Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 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

CV-Attention UNet: Attention-based UNet for 3D Cerebrovascular Segmentation of Enhanced TOF-MRA Images (2311.10224v3)

Published 16 Nov 2023 in eess.IV, cs.CV, and cs.LG

Abstract: Due to the lack of automated methods, to diagnose cerebrovascular disease, time-of-flight magnetic resonance angiography (TOF-MRA) is assessed visually, making it time-consuming. The commonly used encoder-decoder architectures for cerebrovascular segmentation utilize redundant features, eventually leading to the extraction of low-level features multiple times. Additionally, convolutional neural networks (CNNs) suffer from performance degradation when the batch size is small, and deeper networks experience the vanishing gradient problem. Methods: In this paper, we attempt to solve these limitations and propose the 3D cerebrovascular attention UNet method, named CV-AttentionUNet, for precise extraction of brain vessel images. We proposed a sequence of preprocessing techniques followed by deeply supervised UNet to improve the accuracy of segmentation of the brain vessels leading to a stroke. To combine the low and high semantics, we applied the attention mechanism. This mechanism focuses on relevant associations and neglects irrelevant anatomical information. Furthermore, the inclusion of deep supervision incorporates different levels of features that prove to be beneficial for network convergence. Results: We demonstrate the efficiency of the proposed method by cross-validating with an unlabeled dataset, which was further labeled by us. We believe that the novelty of this algorithm lies in its ability to perform well on both labeled and unlabeled data with image processing-based enhancement. The results indicate that our method performed better than the existing state-of-the-art methods on the TubeTK dataset. Conclusion: The proposed method will help in accurate segmentation of cerebrovascular structure leading to stroke

