Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지
DOI QR코드

DOI QR Code

Neuron Tracing- and Deep Learning-guided Interactive Proofreading for Neuron Structure Segmentation

뉴런 추적 및 딥러닝 기반의 대화형 뉴런 구조 교정 기법

  • Received : 2021.05.17
  • Accepted : 2021.08.25
  • Published : 2021.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

Segmenting the compartments of neurons, such as axons, dendrites, and cell bodies, is helpful in the analysis of neurological phenomena. Recently, there have been several studies to segment the compartments through deep learning. However, this approach has the potential to include errors in the results due to noise in data and differences between training data and actual data. Therefore, in order to use these for actual analysis, it is essential to proofread the results. The proofreading process requires a lot of effort and time because an expert must perform it manually. We propose an interactive neuron structure proofreading method that can more easily correct errors in the segmentation results of a deep learning. This method proofread the neuron structure based on the characteristics of the neuron with structural consistency, so that a high-accuracy proofreading result can be obtained with less interaction.

축삭(axon), 가지돌기(dendrite), 신경세포체(cell body)와 같은 뉴런의 소기관을 분리하는 작업은 신경학적 현상의 분석에 도움을 준다. 최근에 딥러닝 기술을 이용하여 이를 수행하고자 하는 시도들이 있지만, 데이터의 노이즈, 훈련 데이터와의 차이 등으로 인해 결과에 오류를 포함할 가능성이 있다. 따라서, 이러한 기술을 실제 분석에 활용하기 위해서는 결과를 교정하는 과정이 필수적이지만, 이는 전문가가 수작업으로 수행해야 하기 때문에 많은 노력과 시간이 소요된다. 우리는 딥러닝 결과에 존재하는 오류들을 보다 손쉽게 교정할 수 있는 대화형 뉴런 구조 교정 방법을 제안한다. 이 방법은 구조적 일관성을 지니는 뉴런의 특성을 기반으로 뉴런 구조를 교정하여 적은 사용자의 인터랙션으로도 높은 정확도의 교정 결과를 얻을 수 있도록 한다.

Keywords

Acknowledgement

본 연구에 사용된 모든 뉴런 현미경 이미지를 제공해준 Kwon lab (Center for Functional Connectomics, Brain Science Institute, KIST, Seoul, South Korea)에 감사를 표함. 본 연구는 과학기술정보통신부 재원의 정보통신기획평가원의 ICT명품인재양성 사업 (IITP-2021-2020-0-01819), 교육부 재원의 한국연구재단의 기초연구사업 (No. NRF-2021R1A6A1A13044830), 그리고 과학기술정보통신부 재원의 한국연구재단의 초융합AI원천기술개발사업 (NRF-2019M3E5D2A01063819)의 지원을 받아 수행되었음.

References

  1. M. London and M. Hausser, "Dendritic computation," Annu. Rev. Neurosci., vol. 28, pp. 503-532, 2005. https://doi.org/10.1146/annurev.neuro.28.061604.135703
  2. T. L. Lewis, S.-K. Kwon, A. Lee, R. Shaw, and F. Polleux, "Mff-dependent mitochondrial fission regulates presynaptic release and axon branching by limiting axonal mitochondria size," Nature communications, vol. 9, no. 1, pp. 1-15, 2018. https://doi.org/10.1038/s41467-017-02088-w
  3. C. Park, K. Lee, S. Kim, F. S. C. Cecen, S.-K. Kwon, and W.-K. Jeong, "Neuron segmentation using incomplete and noisy labels via adaptive learning with structure priors," in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI 2021). IEEE, 2021.
  4. N. Papernot, P. McDaniel, S. Jha, M. Fredrikson, Z. B. Celik, and A. Swami, "The limitations of deep learning in adversarial settings," in 2016 IEEE European symposium on security and privacy (EuroS&P). IEEE, 2016, pp. 372-387.
  5. D. Karimi, H. Dou, S. K. Warfield, and A. Gholipour, "Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis," Medical Image Analysis, vol. 65, p. 101759, 2020. https://doi.org/10.1016/j.media.2020.101759
  6. A. Mosinska, J. Tarnawski, and P. Fua, "Active learning and proofreading for delineation of curvilinear structures," in International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2017, pp. 165-173.
  7. V. J. Dercksen, H.-C. Hege, and M. Oberlaender, "The filament editor: an interactive software environment for visualization, proof-editing and analysis of 3d neuron morphology," Neuroinformatics, vol. 12, no. 2, pp. 325-339, 2014. https://doi.org/10.1007/s12021-013-9213-2
  8. L. Acciai, P. Soda, and G. Iannello, "Automated neuron tracing methods: an updated account," Neuroinformatics, vol. 14, no. 4, pp. 353-367, 2016. https://doi.org/10.1007/s12021-016-9310-0
  9. H. Peng, M. Hawrylycz, J. Roskams, S. Hill, N. Spruston, E. Meijering, and G. A. Ascoli, "Bigneuron: large-scale 3d neuron reconstruction from optical microscopy images," Neuron, vol. 87, no. 2, pp. 252-256, 2015. https://doi.org/10.1016/j.neuron.2015.06.036
  10. R. Lin, R. Wang, J. Yuan, Q. Feng, Y. Zhou, S. Zeng, M. Ren, S. Jiang, H. Ni, C. Zhou, et al., "Cell-type-specific and projection-specific brain-wide reconstruction of single neurons," Nature methods, vol. 15, no. 12, pp. 1033-1036, 2018. https://doi.org/10.1038/s41592-018-0184-y
  11. N. Krasowski, T. Beier, G. Knott, U. Kothe, F. A. Hamprecht, and A. Kreshuk, "Neuron segmentation with high-level biological priors," IEEE transactions on medical imaging, vol. 37, no. 4, pp. 829-839, 2017. https://doi.org/10.1109/TMI.2017.2712360
  12. A. B. Schroeder, E. T. Dobson, C. T. Rueden, P. Tomancak, F. Jug, and K. W. Eliceiri, "The imagej ecosystem: Open-source software for image visualization, processing, and analysis," Protein Science, vol. 30, no. 1, pp. 234-249, 2021. https://doi.org/10.1002/pro.3993
  13. P. A. Yushkevich and G. Gerig, "Itk-snap: an intractive medical image segmentation tool to meet the need for expert-guided segmentation of complex medical images," IEEE pulse, vol. 8, no. 4, pp. 54-57, 2017. https://doi.org/10.1109/MPUL.2017.2701493
  14. Q. Huang, Y. Chen, S. Liu, C. Xu, T. Cao, Y. Xu, X. Wang, G. Rao, A. Li, S. Zeng, et al., "Weakly supervised learning of 3d deep network for neuron reconstruction," Frontiers in Neuroanatomy, vol. 14, 2020.
  15. Y. Deng, Y. Chen, Y. Zhang, and S. Mahadevan, "Fuzzy dijkstra algorithm for shortest path problem under uncertain environment," Applied Soft Computing, vol. 12, no. 3, pp. 1231-1237, 2012. https://doi.org/10.1016/j.asoc.2011.11.011
  16. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," arXiv preprint arXiv:1412.6980, 2014.