Identification and segmentation of myelinated nerve fibers in a cross-sectional optical microscopic image using a deep learning model

Journal of Neuroscience Methods

Volumn 291, Issue , 2017, Pages 141-149

  Naito, Tatsuhiko ^a   Nagashima, Yu ^a   Taira, Kenichiro ^a   Uchio, Naohiro ^a   Tsuji, Shoji ^a   Shimizu, Jun ^a  

^a UNIVERSITY OF TOKYO HOSPITAL   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

ADOLESCENT; ADULT; AGED; ARTICLE; CONVOLUTIONAL NEURAL NETWORK; CROSS-SECTIONAL STUDY; FEMALE; HUMAN; HUMAN TISSUE; IMAGE ANALYSIS; IMAGE SEGMENTATION; LEARNING ALGORITHM; MALE; MICROSCOPY; MIDDLE AGED; MYELIN SHEATH; MYELINATED NERVE; NERVE BIOPSY; NONMYELINATED NERVE; PRIORITY JOURNAL; SCHWANN CELL; SURAL NERVE; AUTOMATED PATTERN RECOGNITION; BIOPSY; CYTOLOGY; IMAGE PROCESSING; MACHINE LEARNING; PATHOLOGY; PROCEDURES;

ADOLESCENT; ADULT; AGED; BIOPSY; FEMALE; HUMANS; IMAGE PROCESSING, COMPUTER-ASSISTED; MACHINE LEARNING; MALE; MICROSCOPY; MIDDLE AGED; NERVE FIBERS, MYELINATED; PATTERN RECOGNITION, AUTOMATED; SURAL NERVE;

EID: 85028066929     PISSN: 01650270     EISSN: 1872678X     Source Type: Journal    
DOI: 10.1016/j.jneumeth.2017.08.014     Document Type: Article

References (29)

1. Said, G., Indications and usefulness of nerve biopsy. Arch. Neurol. 59 (2002), 1532–1535.
2. O'Sullivan, D.J., Swallow, M., The fibre size and content of the radial and sural nerves. J. Neurol. Neurosurg. Psychiatry 31 (1968), 464–470.
3. Koike, H., Misu, K., Sugiura, M., et al. Pathology of early- vs late-onset TTR Met30 familial amyloid polyneuropathy. Neurology 63 (2004), 129–138.
4. Ceballos, D., Cuadras, J., Verdu, E., Navarro, X., Morphometric and ultrastructural changes with ageing in mouse peripheral nerve. J. Anal. 195 (1999), 563–576.
5. Schröder, J.M., Altered ratio between axon diameter and myelin sheath thickness in regenerated nerve fibers. Brain Res. 45 (1972), 49–65.
6. Mackinnon, S.E., Dellon, A.L., Hudson, A.R., Hunter, D.A., Chronic nerve compression − an experimental model in the rat. Ann. Plast. Surg. 13 (1984), 112–120.
7. Oliveira, F.S., Nessler, R.A., Castania, J.A., Salgado, H.C., Fazan, V.P.S., Ultrastructural and morphometric alterations in the aortic depressor nerve of rats due to long term experimental diabetes: effects of insulin treatment. Brain Res. 1491 (2013), 197–203.
8. da Silva, G.A.R., Mendes, V.A., de Genari, A.B., Castania, J.A., Salgado, H.C., Fazan, V.P.S., Recurrent laryngeal nerve alterations in developing spontaneously hypertensive rats. Laryngoscope 126 (2016), E40–E47.
9. Silva da, A.P.D., Jordão, C.E.R., Fazan, V.P.S., Peripheral nerve morphometry: comparison between manual and semi-automated methods in the analysis of a small nerve. J. Neurosci. Methods 159 (2007), 153–157.
10. More, H.L., Chen, J., Gibson, E., Donelan, J.M., Beg, M.F., A semi-automated method for identifying and measuring myelinated nerve fibers in scanning electron microscope images. J. Neurosci. Methods 201 (2011), 149–158.
11. Isaacs, J., Mallu, S., Batchelor, M., Modification of commercially available image analysis software for semi-automated qualitative analysis of axon regeneration and myelination in the rat sciatic nerve. J. Neurosci. Methods 233 (2014), 45–49.
12. Campadelli, P., Gangai, C., Pasquale, F., Automated morphometric analysis in peripheral neuropathies. Comput. Biol. Med. 29 (1999), 147–156.
13. Romero, E., Cuisenaire, O., Denef, J.F., Delbeke, J., Macq, C.V.B., Automatic morphometry of nerve histological sections. J. Neurosci. Methods 97 (2000), 111–122.
14. Wang, Y.Y., Sun, Y.N., Lin, C.C., Ju, M.S., Segmentation of nerve fibers using multi-level gradient watershed and fuzzy systems. Artif. Intell. Med. 54 (2012), 189–200.
15. Novas, R.B., Fazan, V.P.S., Felipe, J.C., Fully-automatic tool for morphometric analysis of myelinated fibers. Comput. Med. Syst., 2013.
16. Novas, R.B., Fazan, V.P., Felipe, J.C., A new method for automated identification and morphometry of myelinated fibers through light microscopy image analysis. J. Digit. Imaging 29 (2016), 63–72.
17. Fok, Y., Chan, J.C.K., Chin, R.T., Automated analysis of nerve-Cell images using active contour models. IEEE Trans. Med. Imaging, 15, 1996.
18. Uchiyama, T., Arbib, M.A., Color image segmentation using competitive learning. IEEE Trans. Pattern Anal. Mach. Intell. 16 (1994), 1197–1206.
19. Behse, F., Buchthal, F., Carlsen, F., Knappeis, G., Unmyelinated fibres and Schwann cells of sural nerve in neuropathy. Brain 93 (1975), 493–510.
20. Krizhevsky, A., Sutskever, I., Hinton, G.E., ImageNet classification with deep convolutional neural networks. NIPS Proc., 2012, 1097–1105.
21. Suzuki, S., be, K., Topological structural analysis of digitized binary images by border following. Comput. Vision, Graph. Image Process. 30 (1985), 32–46.
22. Krizhevsky, A., Learning Multiple Layers of Features from Tiny Images M.S. Thesis. 2009, Dept. Comp. Sci., Univ. Toronto, Toronto, Canada.
23. Kingma, D., Ba, J., Adam: A Method for Stochastic Optimization. ArXiv:1412.6980 [cs.LG]. 2014, 1–15.
24. Ioffe, S., Szegedy, C., Batch normalization: accelerating deep network training by reducing internal covariate shift. J. Mach. Learn. Res., 2015, 37.
25. Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15 (2014), 1929–1958.
26. Tokui, S., Oono, K., Hido, S., Clayton, J., Chainer: a next-Generation open source framework for deep learning. Proc. Work. Mach. Learn. Syst. Twenty-ninth Annu. Conf. Neural Inf. Process. Syst., 2015, 1–6.
27. Simard, P.Y., Steinkraus, D., Platt, J.C., Best practices for convolutional neural networks applied to visual document analysis. Doc. Anal. Recognition, 2003. Proceedings. Seventh Int. Conf., 2003, 958–963.
28. Kumar, S., Ong, S.H., Ranganath, S., Ong, T.C., Chew, F.T., A rule-based approach for robust clump splitting. Pattern Recognit. 39 (2006), 1088–1098.
29. Bland, J., Altman, D., Statistical methods for assessing agreement between two methods for clinical measurement. Lancet 327 (1986), 307–310.