Convolutional Mixture of Experts Model: A Comparative Study on Automatic Macular Diagnosis in Retinal Optical Coherence Tomography Imaging
DOI: 10.4103/jmss.JMSS_27_17
Abstract
Background: Macular disorders, such as diabetic macular edema (DME) and age-related macular degeneration (AMD) are among the major ocular diseases. Having one of these diseases can lead to vision impairments or even permanent blindness in a not-so-long time span. So, the early diagnosis of these diseases are the main goals of eye researchers. Material and Methods: The present study is designed in order to present a comparative study on the recent convolutional mixture of experts (CMoE) models for distinguishing normal macular OCT from DME and AMD. For this purpose, we considered three recent CMoE models called Mixture ensemble of convolutional neural networks (MECNN), Multi-scale Convolutional Mixture of Experts (MCME), and Wavelet-based Convolutional Mixture of Experts (WCME) models. For this research study, the models were evaluated on a database of three different macular OCT sets. Two first OCT sets were acquired by Heidelberg imaging systems consisting of 148 and 45 subjects respectively and set3 was constituted of 384 Bioptigen OCT acquisitions. To provide better performance insight into the CMoE ensembles, we extensively analyzed the models based on the 5-fold cross-validation method and various classification measures such as precision and average area under the ROC curve (AUC). Results: Experimental evaluations showed that the MCME and WCME outperformed the ME-CNN model and presented overall precisions of 98.14% and 96.06% for aligned OCTs respectively. For non-aligned retinal OCTs, these values were 93.95% and 95.56%. Conclusion: Based on the comparative analysis, although the MCME model outperformed the other CMoE models in the analysis of aligned retinal OCTs, the WCME offers a robust model for diagnosis of non-aligned retinal OCTs. This allows having a fast and robust computer aided system in macular OCT imaging which does not rely on the routine computerized processes such as denoising, segmentation of retinal layers, and also retinal layers alignment.
Keywords
Full Text:
PDFReferences
Bressler NM. Age-related macular degeneration is the leading cause of blindness. JAMA 2004;291:1900-1.
Hirai FE, Knudtson MD, Klein BE, Klein R. Clinically significant macular edema and survival in type 1 and type 2 diabetes. Am J Ophthalmol 2008;145:700-6.
Liu YY, Chen M, Ishikawa H, Wollstein G, Schuman JS, Rehg JM, et al. Automated macular pathology diagnosis in retinal OCT images using multi-scale spatial pyramid and local binary patterns in texture and shape encoding. Med Image Anal 2011;15:748-59.
Schmidt-Erfurth U, Chong V, Loewenstein A, Larsen M, Souied E, Schlingemann R, et al. Guidelines for the management of neovascular age-related macular degeneration by the European Society of Retina Specialists (EURETINA). Br J Ophthalmol 2014;98:1144-67.
Hee MR, Izatt JA, Swanson EA, Huang D, Schuman JS, Lin CP, et al. Optical coherence tomography of the human retina. Arch Ophthalmol 1995;113:325-32.
Fujimoto JG. Optical coherence tomography for ultrahigh resolution in vivo imaging. Nat Biotechnol 2003;21:1361-7.
Rasti R, Rabbani H, Mehridehnavi A, Kafieh R. Discrimination between diabetic macular edema and normal retinal OCT B-scan images based on convolutional neural networks. In: IEEE Workshop on Multimedia Signal Processing (MMSP). Montreal, Canada; 2016.
Farsiu S, Chiu SJ, O'Connell RV, Folgar FA, Yuan E, Izatt JA, et al. Quantitative classification of eyes with and without intermediate age-related macular degeneration using optical coherence tomography. Ophthalmology 2014;121:162-72.
Srinivasan PP, Kim LA, Mettu PS, Cousins SW, Comer GM, Izatt JA, et al. Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. Biomed Opt Express 2014;5:3568-77.
Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process 2007;16:2080-95.
Sugmk J, Kiattisin S, Leelasantitham A. Automated classification between age-related macular degeneration and diabetic macular edema in OCT image using image segmentation. In: Biomedical Engineering International Conference (BMEiCON). 7th ed. IEEE. Fukuoka, Japan; 2014. p. 1-4.
