Using of deep learning in the task of diagnosing diseases using optical coherence tomography images

Authors: Tsykunov D.V., Moiseeva V.A.
Published in issue: #12(29)/2018
DOI: 10.18698/2541-8009-2018-12-416
Category: Medical sciences | Chapter: Medical equipment and devices
Keywords: optical coherent tomography, deep learning, convolutional neural networks, artificial intelligence, image classification, choroidal neovascularization, diabetic retinopathy, retina
Published: 17.12.2018

Nowadays artificial intelligence technologies play a very important role in the development of many fields of science, including medicine. In this article considers the possibility of using deep convolutional neural networks to solve the problem of image classification of optical coherent tomography. In the process of developing a model, a method of transfer learning was used. As a result, a convolutional neural network was trained, the accuracy of which in the test sample is 99.5%. This result shows that using of deep learning in the tasks of diagnosis can play a large role in the mass diagnosis of patients.

References

[1] Goldbaum M., Moezzi S., Taylor A., Chatterjee S., Boyd J., Hunter E., Jain R. Automated diagnosis and image understanding with object extraction, object classification, and inferencing in retinal images. Proc. 3rd IEEE Int. Conf. Imaging, 1996, vol. 3, pp. 695–698.

[2] Hoover A., Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels. IEEE Trans. Med. Imaging, 2003, vol. 22, no. 8, pp. 951–958.

[3] Hoover A., Kouznetsova V., Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans. Med. Imaging, 2000, vol. 19, no. 1, pp. 203–210.

[4] Sikorskiy O.S. Review on grid neuron networks for image classification problem. Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh, 2017, no. 20, pp. 37–42.

[5] LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proc. IEEE, 1998, vol. 86, no. 11, pp. 2278–2324

[6] Russakovsky O., Deng J., Su H., Krause J., Satheesh S., Ma S., Huang Z., Karpathy A., Khosla A., Bernstein M., Berg A.C., Fei-Feiand L. Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 2015, vol. 115, no. 3, pp. 211–252.

[7] Shie Ch.K., Chuang Ch.H., Chou Ch.N., Wu M.H., Chang E.Y. Transfer representation learning for medical image analysis. 37th Annual Int. Conf. IEEE EMBC, 2015, pp. 711–714.

[8] Kermany D.S., Goldbaum M., Cai W., et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 2018, vol. 172, no. 5, pp. 1122–1131-e9.

[9] Kermany D., Zhang K., Goldbaum M. Labeled optical coherence tomography (OCT) and chest X-Ray images for classification. Version 2. Available at: https://data.mendeley.com/datasets/rscbjbr9sj/2 (accessed: 28 August 2018).

[10] Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. Available at: https://arxiv.org/abs/1409.1556 (accessed: 28 August 2018).