Distinct Features for Detection of Pigment Epithelial Detachment using Machine Learning and Artificial Neural Network in Two-Dimensional Optical Coherence Tomography Images
Keywords:
Artificial Neural Network, Optical Coherence Tomography, Pigment Epithelial Detachment, Retinal Pigment Epithelium Layer, Machine Learning ClassifiersAbstract
Eye is the very important sense organ of the human body. Retinal diseases affect the normal people. Some of the retinal diseases are Macular hole, Macular Edema, Central series Retinopathy, Diabetic Retinopathy, Pigment Epithelial Detachment (PED) and Age Related Macular Degeneration (ARMD). Two types of Imaging techniques used to diagnose the Retinal diseases such as Fundus images and Optical coherence tomography (OCT) images. OCT is an imaging technique to provide high resolution images to accurate diagnose the Retinal diseases. PED is the one of the retinal diseases that found in the Retinal Pigment Epithelium(RPE) layer. The RPE layer is Elevated and forms arc shape due to PED. In this paper proposed to detect the PED using machine learning algorithms such as SVM (Support Vector Machine), Decision Tree(DT), Logistic Regression(LR), K- Nearest Neighbor (KNN) Classifiers and Artificial Neural Network(ANN). We used around 100 images taken from the OCT (Optical Coherence Tomography) modality and having similar properties. We proposed four novel features such as Maximum-Left-Height, Number-of-Left-Down-Points, Number-of-Right-Down-Points, and Maximum-Right-Height. For implementation process we used PYTHON and MATLAB. OCT images are affected by speckle noise. To remove the speckle noise we used Wiener filtering technique. In the segmentation process, to extract the RPE layer we used thresholding technique. Then these extracted features were used to train the machine learning algorithms and test the model for new input. Then, we calculated the metrics such as accuracy, sensitivity, specificity, precision and F1-score of the SVM, DT, LR, KNN classifiers and we also analysed ANN algorithm such as Back Propagation Neural Network (BPNN) and compared with the machine learning classifiers. The overall results demonstrate that the LR system has produced high accuracy. LR for 95% accuracy, 100% sensitivity, 90% specificity, 90% precision and 95% F1-score.
Downloads
References
Huang, D. et al, “Optical coherence tomography”, Science 254, 1178–1181 (1991).
Zayit-Soudry S et.al, “ A. Retinal pigment epithelial detachment”, Surv Ophthalmol 52, 227–243 (2007).
Lommatzsch A, Helmes B, Gutfleisch M and Spital G, “Serous pigment epithelial detachment in age-related macular degeneration comparison of different treatments”, Eye 23, 2163–2168 (2009).
Mrejen S, Sarraf D, Mukkamala S. K. and Freund K. B,” Multimodal imaging of pigment epithelial detachment a guide to evaluation”, Retina 33, 1735–1762 (2013).
Keane P. A. et. al, “Evaluation of age-related macular degeneration with optical coherence tomography”, Surv Ophthalmol 57, 389–414 (2012).
Masahiro Miura et.al , “ Evaluation of retinal pigment epithelium changes in serous pigment epithelial detachment in age related macular degeneration”, www.nature.com/scientificreports, 2021.
Poliner LS, Olk RJ, Burgess D, Gordon ME, “ Natural history of retinal pigment epithelial detachments in age-related macular degeneration”, Ophthalmology. 1986;93:543–551.
Pauleikhoff D, Loffert D, Spital G, et al., “Pigment epithelial detachment in the elderly. Clinical differentiation, natural course and pathogenetic implications”, Graefes Arch Clin Exp Ophthalmol. 2002;240:533–538.
Spaide RF, “Enhanced depth imaging optical coherence tomography of retinal pigment epithelial detachment in age-related macular degeneration”, Am J Ophthalmol. 2009;147:644 – 652.
Ojima Y, Hangai M, Sakamoto A, et al.,” Improved visualization of polypoidal vasculopathy lesions using spectral-domain optical coherence tomography”, Retina. 2009;29:52–59.
Smretschnig E, Krebs I, Moussa S, Ansari-Shahrezaei S, Binder S., “Cirrus OCT versus Spectralis OCT: differences in segmentation in fibrovascular pigment epithelial detachment”, Graefes Arch Clin Exp Ophthalmol. 2010;238:1693–1698.
Gupta V, Gupta P, Dogra MR, Singh R, Gupta A., “Morphological changes in the retinal pigment epithelium on spectral-domain OCT in the unaffected eyes with idiopathic central serous chorioretinopathy”, Int Ophthalmol. 2010;30:175–181.
Khanifar AA, Koreishi AF, Izatt JA, Toth CA., “Drusen ultrastructure imaging with spectral domain optical coherence tomography in age-related macular degeneration”,Ophthalmology 2008;115: 1883–1890.
Liakopoulos S, Ongchin S, Bansal A, et al., “Quantitative optical coherence tomography findings in various subtypes of neovascular age-related macular degeneration”, Invest Ophthalmol Vis Sci. 2008;49:5048 –5054.
