RECONSTRUCTION AND SEPARATION OF 3D NEURON USING RANDOM FOREST ALGORITHM

Authors

  • D. Vasanthi IFET College of Engineering, Villupuram, Tamil Nadu, India Author

DOI:

https://doi.org/10.61841/dth0rp02

Keywords:

Image segmentation, Spatial filter,, Patch extraction,, Neuron Reconstruction,, Image Classification,, Random forest algorithm.

Abstract

Digital reconstruction (or) tracing 3-dimensional neuron structure with optical microscopy images is a primary approach for characterizing the 3-dimensional neuron, which is very important for understanding the brain functions. It is more difficult when the images are contaminated by the noise and it is very challenging tasks when the neuron images having the discontinued segments of neuron pattern. While the existing algorithm works only for the single clean neuron image and does not classify the neuron and the surrounding nerve fibres. Here, the proposed method of 3-dimensional neuron segmentation using the spatial filter, Patch extraction and classification using the random forest algorithm. This segmentation process helps to reduce and remove the noise in neuron image, so the 3-dimensional neuron tracing performance will be improved. Then the neuron and nerve fibre are separated by using the random forest algorithm. The experimental results showed that the proposed method has accurate results when compared with the other reconstruction algorithm.

 

Downloads

Download data is not yet available.

References

[1] S. Liu, D. Zhand, Y. Song, et al. “Automated 3D Neuron Tracing with Precise Branch Erasing and Confidence Controlled Back-Tracking,” IEEE Transactions on Medical Imaging, vol. 37, no. 1, pp. 2441C-2452, 2018.

[2] L. Chen, G. Papandreou, I. Kokkinos, et al. “Deep Lab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 4, pp. 834–848, 2018.

[3] L. Chen, Y. Zhu, G. Papandreou, et al. “Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation,” arXiv preprint arXiv:1802.02611, 2018.

[4] Q. Aou, H.Chen, et al“3D deeply supervised for automated segmentation of volumetric medical images,” Medical Image Analysis, vol. 41, pp. 40–54, Oct. 2017.

[5] H. Peng, Z. Zhou, E. Meijering, et al. “Automatic tracing of ultravolumes34 of neuronal images,” Nature Methods, vol. 14, no. 4, pp. 332– 333, 2017.

[6] H. Peng, Z. Zhou, E. Meijering, et al. “Automatic tracing of ultravolumes of neuronal images,” Nature Methods, vol. 14, no. 4, pp. 332– 333, 2017.

[7] R. Li, T. Zeng, H. Peng, et al. “Deep Learning Segmentation of Optical Microscopy Images Improves 3D Neuron Reconstruction,” IEEE Transactions on Medical Imaging, vol. 36, no. 7, pp. 1533–1541, 2017.

[8] S. Liu, D. Zhang, S. Liu, et al. “Rivulet: 3D Neuron Morphology Tracing with Iterative Back-Tracking,” Neuro informatics, vol. 14, no. 4, pp. 387– 401, 2016.

[9] G. Ros, L. Sellart, J. Materzynska, et al. “The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 9, pp. 3234–3243, 2016.

[10].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.

[11].A. Fakhry, H. Peng, and S. Ji, “Deep models for brain EM image segmentation: novel insights and improved performance,” Bioinformatics, vol. 32, pp. 2352–2358, 2016.

[12].Y. Wan, F. Long, L. Qu, H. Xiao, M. Hawrylycz, E. W. Myers, and H. Peng, “Blast Neuron for automated comparison, retrieval and clustering of 3d neuron morphologies,” Neuro informatics, vol. 13, no. 4, pp. 487–499, 2015.

[13].H. Chen, H. Xiao, T. Liu, and H. Peng, “Smart Tracing: self- learning-based neuron reconstruction,” Brain Informatics, vol. 2, no. 3, pp. 135–144, 2015.

[14] H. Chen, X. Hang, T. Liu, et al. “Smart Tracing: self-learning-based neuron reconstruction,” Brain Informatics, vol. 2, no. 3, pp. 135–144, 2015.

[15] H. Xiao, H. Peng. “APP2: automatic tracing of 3D neuron morphology based on hierarchical pruning of a gray-weighted image distance-tree,” Bioinformatics, vol. 29, no. 11, pp. 1448–1454, 2013.

[16] J. Wu, Y. He, Z. Yang, et al. “3D Brain CV: simultaneous visualization and analysis of cells and capillaries in a whole mouse brain with one-micron voxel resolution,” Neuroimage, vol. 87, no. 2, pp. 199–208, 2014.

[17] H. Xiao, H. Peng. “APP2: automatic tracing of 3D neuron morphology based on hierarchical pruning of a gray-weighted image distance-tree,” Bioinformatics, vol. 29, no. 11, pp. 1448–1454, 2013.

Downloads

Published

30.06.2020

How to Cite

Vasanthi, D. (2020). RECONSTRUCTION AND SEPARATION OF 3D NEURON USING RANDOM FOREST ALGORITHM. International Journal of Psychosocial Rehabilitation, 24(4), 9554-9560. https://doi.org/10.61841/dth0rp02