Multilayered Deep Structure Tensor Delaunay Triangulation and Morphing Based Automated Diagnosis and 3D Presentation of Human Macula
- 38 Downloads
Maculopathy is the group of diseases that affects central vision of a person and they are often associated with diabetes. Many researchers reported automated diagnosis of maculopathy from optical coherence tomography (OCT) images. However, to the best of our knowledge there is no literature that presents a complete 3D suite for the extraction as well as diagnosis of macula. Therefore, this paper presents a multilayered convolutional neural networks (CNN) structure tensor Delaunay triangulation and morphing based fully autonomous system that extracts up to nine retinal and choroidal layers along with the macular fluids. Furthermore, the proposed system utilizes the extracted retinal information for the automated diagnosis of maculopathy as well as for the robust reconstruction of 3D macula of retina. The proposed system has been validated on 41,921 retinal OCT scans acquired from different OCT machines and it significantly outperformed existing state of the art solutions by achieving the mean accuracy of 95.27% for extracting retinal and choroidal layers, mean dice coefficient of 0.90 for extracting fluid pathology and the overall accuracy of 96.07% for maculopathy diagnosis. To the best of our knowledge, the proposed framework is first of its kind that provides a fully automated and complete 3D integrated solution for the extraction of candidate macula along with its fully automated diagnosis against different macular syndromes.
KeywordsOptical coherence tomography Image processing Ophthalmology Pattern recognition Neural networks
We are thankful to AFIO, Rawalpindi and Amanat Eye Hospital, Rawalpindi for providing us the dataset. We are also thankful to Vision and Image Processing Lab, Duke University for making their OCT datasets publicly available.
This work has been funded by Ignite National Technology Fund, Ministry of Information Technology, Government of Pakistan.
Compliance with Ethical Standards
Conflict of Interest
All authors declare that they don’t have any conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- 2."Implant gives rats sixth sense for infrared light". Wired UK. 14 February 2013. Accessed 14 February 2013.Google Scholar
- 3.Comers, G. M., Cystoid macular edema, Kellog Eye Center, Accessed June 2016.Google Scholar
- 5.Saine P. J., Fundus Photography: What is a Fundus Camera? Ophthalmic Photographers Society Accessed March 30th, 2018.Google Scholar
- 6.Schuman, J. S., Introduction to Optical Coherence Tomography Technology.Google Scholar
- 7.Shrestha, A., Maharjan, N., Shrestha, A., Thapa, R., and Poudyal, G., Optical Coherence Tomographic assessment of macular thickness and morphological patterns in diabetic macular edema: Prognosis after modified grid photocoagulation. Nepal J. Ophthalmol. 4(7):128–133, 2012.Google Scholar
- 8.Zhang, W., Yamamoto, K., and Hori, S., Optical Coherence Tomography for assessment of diabetic macular edema. Int. J. Opthalmol. 1, December 18, 2008.Google Scholar
- 10.Mokwa, N. F., Ristau, T., Keane, P. A., Kirchhoff, B., Sadda, S. R., and Liakopoulos, S., Diagnosis of age-related macular degeneration: comparison between color fundus photography, fluorescein angiography, and spectral domain optical coherence tomography. J. Ophthalmol. 2013:6, 2013), Article ID 85915.CrossRefGoogle Scholar
- 11.Georgieva, D. K., Optical coherence tomography findings in diabetic macular edema, February 24, 2012.Google Scholar
- 12.Helmy, Y. M., and Atta Allah, H. R., Optical coherence tomography classification of diabetic cystoid macular edema. Clinical Ophthalmology - Dove press, August 27, 2013.Google Scholar
- 13.Virgili, G., Menchini, F., Murro, V., Peluso, E., Rosa, F., Casazza, G., Optical coherence tomography (OCT) for detection of macular oedema in patients with diabetic retinopathy. Cochrane Database Syst. Rev. Jul 6;(7): CD008081. doi: https://doi.org/10.1002/14651858, 2011.
- 17.Hee, M. R., Puliafito, C. A., Duker, J. S., Reichel, E., Coker, J. G., Wilkins, J. R., Schuman, J. S., Swanson, E. A., Fujimoto, J. G., Topography of diabetic macular edema with optical coherence tomography, Elsevier J Ophthalmol.. doi: https://doi.org/10.1016/S0161-6420(98)93601-6, 14 March 2005.CrossRefGoogle Scholar
- 18.Zhang, L., Zhu, W., Shi, F., Chen, H., and Chen, X., Automated segmentation of intra-retinal cystoid macular edema for retinal 3D OCT images with macular hole. Int. Symp. Biomed. Imag. 12:1494–1497, 2015.Google Scholar
- 20.Sugruk, J., Kiattisin, S., and Lasantitham, A. L., Automated classification between age-related macular degeneration and diabetic macular edema in OCT image using image segmentation. IEEE Biomed. Eng. Int. Conf. 2014.Google Scholar
- 21.Hassan, B., and Raja, G., Fully automated assessment of macular edema using optical coherence tomography (OCT) images. 2016 Int Conf Intell. Syst. Eng. (ICISE), 15th – 17th January 2016.Google Scholar
- 25.Abhishek, A. M., Berendschot, T. T., Rao, S. V., and Dabir, S., Segmentation and analysis of retinal layers (ILM & RPE) in optical coherence tomography images with edema. IEEE Conf. Biomed. Eng. Sci. (IECBES). 204-209, 2014Google Scholar
- 28.Srinivasan, P. P., Kim, L. A., Mettu, P. S., Cousins, S. W., Comer, G. M., Izatt, J. A., and Farsiu, S., Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. Biomed. Opt. Express 5(10). https://doi.org/10.1364/BOE.5.003568, 12 Sep 2014.CrossRefGoogle Scholar
- 31.Rashno, A., Koozekanani, D. D., Drayna, P. M., Nazari, B., Sadri, S., Rabbani, H., Parhi, K. K., Fully-automated segmentation of fluid/cyst regions in optical coherence tomography images with diabetic macular edema using neutrosophic sets and graph algorithms. IEEE Trans. Biomed. Eng., vol. PP, no. 99, pp. 1-1, 2017.Google Scholar
- 32.Lee, C. S., Tyring, A. J., Deruyter, N. P., Wu, Y., Rokem, A., and Lee, A. Y., Deep-learning based, automated segmentation of macular edema in optical coherence tomography. Biomed. Opt. Express 8(7), 2017.Google Scholar
- 36.Badrinarayanan, V., Kendall, A., and Cipolla, R.. SegNet: A deep convolutional encoder-decoder architecture for image segmentation. arXiv preprint arXiv: 1511.00561, 2015.Google Scholar
- 37.Krizhevsky, A., Sutskever, I., Hinton, G. E., imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems (NIPS), 2012.Google Scholar
- 39.Delaunay, B., "Sur la sphère vide", Bulletin de l'Académie des Sciences de l'URSS. Classe des sciences mathématiques et naturelles. 6:793–800, 1934.Google Scholar
- 41.Bengio, Y., Practical recommendations for gradient based training of deep architectures. Neural Networks: Tricks of the Trade, Springer, 437-478, 2012.Google Scholar
- 42.Murguia, M., and Villasenor, J. L., Estimating the effect of the similarity coefficient and the cluster algorithm on biogeographic classifications. Ann. Bot. Fennici. 40:415–421, 2003.Google Scholar