Papers
Topics
Authors
Recent
Search
2000 character limit reached

Deep models for stroke segmentation: do complex architectures always perform better?

Published 25 Mar 2024 in eess.IV, cs.CV, and cs.LG | (2403.17177v2)

Abstract: Stroke segmentation plays a crucial role in the diagnosis and treatment of stroke patients by providing spatial information about affected brain regions and the extent of damage. Segmenting stroke lesions accurately is a challenging task, given that conventional manual techniques are time consuming and prone to errors. Recently, advanced deep models have been introduced for general medical image segmentation, demonstrating promising results that surpass many state of the art networks when evaluated on specific datasets. With the advent of the vision Transformers, several models have been introduced based on them, while others have aimed to design better modules based on traditional convolutional layers to extract long-range dependencies like Transformers. The question of whether such high-level designs are necessary for all segmentation cases to achieve the best results remains unanswered. In this study, we selected four types of deep models that were recently proposed and evaluated their performance for stroke segmentation: a pure Transformer-based architecture (DAE-Former), two advanced CNN-based models (LKA and DLKA) with attention mechanisms in their design, an advanced hybrid model that incorporates CNNs with Transformers (FCT), and the well-known self-adaptive nnUNet framework with its configuration based on given data. We examined their performance on two publicly available datasets, and found that the nnUNet achieved the best results with the simplest design among all. Revealing the robustness issue of Transformers to such variabilities serves as a potential reason for their weaker performance. Furthermore, nnUNet's success underscores the significant impact of preprocessing and postprocessing techniques in enhancing segmentation results, surpassing the focus solely on architectural designs

