نوع مقاله : مقاله کامل پژوهشی

نویسنده

استادیار، گروه بیوالکتریک، دانشکده‌ی مهندسی پزشکی، دانشگاه صنعتی سهند، تبریز، ایران

10.22041/ijbme.2022.545364.1741

چکیده

بررسی شهودی لایه‌های شبکیه در تصاویر برش‌نگاری همدوسی اپتیکی حوزه‌ی طیف (SD-OCT) یکی از روش‌های اصلی مورد استفاده‌ی پزشکان برای تشخیص بیماری‌های شبکیه است. این روش با چالش‌هایی مانند نویز، پیچیدگی تصاویر و نزدیکی لایه‌ّهای شبکیه مواجه می‌باشد. در سال‌های اخیر تشخیص خودکار بیماری‌های شبکیه‌ی چشم به یکی از موضوعات مهم بالینی در حوزه‌ی بینایی کامپیوتر تبدیل شده است. در این تحقیق روشی جدید برای طبقه‌بندی کارآمد چندکلاسه‌ی خودکار تصاویر SD-OCT ارائه شده که متشکل از پنج مرحله‌ی پیش‌پردازش، تشخیص لایه‌ها، استخراج ویژگی‌ها، کاهش بعد، و طبقه‌بندی تصویر است. بررسی شکل لایه‌ی RNFL و پیوند IS/OS به عنوان روشی بالینی در تصمیم‌گیری‌های پزشکان برای تشخیص بیماری‌های شبکیه موثر است. از این رو در این پژوهش با الهام از این روش تشخیص بالینی، لایه‌ی RNFL و پیوند IS/OS توسط روشی جدید مبتنی بر الگوریتم بهبود رگ فرنگی و گرادیان تصویر تشخیص داده شده است. سپس با استخراج و انتخاب انواعی از ویژگی‌های موثر از لایه‌ها، الگوریتمی بر پایه‌ی درخت تصمیم ترکیبی برای طبقه‌بندی تصاویر شبکیه پیشنهاد شده و در قالب یک نرم‌افزار کاربردی در متلب ارائه شده است. روش پیشنهادی روی تصاویر دو پایگاه داده‌ی شناخته شده‌ی دوک و کرمنی ارزیابی شده است. بر اساس ‌نتایج، دقت، حساسیت، اختصاصیت، درستی، نرخ منفی نادرست و معیار F1 روش پیشنهادی در پایگاه داده‌ی دوک به ترتیب برابر با 7/98، 8/98، 4/99، 1/99، 3/1 و 7/98 درصد و در پایگاه کرمنی به ترتیب برابر با 8/96، 7/96، 9/98، 4/98، 2/3 و 7/96 درصد است. نتایج نشان‌دهنده‌ی برتری روش پیشنهادی در مقایسه با سایر روش‌های مقایسه‌ای است. در مجموع به کارگیری ویژگی‌های کارآمد از لایه‌های تاثیرگذار شبکیه و توانمندی روش طبقه‌بندی، موجب ارتقای عمل‌کرد روش پیشنهادی در مقایسه با روش‌های پیچیده‌تر پیشین شده است. 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

An Efficient Method for Automatic Multi-Class Classification of SD-OCT Images of Human Eye Based on RNFL layer and the IS/OS Junction Detection and Ensemble Decision Tree

نویسنده [English]

  • Sina Shamekhi

Assistant Professor, Faculty of Biomedical Engineering, Sahand University of Technology, Tabriz, Iran

چکیده [English]

Intuitive examination of retinal layers in Spectral-Domain Optical Coherence Tomography (SD-OCT) images is one of the main methods used by physicians to diagnose retinal diseases. This method faces challenges such as noise and image complexity and the proximity of retinal layers. In recent years, the automatic diagnosis of retinal diseases has become an important clinical issue in computer vision. In this research, a new method for efficient multi-class automatic classification of SD-OCT images has been proposed. This method consists of five stages, preprocessing, layer recognition, feature extraction, and image classification. Examination of the shape of the RNFL layer and IS/OS junction as a clinical method is influential in physicians' decisions to diagnose retinal diseases. Therefore, in this study, inspired by this clinical diagnosis method, the RNFL layer, and the IS/OS junction have been detected by a new method based on the Frangi vessel enhancement algorithm and the gradient of the image. Then, by extracting and selecting several efficient features from the curves of the layers, an algorithm based on the ensemble decision tree has been proposed for classifying SD-OCT images of the retina and presented as a MATLAB application. The proposed method has been evaluated using images of two well-known databases of Duke and Kermany. Based on the results, precision, sensitivity, specificity, accuracy, miss rate and F1-score of the proposed method in Duke database were equal to 98.7, 98.8, 99.4, 99.1, 1.3, and 98.7, respectively, and in Kermany database were 96.8, 96.7, 98.9, 98.4, 3.2 and 96.7 respectively. The results show the superiority of the proposed method compared to other comparative methods. In summary, the use of efficient features of retinal effective layers and a powerful algorithm for classification has improved the performance of the proposed method compared to previous more complex methods.

