Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Circle Representation for Medical Instance Object Segmentation (2403.11507v1)

Published 18 Mar 2024 in cs.CV

Abstract: Recently, circle representation has been introduced for medical imaging, designed specifically to enhance the detection of instance objects that are spherically shaped (e.g., cells, glomeruli, and nuclei). Given its outstanding effectiveness in instance detection, it is compelling to consider the application of circle representation for segmenting instance medical objects. In this study, we introduce CircleSnake, a simple end-to-end segmentation approach that utilizes circle contour deformation for segmenting ball-shaped medical objects at the instance level. The innovation of CircleSnake lies in these three areas: (1) It substitutes the complex bounding box-to-octagon contour transformation with a more consistent and rotation-invariant bounding circle-to-circle contour adaptation. This adaptation specifically targets ball-shaped medical objects. (2) The circle representation employed in CircleSnake significantly reduces the degrees of freedom to two, compared to eight in the octagon representation. This reduction enhances both the robustness of the segmentation performance and the rotational consistency of the method. (3) CircleSnake is the first end-to-end deep instance segmentation pipeline to incorporate circle representation, encompassing consistent circle detection, circle contour proposal, and circular convolution in a unified framework. This integration is achieved through the novel application of circular graph convolution within the context of circle detection and instance segmentation. In practical applications, such as the detection of glomeruli, nuclei, and eosinophils in pathological images, CircleSnake has demonstrated superior performance and greater rotation invariance when compared to benchmarks. The code has been made publicly available: https://github.com/hrlblab/CircleSnake.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Y.-C. Lo, C.-F. Juang, I.-F. Chung, S.-N. Guo, M.-L. Huang, M.-C. Wen, C.-J. Lin, and H.-Y. Lin, “Glomerulus detection on light microscopic images of renal pathology with the faster r-cnn,” in International Conference on Neural Information Processing.   Springer, 2018, pp. 369–377.
  2. H. Liang, Z. Cheng, H. Zhong, A. Qu, and L. Chen, “A region-based convolutional network for nuclei detection and segmentation in microscopy images,” Biomedical Signal Processing and Control, vol. 71, p. 103276, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1746809421008739
  3. J. Xiong, Y. Liu, R. Deng, R. N. Tyree, H. Correa, G. Hiremath, Y. Wang, and Y. Huo, “Deep learning-based open source toolkit for eosinophil detection in pediatric eosinophilic esophagitis,” 2023.
  4. H. Yang, R. Deng, Y. Lu, Z. Zhu, Y. Chen, J. T. Roland, L. Lu, B. A. Landman, A. B. Fogo, and Y. Huo, “Circlenet: Anchor-free glomerulus detection with circle representation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2020, pp. 35–44.
  5. E. H. Nguyen, H. Yang, R. Deng, Y. Lu, Z. Zhu, J. T. Roland, L. Lu, B. A. Landman, A. B. Fogo, and Y. Huo, “Circle representation for medical object detection,” IEEE transactions on medical imaging, vol. 41, no. 3, pp. 746–754, 2021.
  6. E. H. Nguyen, H. Yang, Z. Asad, R. Deng, A. B. Fogo, and Y. Huo, “Circlesnake: Instance segmentation with circle representation,” in International Workshop on Machine Learning in Medical Imaging.   Springer, 2022, pp. 298–306.
  7. X. Luo, T. Song, G. Wang, J. Chen, Y. Chen, K. Li, D. Metaxas, and S. Zhang, “Scpm-net: An anchor-free 3d lung nodule detection network using sphere representation and center points matching,” arXiv preprint arXiv:2104.05215, 2021.
  8. Y. Liu, R. Deng, J. Xiong, R. N. Tyree, H. Correa, G. Hiremath, Y. Wang, and Y. Huo, “Eosinophils instance object segmentation on whole slide imaging using multi-label circle representation,” 2023.
  9. H. Zhang, P. Liang, Z. Sun, B. Song, and E. Cheng, “Circleformer: Circular nuclei detection in whole slide images with circle queries and attention,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2023, pp. 493–502.
  10. K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” 2018.
  11. Z. Cai and N. Vasconcelos, “Cascade r-cnn: High quality object detection and instance segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 43, no. 5, pp. 1483–1498, 2021.
  12. D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee, “Yolact: Real-time instance segmentation,” 2019.
  13. H. Ying, Z. Huang, S. Liu, T. Shao, and K. Zhou, “Embedmask: Embedding coupling for one-stage instance segmentation,” 2019.
  14. R. Girshick, J. Donahue, T. Darrell, and J. Malik, “Rich feature hierarchies for accurate object detection and semantic segmentation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2014, pp. 580–587.
  15. R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
