Data Augmentation Using Firefly and Level Sets Applied to Segmentation of Medical and Biological Images
Keywords:
Data Augmentation, Image Segmentation, Image ProcessingAbstract
It has been estimated that about 75 % of disease-associated genes in humans have homologs in Drosophila melanogaster. Despite recent advances in biological and medical image capture technologies, for counting collected cells in vivo, it is still necessary to make the manual supply process. On the other hand, convolutional networks have been advancing and obtaining good results, especially on bases with a large volume. This work proposes adapting a data augmentation technique, increasing a specific segmentation pipeline for confocal microscopy images, and uses the results in segmentation training using U-Net.
Downloads
References
Doi, K. (2007). Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Computerized medical imaging and graphics, 31(4-5):198–211.
Higham, J. P., Malik, B. R., Buhl, E., Dawson, J. M., Ogier, A. S., Lunnon, K., and Hodge, J. J. (2019). Alzheimer’s disease associated genes ankyrin and tau cause shortened lifespan and memory loss in drosophila. Frontiers in cellular neuroscience, 13.
Hirth, F. (2010). Drosophila melanogaster in the study of human neurodegeneration. CNS & Neurological Disorders-Drug Targets (Formerly Current Drug Targets-CNS & Neurological Disorders), 9(4):504–523.
Hughes, T. T., Allen, A. L., Bardin, J. E., Christian, M. N., Daimon, K., Dozier, K. D., Hansen, C. L., Holcomb, L. M., and Ahlander, J. (2012). Drosophila as a genetic model for studying pathogenic human viruses. Virology, 423(1):1–5.
Joia, P., Paulovich, F., Coimbra, D., Cuminato, J., and Nonato, L. (2011). Local affine multidimensional projection. IEEE transactions on visualization and computer graphics, 17:2563–71.
Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3431–3440.
Malladi, R., Sethian, J. A., and Vemuri, B. C. (1994). Shape modeling with front propagation: A level set approach.
Naturalis, P. (2018). 30 amazing applications of deep learning.
Palmeira, O. F. (2017). Efeitos da irradiação em células-tronco germinativas de drosophila melanogaster e influência da dieta na recuperação dessas células e tecidos ovarianos submetidos ao tratamento com cisplatina. Monografia apresentada ao Programa de Graduação em Ciências Biológicas: Biotecnologia, do Polo Avançado de Xerém, Universidade Federal do Rio de Janeiro. UFRJ.
Pandey, U. B. and Nichols, C. D. (2011). Human disease models in drosophila melanogaster and the role of the fly in therapeutic drug discovery. Pharmacological reviews, 63(2):411–436.
Peixinho, A. Z., Benato, B. C., Nonato, L. G., and Falcão, A. X. (2018). Delaunay triangulation data augmentation guided by visual analytics for deep learning. In 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 384–391. IEEE.
Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer.
Shorten, C. and Khoshgoftaar, T. M. (2019). A survey on image data augmentation for deep learning. Journal of Big Data, 6(1):60.
Sonoshita, M. and Cagan, R. (2017). Modeling human cancers in drosophila. In Current topics in developmental biology, volume 121, pages 287–309. Elsevier.
Stephens, D. J. and Allan, V. J. (2003). Light microscopy techniques for live cell imaging. science, 300(5616):82–86.
Wachs Lopes, G. A., Beltrame, F. S., Santos, R. M., and Rodrigues, P. S. (2018). Comparison of bio-inspired algorithms from the point of view of medical image segmentation. In 2018 IEEE International Work Conference on Bioinspired Intelligence (IWOBI), pages 1–7.
Yang, X.-S. (2009). Firefly algorithms for multimodal optimization. In SAGA.