کلیدواژه‌ها [English]

  • SD-OCT
  • Retina
  • Frangi
  • Ensemble Decision Tree
  • Classification
  1. P. Gupta, A. A. Herzlich, T. Sauer, and C.-C. Chan, "Retinal anatomy and pathology," Retinal Pharmacotherapeutics, vol. 55, pp. 7-17, 2016.
  2. H. Organization, "World report on vision," 2019.
  3. M. Alqudah, "AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images," Medical & biological engineering & computing, vol. 58, no. 1, pp. 41-53, 2020.
  4. Alqudah and A. M. Alqudah, "Artificial Intelligence Hybrid System for Enhancing Retinal Diseases Classification Using Automated Deep Features Extracted from OCT Images," International Journal of Intelligent Systems and Applications in Engineering, vol. 9, no. 3, pp. 91-100, 2021.
  5. فیضی, محدثه, پاکروان, and محمد, "آزمون‌های تشخیصی در نوروافتالمولوژی," مجله چشم‌پزشکی بینا, vol. 21, no. 3, pp. 285-294, 2016.
  6. P. Srinivasan et al., "Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images," Biomedical optics express, vol. 5, no. 10, pp. 3568-3577, 2014.
  7. A. Hussain et al., "Classification of healthy and diseased retina using SD-OCT imaging and Random Forest algorithm," PloS one, vol. 13, no. 6, p. e0198281, 2018.
  8. Herzog, K. L. Boyer, and C. Roberts, "Extracting the optic disk endpoints in optical coherence tomography data," in 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05)-Volume 1, 2005, vol. 1, pp. 263-268: IEEE.
  9. Bernardes, C. Maduro, P. Serranho, A. Araújo, S. Barbeiro, and J. Cunha-Vaz, "Improved adaptive complex diffusion despeckling filter," Optics express, vol. 18, no. 23, pp. 24048-24059, 2010.
  10. Usha, N. Shajil, and M. Sasikala, "Automatic Anisotropic Diffusion Filtering and Graph-search Segmentation of Macular Spectral-domain Optical Coherence Tomographic (SD-OCT) Images," Current Medical Imaging, vol. 15, no. 3, pp. 308-318, 2019.
  11. س. دانشور, "تشخیص ضایعات قرمز بیماری رتینوپاتی با استفاده از موجک مورلت در تصاویر رنگی شبکیه," کارشناسی ارشد, وزارت علوم، تحقیقات و فناوری - دانشگاه فردوسی مشهد - دانشکده مهندسی, 1391.
  12. م. تاجی and س. آیت, "تشخیص بیماری رتینوپاتی دیابت با استفاده از پردازش تصاویر فوندوس شبکیه و تکنیک‌های مورفولوژیک," (in persian), مجله انفورماتیک سلامت و زیست پزشکی, vol. 6, no. 3, pp. 218-230, 1398.
  13. Lemaître, M. Rastgoo, J. Massich, S. Sankar, F. Mériaudeau, and D. Sidibé, "Classification of SD-OCT Volumes with LBP: Application to DME Detection," presented at the Ophthalmic Medical Image Analysis Workshop (OMIA), Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015, Munich, Germany, 2015-10-05, 2015. Available: https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01235888
  14. Sidibe et al., "An anomaly detection approach for the identification of DME patients using spectral domain optical coherence tomography images," Computer methods and programs in biomedicine, vol. 139, pp. 109-117, 2017.
  15. S. Gerendas et al., "Computational image analysis for prognosis determination in DME," Vision research, vol. 139, pp. 204-210, 2017.
  16. Kermany, K. Zhang, and M. Goldbaum, "Labeled optical coherence tomography (oct) and chest X-ray images for classification," Mendeley data, vol. 2, no. 2, 2018.
  17. S. Kermany et al., "Identifying medical diagnoses and treatable diseases by image-based deep learning," Cell, vol. 172, no. 5, pp. 1122-1131. e9, 2018.
  18. Rong et al., "Surrogate-assisted retinal OCT image classification based on convolutional neural networks," IEEE journal of biomedical and health informatics, vol. 23, no. 1, pp. 253-263, 2018.
  19. Luo, Q. Xu, R. Jin, M. Wu, and L. Liu, "Automatic detection of retinopathy with optical coherence tomography images via a semi-supervised deep learning method," Biomedical Optics Express, vol. 12, no. 5, pp. 2684-2702, 2021.
  20. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever, "Multiscale vessel enhancement filtering," in International conference on medical image computing and computer-assisted intervention, 1998, pp. 130-137: Springer.