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. E. S. Donkor, “Stroke in the 21st century: A snapshot of the burden, epidemiology, and quality of life,” Stroke research and treatment, vol. 2018, 2018.
  2. R. Wang, C. Li, J. Wang, X. Wei, Y. Li, Y. Zhu, and S. Zhang, “Threshold segmentation algorithm for automatic extraction of cerebral vessels from brain magnetic resonance angiography images,” Journal of neuroscience methods, vol. 241, pp. 30–36, 2015.
  3. D.-Y. Kim, “3d volume extraction of cerebrovascular structure on brain magnetic resonance angiography data sets,” 2012.
  4. D. Babin, E. Vansteenkiste, A. Pižurica, and W. Philips, “Segmentation of brain blood vessels using projections in 3-d ct angiography images,” in 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 8475–8478, IEEE, 2011.
  5. L. M. Lorigo, O. D. Faugeras, W. E. L. Grimson, R. Keriven, R. Kikinis, A. Nabavi, and C.-F. Westin, “Curves: Curve evolution for vessel segmentation,” Medical image analysis, vol. 5, no. 3, pp. 195–206, 2001.
  6. S. Zhao, M. Zhou, Y. Tian, P. Xu, Z. Wu, and Q. Deng, “Extraction of vessel networks based on multiview projection and phase field model,” Neurocomputing, vol. 162, pp. 234–244, 2015.
  7. K. C. Wang, R. W. Dutton, and C. A. Taylor, “Improving geometric model construction for blood flow modeling,” IEEE Engineering in Medicine and Biology Magazine, vol. 18, no. 6, pp. 33–39, 1999.
  8. Y. Zhang, B. J. Matuszewski, L.-K. Shark, and C. J. Moore, “Medical image segmentation using new hybrid level-set method,” in 2008 fifth international conference biomedical visualization: information visualization in medical and biomedical informatics, pp. 71–76, IEEE, 2008.
  9. M. S. Hassouna, A. A. Farag, S. Hushek, and T. Moriarty, “Cerebrovascular segmentation from tof using stochastic models,” Medical image analysis, vol. 10, no. 1, pp. 2–18, 2006.
  10. L. Wen, X. Wang, Z. Wu, M. Zhou, and J. S. Jin, “A novel statistical cerebrovascular segmentation algorithm with particle swarm optimization,” Neurocomputing, vol. 148, pp. 569–577, 2015.
  11. X. Gao, Y. Uchiyama, X. Zhou, T. Hara, T. Asano, and H. Fujita, “A fast and fully automatic method for cerebrovascular segmentation on time-of-flight (tof) mra image,” Journal of digital imaging, vol. 24, no. 4, pp. 609–625, 2011.
  12. P. Lu, J. Xia, Z. Li, J. Xiong, J. Yang, S. Zhou, L. Wang, M. Chen, and C. Wang, “A vessel segmentation method for multi-modality angiographic images based on multi-scale filtering and statistical models,” Biomedical engineering online, vol. 15, no. 1, pp. 1–18, 2016.
  13. J. Dolz, K. Gopinath, J. Yuan, H. Lombaert, C. Desrosiers, and I. B. Ayed, “Hyperdense-net: a hyper-densely connected cnn for multi-modal image segmentation,” IEEE transactions on medical imaging, vol. 38, no. 5, pp. 1116–1126, 2018.
  14. O. Bernard, A. Lalande, C. Zotti, F. Cervenansky, X. Yang, P.-A. Heng, I. Cetin, K. Lekadir, O. Camara, M. A. G. Ballester, et al., “Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved?,” IEEE transactions on medical imaging, vol. 37, no. 11, pp. 2514–2525, 2018.
  15. H. R. Roth, L. Lu, N. Lay, A. P. Harrison, A. Farag, A. Sohn, and R. M. Summers, “Spatial aggregation of holistically-nested convolutional neural networks for automated pancreas localization and segmentation,” Medical image analysis, vol. 45, pp. 94–107, 2018.
  16. J. Long, E. Shelhamer, and T. Darrell, “Fully convolutional networks for semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440, 2015.
  17. K. Qi, H. Yang, C. Li, Z. Liu, M. Wang, Q. Liu, and S. Wang, “X-net: Brain stroke lesion segmentation based on depthwise separable convolution and long-range dependencies,” in Medical Image Computing and Computer Assisted Intervention – MICCAI 2019, pp. 247–255, 22nd International Conference Shenzhen, China, October 13–17, 2019 Proceedings, Part III, 2019.
  18. Y. Zhou, W. Huang, P. Dong, Y. Xia, and S. Wang, “D-unet: A dimension-fusion u shape network for chronic stroke lesion segmentation,” in IEEE/ACM Transactions on Computational Biology and Bioinformatics, pp. 940–950, IEEE, 2021.
  19. Z. Zhou, M. M. R. Siddiquee, N. Tajbakhsh, and J. Liang, “Unet++: A nested u-net architecture for medical image segmentation,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 3–11, Springer, 2018.
  20. F. Wang, M. Jiang, C. Qian, S. Yang, C. Li, H. Zhang, X. Wang, and X. Tang, “Residual attention network for image classification,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3156–3164, 2017.
  21. Y. Wang, Z. Deng, X. Hu, L. Zhu, X. Yang, X. Xu, P.-A. Heng, and D. Ni, “Deep attentional features for prostate segmentation in ultrasound,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 523–530, Springer, 2018.
  22. L. Chen, Y. Xie, J. Sun, N. Balu, M. Mossa-Basha, K. Pimentel, T. S. Hatsukami, J.-N. Hwang, and C. Yuan, “3d intracranial artery segmentation using a convolutional autoencoder,” in 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pp. 714–717, IEEE, 2017.