  16. L.-C. Chen, A. Hermans, G. Papandreou, F. Schroff, P. Wang, and H. Adam, “Masklab: Instance segmentation by refining object detection with semantic and direction features,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 4013–4022.
  17. K. Chen, J. Pang, J. Wang, Y. Xiong, X. Li, S. Sun, W. Feng, Z. Liu, J. Shi, W. Ouyang, C. C. Loy, and D. Lin, “Hybrid task cascade for instance segmentation,” 2019.
  18. S. Fang, B. Zhang, and J. Hu, “Improved mask r-cnn multi-target detection and segmentation for autonomous driving in complex scenes,” Sensors, vol. 23, no. 8, 2023. [Online]. Available: https://www.mdpi.com/1424-8220/23/8/3853
  19. Q. Zhang, X. Chang, and S. B. Bian, “Vehicle-damage-detection segmentation algorithm based on improved mask rcnn,” IEEE Access, vol. 8, pp. 6997–7004, 2020.
  20. S. Wang, G. Sun, B. Zheng, and Y. Du, “A crop image segmentation and extraction algorithm based on mask rcnn,” Entropy, vol. 23, no. 9, 2021. [Online]. Available: https://www.mdpi.com/1099-4300/23/9/1160
  21. S. Liu, L. Qi, H. Qin, J. Shi, and J. Jia, “Path aggregation network for instance segmentation,” 2018.
  22. W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C.-Y. Fu, and A. C. Berg, “Ssd: Single shot multibox detector,” in European conference on computer vision.   Springer, 2016, pp. 21–37.
  23. H. Liu, R. A. R. Soto, F. Xiao, and Y. J. Lee, “Yolactedge: Real-time instance segmentation on the edge,” 2021.
  24. J. Zeng, H. Ouyang, M. Liu, L. Leng, and X. Fu, “Multi-scale yolact for instance segmentation,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 10, Part B, pp. 9419–9427, 2022. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1319157822003482
  25. D. Bolya, C. Zhou, F. Xiao, and Y. J. Lee, “Yolact++ better real-time instance segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 2, p. 1108–1121, Feb. 2022. [Online]. Available: http://dx.doi.org/10.1109/TPAMI.2020.3014297
  26. M. Gadermayr, A.-K. Dombrowski, B. M. Klinkhammer, P. Boor, and D. Merhof, “Cnn cascades for segmenting whole slide images of the kidney,” arXiv preprint arXiv:1708.00251, 2017.
  27. G. Bueno, M. M. Fernandez-Carrobles, L. Gonzalez-Lopez, and O. Deniz, “Glomerulosclerosis identification in whole slide images using semantic segmentation,” Computer methods and programs in biomedicine, vol. 184, p. 105273, 2020.
  28. S. Kannan, L. A. Morgan, B. Liang, M. G. Cheung, C. Q. Lin, D. Mun, R. G. Nader, M. E. Belghasem, J. M. Henderson, J. M. Francis et al., “Segmentation of glomeruli within trichrome images using deep learning,” Kidney international reports, vol. 4, no. 7, pp. 955–962, 2019.
  29. B. Ginley, B. Lutnick, K.-Y. Jen, A. B. Fogo, S. Jain, A. Rosenberg, V. Walavalkar, G. Wilding, J. E. Tomaszewski, R. Yacoub et al., “Computational segmentation and classification of diabetic glomerulosclerosis,” Journal of the American Society of Nephrology, vol. 30, no. 10, pp. 1953–1967, 2019.
  30. S. Peng, W. Jiang, H. Pi, X. Li, H. Bao, and X. Zhou, “Deep snake for real-time instance segmentation,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 8533–8542.
  31. K. Huang, L. Xu, Y. Zhu, and P. Meng, “A u-snake based deep learning network for right ventricle segmentation.” Medical physics, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:247520303
  32. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” 2015.
  33. X. Zhou, D. Wang, and P. Krähenbühl, “Objects as points,” arXiv preprint arXiv:1904.07850, 2019.
  34. H. Law and J. Deng, “Cornernet: Detecting objects as paired keypoints,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 734–750.
  35. T.-Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollár, “Focal loss for dense object detection,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 2980–2988.
  36. V. G. Puelles, W. E. Hoy, M. D. Hughson, B. Diouf, R. N. Douglas-Denton, and J. F. Bertram, “Glomerular number and size variability and risk for kidney disease,” Current opinion in nephrology and hypertension, vol. 20, no. 1, pp. 7–15, 2011.
  37. T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” in European conference on computer vision.   Springer, 2014, pp. 740–755.
  38. S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” in Advances in neural information processing systems, 2015, pp. 91–99.
  39. K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  40. F. Yu, D. Wang, E. Shelhamer, and T. Darrell, “Deep layer aggregation,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 2403–2412.
  41. N. Kumar, R. Verma, S. Sharma, S. Bhargava, A. Vahadane, and A. Sethi, “A dataset and a technique for generalized nuclear segmentation for computational pathology,” IEEE transactions on medical imaging, vol. 36, no. 7, pp. 1550–1560, 2017.
  42. N. Kumar, R. Verma, D. Anand, Y. Zhou, O. F. Onder, E. Tsougenis, H. Chen, P.-A. Heng, J. Li, Z. Hu et al., “A multi-organ nucleus segmentation challenge,” IEEE transactions on medical imaging, vol. 39, no. 5, pp. 1380–1391, 2019.

Summary

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

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