  21. Edge-aware local contrast manipulation of images. Available: https://www.mathworks.com/help/images/ref/localcontrast.html
  22. E. Shannon, "A mathematical theory of communication," The Bell system technical journal, vol. 27, no. 3, pp. 379-423, 1948.
  23. S. Richman and J. R. Moorman, "Physiological time-series analysis using approximate entropy and sample entropy," American Journal of Physiology-Heart and Circulatory Physiology, 2000.
  24. Rényi, Probability theory. Courier Corporation, 2007.
  25. Tsallis, R. Mendes, and A. R. Plastino, "The role of constraints within generalized nonextensive statistics," Physica A: Statistical Mechanics and its Applications, vol. 261, no. 3-4, pp. 534-554, 1998.
  26. M. Pincus, "Approximate entropy as a measure of system complexity," Proceedings of the National Academy of Sciences, vol. 88, no. 6, pp. 2297-2301, 1991.
  27. W. Harris and H. Stöcker, Handbook of mathematics and computational science. Springer Science & Business Media, 1998.
  28. Nielsen, "On the construction and frequency localization of finite orthogonal quadrature filters," Journal of Approximation Theory, vol. 108, no. 1, pp. 36-52, 2001.
  29. Song and P. Liò, "A new approach for epileptic seizure detection: sample entropy based feature extraction and extreme learning machine," Journal of Biomedical Science and Engineering, vol. 3, no. 06, p. 556, 2010.
  30. Borowska, "Entropy-based algorithms in the analysis of biomedical signals," Studies in Logic, Grammar and Rhetoric, vol. 43, no. 1, pp. 21-32, 2015.
  31. Ding and H. Peng, "Minimum redundancy feature selection from microarray gene expression data," Journal of bioinformatics and computational biology, vol. 3, no. 02, pp. 185-205, 2005.
  32. J. Tallarida and R. B. Murray, "Chi-square test," in Manual of pharmacologic calculations: Springer, 1987, pp. 140-142.
  33. Yang, K. Wang, and W. Zuo, "Neighborhood component feature selection for high-dimensional data," J. Comput., vol. 7, no. 1, pp. 161-168, 2012.
  34. Robnik-Šikonja and I. Kononenko, "An adaptation of Relief for attribute estimation in regression," in Machine Learning: Proceedings of the Fourteenth International Conference (ICML’97), 1997, vol. 5, pp. 296-304.
  35. T. Jolliffe and J. Cadima, "Principal component analysis: a review and recent developments," Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 374, no. 2065, p. 20150202, 2016.
  36. G. Dietterich, "Ensemble learning," The handbook of brain theory and neural networks, vol. 2, no. 1, pp. 110-125, 2002.
  37. Che, Q. Liu, K. Rasheed, and X. Tao, "Decision tree and ensemble learning algorithms with their applications in bioinformatics," Software tools and algorithms for biological systems, pp. 191-199, 2011.
  38. Breiman, "Bagging predictors," Machine learning, vol. 24, no. 2, pp. 123-140, 1996.
  39. -D. Li, M. Kallergi, L. P. Clarke, V. K. Jain, and R. A. Clark, "Markov random field for tumor detection in digital mammography," IEEE transactions on medical imaging, vol. 14, no. 3, pp. 565-576, 1995.
  40. Hossin and M. N. Sulaiman, "A review on evaluation metrics for data classification evaluations," International journal of data mining & knowledge management process, vol. 5, no. 2, p. 1, 2015.
  41. Fatourechi, R. K. Ward, S. G. Mason, J. Huggins, A. Schloegl, and G. E. Birch, "Comparison of evaluation metrics in classification applications with imbalanced datasets," in 2008 seventh international conference on machine learning and applications, 2008, pp. 777-782: IEEE.
  42. (11/10/2021). Karpathy Random Forest Matlab. Available: https://github.com/karpathy/Random-Forest-Matlab/blob/master/lib/
  43. Fang, Y. Jin, L. Huang, S. Guo, G. Zhao, and X. Chen, "Iterative fusion convolutional neural networks for classification of optical coherence tomography images," Journal of Visual Communication and Image Representation, vol. 59, pp. 327-333, 2019.