified U-Net-like architectures. However, in the literature, dedicated architecture modifications were always required to maximize their performance. In addition, the best-performing methods have not proven to be generalizable to diverse test datasets with contrast variations and image artifacts. In this work, we developed an accurate and generalizable MS lesion segmentation model using the well-known U-Net architecture without further modification. A novel test-time self-ensembled lesion fusion strategy is proposed that not only achieved the best performance using the ISBI 2015 MS segmentation challenge data but also demonstrated robustness across various self-ensemble parameter choices. Moreover, equipped with instance normalization rather than batch normalization widely used in literature, the model trained on the ISBI challenge data generalized well on clinical test datasets from different scanners.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (20)
  1. L. Haider et al., “The topograpy of demyelination and neurodegeneration in the multiple sclerosis brain,” Brain, vol. 139, no. 3, pp. 807–815, 2016.
  2. H. Zhang et al., “Multiple sclerosis lesion segmentation with tiramisu and 2.5D stacked slices,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part III 22. Springer, 2019, pp. 338–346.
  3. H. Zhang et al., “ALL-Net: Anatomical information lesion-wise loss function integrated into neural network for multiple sclerosis lesion segmentation,” NeuroImage: Clinical, vol. 32, pp. 102854, 2021.
  4. O. Ronneberger et al., “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, 2015, pp. 234–241.
  5. A. Carass et al., “Longitudinal multiple sclerosis lesion segmentation: Resource and challenge,” NeuroImage, vol. 148, pp. 77–102, 2017.
  6. A. Carass et al., “Longitudinal multiple sclerosis lesion segmentation data resource,” vol. 12, pp. 346–350, 2017.
  7. B.E. Dewey et al., “DeepHarmony: A deep learning approach to contrast harmonization across scanner changes,” Magnetic Resonance Imaging, vol. 64, pp. 160–170, 2019.
  8. L. Zuo et al., “HACA3: A unified approach for multi-site MR image harmonization,” Computerized Medical Imaging and Graphics, vol. 109, pp. 102285, 2023.
  9. S. Hays et al., “Exploring the optimal operating mr contrast for brain ventricle parcellation,” in Medical Imaging with Deep Learning, short paper track, 2023.
  10. Robel K Gebre et al., “Cross–scanner harmonization methods for structural mri may need further work: A comparison study,” Neuroimage, vol. 269, pp. 119912, 2023.
  11. J. Zhang et al., “Harmonization-enriched domain adaptation with light fine-tuning for multiple sclerosis lesion segmentation,” arXiv preprint arXiv:2310.20586, 2023.
  12. R.A. Kamraoui et al., “DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation,” Medical Image Analysis, vol. 76, pp. 102312, 2022.
  13. S. Aslani et al., “Scanner invariant multiple sclerosis lesion segmentation from MRI,” in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE, 2020, pp. 781–785.
  14. D. Ulyanov et al., “Instance normalization: The missing ingredient for fast stylization,” arXiv preprint arXiv:1607.08022, 2016.
  15. S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in International conference on machine learning. pmlr, 2015, pp. 448–456.
  16. S. Han et al., “Automatic cerebellum anatomical parcellation using u-net with locally constrained optimization,” Neuroimage, vol. 218, pp. 116819, 2020.
  17. John Canny, “A computational approach to edge detection,” IEEE Transactions on pattern analysis and machine intelligence, , no. 6, pp. 679–698, 1986.
  18. S. W. Remedios et al., “Self-supervised super-resolution for anisotropic mr images with and without slice gap,” in International Workshop on Simulation and Synthesis in Medical Imaging. Springer, 2023, pp. 118–128.
  19. C. Zhao et al., “Smore: a self-supervised anti-aliasing and super-resolution algorithm for mri using deep learning,” IEEE transactions on medical imaging, vol. 40, no. 3, pp. 805–817, 2020.
  20. D.P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (7)
  1. Jinwei Zhang (32 papers)
  2. Lianrui Zuo (25 papers)
  3. Blake E. Dewey (18 papers)
  4. Samuel W. Remedios (16 papers)
  5. Dzung L. Pham (14 papers)
  6. Aaron Carass (48 papers)
  7. Jerry L. Prince (58 papers)
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