Joeres S, Tsong J, Updike PG, et al., “Reproducibility of quantitative optical coherence tomography subanalysis in neovascular agerelated macular degeneration”, Invest Ophthalmol Vis Sci. 2007; 48:4300 – 4308.
Ahlers C, Simader C, Geitzenauser W, et al., “Automatic segmentation in three-dimensional analysis of fibrovascular pigment epithelial detachment using high-definition optical coherence tomography”, Br J Ophthalmol. 2008;92:197–203.
Penha FM, Rosenfeld PJ, Gregori G, et al., “Quantitative imaging of retinal pigment epithelial detachments using spectral-domain optical coherence tomography”, Am J Ophthalmol. Published online October 24, 2011.
Wilkins GR, Houghton OM, Oldenburg AL., “Automated segmentation of intrarentinal cystoid fluid in optical coherence tomography”, IEEE Trans Biomed Eng. 2013; 59 (4), pp. 1109–1114.
Wang C, Wang YX, Li Y,” Automatic choroidal layer segmentation using markov random field and level set method”, IEEE J. Biomed Heal Informatics. 2017; 21(6), pp. 1694–1702.
Niu S, Chen Q, L. de Sisternes, Rubin DL, Zhang W, Liu Q., “Automated retinal layers segmentation in SD-OCT images using dual-gradient and spatial correlation smoothness constraint”,ComputBiol Med. 2015; 5, pp. 116–128.
M. Anand, C. Jayakumari, “Automated Detection of Macular Hole in Optical Coherence Tomography Images using Depth-Check Algorithm”, International Journal of Engineering and Advanced Technology (IJEAT) ISSN: 2249 – 8958, Volume-9 Issue-1, October 2019.
M. Anand, C. Jayakumari,” A Novel Depth-Check Algorithm to Detect Macular Hole from Optical Coherence Tomography Images”, International Journal of Innovative Technology and Exploring Engineering (IJITEE) ISSN: 2278-3075, Volume-8 Issue-12, October 2019.
T.M. Sheeba and S. Albert Antony Raj ,” Analysis of Noise Removal Techniques on Retinal Optical Coherence Tomography Images”, (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 13, No. 9, 2022.
M. Anand, C. Jayakumari,” Automated detection of full thickness macular hole in optical coherence tomography images”, Journal of International Pharmaceutical Research, ISSN: 1674-0440.
M. Anand, C. Jayakumari,” A New Approach to Detect Macular Hole from Optical Coherence Tomography Images”, Indian Journal of Public Health Research & Development, July 2019, Vol.10, No. 7.
M Anand , T.M. Sheeba and A.S. Anshy Princella, “Detection of Retinal Diseases in Retinal Optical Coherence Tomography Images”, IEEE, ICEEICT 2023, pp. 2213-2219.
T.M. Sheeba and S. Albert Antony Raj and M. Anand, “Computational Intelligent Techniques and Analysis on Automated Retinal Layer Segmentation and Detection of Retinal Diseases”, IEEE, ICACCS 2023, 2023, pp. 2213–2219.
T.M. Sheeba and S. Albert Antony Raj and M. Anand, “ Analysis of Various Image Segmentation Techniques on Retinal OCT Images”, IEEE, ICAIS 2023, 2023, pp. 716–721.
T.M. Sheeba and S. Albert Antony Raj and M. Anand, “ Comparison of Machine Learning Algorithms for Pigment Epithelial Detachment Classification using Shape and Curvature Features”, IEEE, ICACRS 2022 - Proceedings, 2022, pp. 550–554.
T.M. Sheeba and S. Albert Antony Raj and M. Anand, “ Pigment Epithelial Detachment Detection: A Review of Imaging Techniques and Algorithms”, IEEE, ICACTA 2022, pp.1-8.
T.M. Sheeba and S. Albert Antony Raj and M. Anand, “Fluid Segmentation in Retinal OCT images with Pigment Epithelial Detachment”, IEEE, ICAEECI 2023.
Ana Maria,” Measures of Diagnostic Accuracy Basic Definitions”, EJIFCC. 2009; 19(4): 203-211.
RJ Hemalatha, V Vijayabaskarin, “Histogram Based Synovitis Scoring System Using Ultrasound Images of Rheumatoid Arthritis. Journal of Clinical and Diagnostic Research”, 2018; 12(8), pp. LC10-LC14.
Venkatraman and K M Sumathi, “A Study on Fluid based Retinal abnormalities Analysis from OCT Images using SVM Classifier”, ICACCS 2020 IEEE ,pp.86-89.
Guo J, Shi F, Zhu W, Chen H, Chen X., ”A framework for classification and segmentation of branch retinal artery occlusion in SD-OCT”, Prog Biomed Opt Imaging - Proc SPIE. 2016; 9784(7), pp. 3518–3527.
Hussain MA, Alauddin Bhuiyan, Andrew Turpin, Chi D. Luu, Theodre Smith R, Robyn H. Guymer, RamamohanraoKotagiri, “Automatic identification of pathology-distorted retinal layer boundaries using SDOCT imaging”, IEEE Trans Biomed Eng. 2017; 64(7), pp. 1638–1649.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