Apostolopoulos S, Ciller C, De Zanet SI, Wolf S, Sznitman R. RetiNet: Automatic AMD identification in OCT volumetric data. ArXiv preprint arXiv:1610.03628; 2016.
Hassan B, Raja G, Hassan T, Usman Akram M. Structure tensor based automated detection of macular edema and central serous retinopathy using optical coherence tomography images. J Opt Soc Am A Opt Image Sci Vis 2016;33:455-63.
Sun Y, Li S, Sun Z. Fully automated macular pathology detection in retina optical coherence tomography images using sparse coding and dictionary learning. J Biomed Opt 2017;22:16012.
Rasti R, Mehridehnavi A, Rabbani H, Hajizadeh F. Automatic diagnosis of abnormal macula in retinal optical coherence tomography images using wavelet-based convolutional neural network features and random forests classifier. J Biomed Opt 2018;23:1-10.
Rasti R, Rabbani H, Mehridehnavi A, Hajizadeh F. Macular OCT classification using a multi-scale convolutional neural network ensemble. IEEE Trans Med Imaging 2018;37:1024-34.
Rasti R, Mehridehnavi A, Rabbani H, Hajizadeh F. Wavelet-based convolutional mixture of experts model: An application to automatic diagnosis of abnormal macula in retinal optical coherence tomography images. In: Machine Vision and Image Processing (MVIP), 2017 10th Iranian Conference on, Isfahan-Iran; 2017. p. 192-6.
Soille P. Morphological Image Analysis: Principles and Applications. Springer Berlin Heidelberg: Springer Science & Business Media; 2013.
Fang L, Li S, Nie Q, Izatt JA, Toth CA, Farsiu S, et al. Sparsity based denoising of spectral domain optical coherence tomography images. Biomed Opt Express 2012;3:927-42.
Kafieh R, Rabbani H, Abramoff MD, Sonka M. Curvature correction of retinal OCTs using graph-based geometry detection. Phys Med Biol 2013;58:2925-38.
LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE. Vol. 86. 1998. p. 2278-324.
Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning. Lille, France; 2015. p. 448-56.
Srivastava N. Improving Neural Networks with Dropout. Vol. 182. University of Toronto; 2013.
Rasti R, Teshnehlab M, Jafari R. A CAD system for identification and classification of breast cancer tumors in DCE-MR images based on hierarchical convolutional neural networks. Computational Intelligence in Electrical Engineering. Vol. 6. University of Isfahan, Isfahan; 2015. p. 1-14.
Rasti R, Teshnehlab M, Phung SL. Breast cancer diagnosis in DCE-MRI using mixture ensemble of convolutional neural networks. Pattern Recognit 2017;72:381-90.
Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE. Adaptive mixtures of local experts. Neural Comput 1991;3:79-87.
Burt PJ, Adelson EH. The Laplacian pyramid as a compact image code. In: Readings in Computer Vision. Morgan Kaufmann; 1st ed. Elsevier; 1987. p. 671-9.
Chui CK. An Introduction to Wavelets. Elsevier; San Diego, USA. 2016.
Hinton G, Srivastava N, Swersky K. Lecture 6a Overview of Mini – Batch Gradient Descent. Coursera Lecture Slides; 2012. Available from: https://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf. [Last accessed on 2017 Jun 18].
Powers DM. Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. J Mach Learn Technol2011;2:37-63.
Fawcett T. An introduction to ROC analysis. Pattern Recognit Lett 2006;27:861-74.
Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Meas 1960;20:37-46.
Team TT, Al-Rfou R, Alain G, Almahairi A, Angermueller C, Bahdanau D, et al. Theano: A python framework for fast computation of mathematical expressions. ArXiv preprint arXiv:1605.02688; 2016. Available from: https://github.com/keras-team/keras. [Last accessed on 2017 Jun 18].
Chollet F. Keras. In: GitHub Repository. GitHub; 2015.
Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Sardinia, Italy; 2010. p. 249-56.
Refbacks
- There are currently no refbacks.
https://e-rasaneh.ir/Certificate/22728
ISSN : 2228-7477