  23. O. Oktay, J. Schlemper, L. L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N. Y. Hammerla, B. Kainz, et al., “Attention u-net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
  24. R. Phellan, A. Peixinho, A. Falcão, and N. D. Forkert, “Vascular segmentation in tof mra images of the brain using a deep convolutional neural network,” in Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesis, pp. 39–46, Springer, 2017.
  25. G. Tetteh, V. Efremov, N. D. Forkert, M. Schneider, J. Kirschke, B. Weber, C. Zimmer, M. Piraud, and B. H. Menze, “Deepvesselnet: Vessel segmentation, centerline prediction, and bifurcation detection in 3-d angiographic volumes,” Frontiers in Neuroscience, vol. 14, 2020.
  26. Ö. Çiçek, A. Abdulkadir, S. Lienkamp, T. Brox, and O. Ronneberger, “3d u-net: learning dense volumetric segmentation from sparse annotation. corr,” arXiv preprint arXiv:1606.06650, 2016.
  27. M. Livne, J. Rieger, O. U. Aydin, A. A. Taha, E. M. Akay, T. Kossen, J. Sobesky, J. D. Kelleher, K. Hildebrand, D. Frey, et al., “A u-net deep learning framework for high performance vessel segmentation in patients with cerebrovascular disease,” Frontiers in neuroscience, vol. 13, p. 97, 2019.
  28. L. Mou, Y. Zhao, H. Fu, Y. Liu, J. Cheng, Y. Zheng, P. Su, J. Yang, L. Chen, A. F. Frangi, et al., “Cs2-net: Deep learning segmentation of curvilinear structures in medical imaging,” Medical image analysis, vol. 67, p. 101874, 2020.
  29. B. Zhang, S. Liu, S. Zhou, J. Yang, C. Wang, N. Li, Z. Wu, and J. Xia, “Cerebrovascular segmentation from tof-mra using model-and data-driven method via sparse labels,” Neurocomputing, vol. 380, pp. 162–179, 2020.
  30. R. Phellan and N. D. Forkert, “Comparison of vessel enhancement algorithms applied to time-of-flight mra images for cerebrovascular segmentation,” Medical physics, vol. 44, no. 11, pp. 5901–5915, 2017.
  31. M. M. McCormick, X. Liu, L. Ibanez, J. Jomier, and C. Marion, “Itk: enabling reproducible research and open science,” Frontiers in neuroinformatics, vol. 8, p. 13, 2014.
  32. M. S. Miri and A. Mahloojifar, “A comparison study to evaluate retinal image enhancement techniques,” in 2009 IEEE international conference on signal and image processing applications, pp. 90–94, IEEE, 2009.
  33. H. M. Luu, A. Moelker, C. Klink, A. Mendrik, W. Niessen, and T. van Walsum, “Evaluation of diffusion filters for 3d cta liver vessel enhancement,” in International MICCAI Workshop on Computational and Clinical Challenges in Abdominal Imaging, pp. 168–177, Springer, 2012.
  34. Q. Meng, T. Kitasaka, M. Oda, and K. Mori, “Airway extraction from 3d chest ct volumes based on iterative extension of voi enhanced by cavity enhancement filter,” in Medical Imaging 2017: Computer-Aided Diagnosis, vol. 10134, p. 101343S, International Society for Optics and Photonics, 2017.
  35. A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever, “Multiscale vessel enhancement filtering,” in International conference on medical image computing and computer-assisted intervention, pp. 130–137, Springer, 1998.
  36. M. Drozdzal, E. Vorontsov, G. Chartrand, S. Kadoury, and C. Pal, “Deep learning and data labeling for medical applications,” in First International Workshop, LABELS 2016, and Second International Workshop, DLMIA 2016, Held in Conjunction with MICCAI 2016, 2016.
  37. Y. Wu and K. He, “Group normalization,” in Proceedings of the European conference on computer vision (ECCV), pp. 3–19, 2018.
  38. C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, “Deeply-supervised nets,” in Artificial intelligence and statistics, pp. 562–570, 2015.
  39. L. Folle, S. Vesal, N. Ravikumar, and A. Maier, “Dilated deeply supervised networks for hippocampus segmentation in mri,” in Bildverarbeitung für die Medizin 2019, pp. 68–73, Springer, 2019.
  40. S. S. M. Salehi, D. Erdogmus, and A. Gholipour, “Tversky loss function for image segmentation using 3d fully convolutional deep networks,” in International Workshop on Machine Learning in Medical Imaging, pp. 379–387, Springer, 2017.
  41. S. R. Aylward and E. Bullitt, “Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction,” IEEE transactions on medical imaging, vol. 21, no. 2, pp. 61–75, 2002.
  42. S. Moccia, E. De Momi, S. El Hadji, and L. S. Mattos, “Blood vessel segmentation algorithms—review of methods, datasets and evaluation metrics,” Computer methods and programs in biomedicine, vol. 158, pp. 71–91, 2018.
  43. A. Hilbert, V. I. Madai, E. M. Akay, O. U. Aydin, J. Behland, J. Sobesky, I. Galinovic, A. A. Khalil, A. A. Taha, J. Würfel, et al., “Brave-net: Fully automated arterial brain vessel segmentation in patients with cerebrovascular disease,” medRxiv, 2020.
  44. F. Milletari, N. Navab, and S.-A. Ahmadi, “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 fourth international conference on 3D vision (3DV), pp. 565–571, IEEE, 2016.

Summary

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

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