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. World stroke organization (wso): global stroke fact sheet 2022. International Journal of Stroke, 17(1):18–29, 2022.
  2. A systematic review of studies reporting multivariable models to predict functional outcomes after post-stroke inpatient rehabilitation. Disability and rehabilitation, 37(15):1316–1323, 2015.
  3. Is this patient having a stroke? Jama, 293(19):2391–2402, 2005.
  4. Comparative sensitivity of computed tomography vs. magnetic resonance imaging for detecting acute posterior fossa infarct. The Journal of emergency medicine, 42(5):559–565, 2012.
  5. Sensitivity of diffusion-and perfusion-weighted imaging for diagnosing acute ischemic stroke is 97.5%. Stroke, 46(1):98–101, 2015.
  6. Handbook of medical image computing and computer assisted intervention. Academic Press, 2019.
  7. 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, pages 234–241. Springer, 2015.
  8. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306, 2021.
  9. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  10. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021.
  11. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  12. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI Brainlesion Workshop, pages 272–284. Springer, 2021.
  13. Unetr: Transformers for 3d medical image segmentation. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 574–584, 2022.
  14. nnformer: Interleaved transformer for volumetric segmentation. arXiv preprint arXiv:2109.03201, 2021.
  15. Transfuse: Fusing transformers and cnns for medical image segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24, pages 14–24. Springer, 2021.
  16. Acute ischemic stroke lesion core segmentation in ct perfusion images using fully convolutional neural networks. Computers in biology and medicine, 115:103487, 2019.
  17. Automatic brain ischemic stroke segmentation with deep learning: A review. Neuroscience Informatics, page 100145, 2023.
  18. Automatic segmentation of the brain stroke lesions from mr flair scans using improved u-net framework. Biomedical Signal Processing and Control, 78:103978, 2022.
  19. Concurrent ischemic lesion age estimation and segmentation of ct brain using a transformer-based network. IEEE Transactions on Medical Imaging, 2023.
  20. Sthardnet: Swin transformer with hardnet for mri segmentation. Applied Sciences, 12(1):468, 2022.
  21. D-unet: a dimension-fusion u shape network for chronic stroke lesion segmentation. IEEE/ACM transactions on computational biology and bioinformatics, 18(3):940–950, 2019.
  22. Ischemic stroke lesion segmentation in ct perfusion scans using pyramid pooling and focal loss. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 4th International Workshop, BrainLes 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Revised Selected Papers, Part I 4, pages 352–363. Springer, 2019.
  23. Pyramid scene parsing network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2881–2890, 2017.
  24. Efficient multi-kernel dcnn with pixel dropout for stroke mri segmentation. Neurocomputing, 350:117–127, 2019.
  25. Pool-unet: Ischemic stroke segmentation from ct perfusion scans using poolformer unet. In 2022 6th Asian Conference on Artificial Intelligence Technology (ACAIT), pages 1–6. IEEE, 2022.
  26. Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7132–7141, 2018.
  27. Metaformer is actually what you need for vision. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10819–10829, 2022.
  28. Large-kernel attention for efficient and robust brain lesion segmentation. arXiv preprint arXiv:2308.07251, 2023.
  29. Visual attention network. Computational Visual Media, 9(4):733–752, 2023.
  30. Ucatr: Based on cnn and transformer encoding and cross-attention decoding for lesion segmentation of acute ischemic stroke in non-contrast computed tomography images. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pages 3565–3568. IEEE, 2021.
  31. Utransnet: Transformer within u-net for stroke lesion segmentation. In 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pages 359–364. IEEE, 2022.
  32. Metrans: Multi-encoder transformer for ischemic stroke segmentation. Electronics Letters, 58(9):340–342, 2022.
  33. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pages 3–19, 2018.
  34. Llrhnet: Multiple lesions segmentation using local-long range features. Frontiers in Neuroinformatics, 16:859973, 2022.
  35. Transrender: a transformer-based boundary rendering segmentation network for stroke lesions. Frontiers in Neuroscience, 17, 2023.
  36. W-net: A boundary-enhanced segmentation network for stroke lesions. Expert Systems with Applications, page 120637, 2023.
  37. Application of deep learning method on ischemic stroke lesion segmentation. Journal of Shanghai Jiaotong University (Science), pages 1–13, 2022.
  38. Deep learning techniques for automatic mri cardiac multi-structures segmentation and diagnosis: is the problem solved? IEEE transactions on medical imaging, 37(11):2514–2525, 2018.
  39. Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the international skin imaging collaboration (isic). arXiv preprint arXiv:1902.03368, 2019.
  40. Dae-former: Dual attention-guided efficient transformer for medical image segmentation. In International Workshop on PRedictive Intelligence In MEdicine, pages 83–95. Springer, 2023.
  41. Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999, 2018.
  42. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision, pages 205–218. Springer, 2022.
  43. Levit-unet: Make faster encoders with transformer for medical image segmentation. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pages 42–53. Springer, 2023.
  44. Mixed transformer u-net for medical image segmentation. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2390–2394. IEEE, 2022.
  45. Transdeeplab: Convolution-free transformer-based deeplab v3+ for medical image segmentation. In International Workshop on PRedictive Intelligence In MEdicine, pages 91–102. Springer, 2022.
  46. Hiformer: Hierarchical multi-scale representations using transformers for medical image segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 6202–6212, 2023.
  47. Missformer: An effective medical image segmentation transformer. arXiv preprint arXiv:2109.07162, 2021.
  48. Multi-level context gating of embedded collective knowledge for medical image segmentation. arXiv preprint arXiv:2003.05056, 2020.
  49. Medical transformer: Gated axial-attention for medical image segmentation. In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24, pages 36–46. Springer, 2021.
  50. Fat-net: Feature adaptive transformers for automated skin lesion segmentation. Medical image analysis, 76:102327, 2022.
  51. Contextual attention network: Transformer meets u-net. In International Workshop on Machine Learning in Medical Imaging, pages 377–386. Springer, 2022.
  52. Transnorm: Transformer provides a strong spatial normalization mechanism for a deep segmentation model. IEEE Access, 10:108205–108215, 2022.
  53. The fully convolutional transformer for medical image segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 3660–3669, 2023.
  54. Transclaw u-net: Claw u-net with transformers for medical image segmentation. arXiv preprint arXiv:2107.05188, 2021.
  55. Beyond self-attention: Deformable large kernel attention for medical image segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 1287–1297, 2024.
  56. Medical image segmentation via cascaded attention decoding. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 6222–6231, 2023.
  57. Skin lesion segmentation via generative adversarial networks with dual discriminators. Medical Image Analysis, 64:101716, 2020.
  58. Encoder-decoder with atrous separable convolution for semantic image segmentation. In Proceedings of the European conference on computer vision (ECCV), pages 801–818, 2018.
  59. Scaleformer: revisiting the transformer-based backbones from a scale-wise perspective for medical image segmentation. arXiv preprint arXiv:2207.14552, 2022.
  60. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nature methods, 18(2):203–211, 2021.
  61. 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, pages 20730–20740, 2022.
  62. Evaluating nnu-net for early ischemic change segmentation on non-contrast computed tomography in patients with acute ischemic stroke. Computers in biology and medicine, 141:105033, 2022.
  63. Mapping: Model average with post-processing for stroke lesion segmentation. arXiv preprint arXiv:2211.15486, 2022.
  64. Efficient attention: Attention with linear complexities. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 3531–3539, 2021.
  65. Xcit: Cross-covariance image transformers. Advances in neural information processing systems, 34:20014–20027, 2021.
  66. Deformable convolutional networks. In Proceedings of the IEEE international conference on computer vision, pages 764–773, 2017.
  67. Isles 2022: A multi-center magnetic resonance imaging stroke lesion segmentation dataset. Scientific data, 9(1):762, 2022.
  68. A large, curated, open-source stroke neuroimaging dataset to improve lesion segmentation algorithms. Scientific data, 9(1):320, 2022.
  69. Brain tumor segmentation of mri images: A comprehensive review on the application of artificial intelligence tools. Computers in biology and medicine, 152:106405, 2023.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

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

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

Collections

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

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