Deteksi Glaukoma Menggunakan Metode Convolutional Neural Network Dan Grabcut Segmentation
DOI:
https://doi.org/10.34818/eoe.v9i3.17987Abstract
Abstrak Glaukoma adalah jenis gangguan yang menyerang penglihatan. Glaukoma terjadi karena kerusakan saraf optik yang dapat menyebabkan kebutaan. Cara yang dapat dilakukan untuk mendeteksi glaukoma adalah melalui gambar retina. Ada banyak cara untuk memproses gambar retina sebelum dapat mendeteksi glaukoma. Proses ini sangat penting karena dapat mempengaruhi tingkat keberhasilan sistem pendeteksian glaukoma. Dalam penelitian ini, kami menggunakan Convolution Neural Network sebagai metode klasifikasi. Gambaran retina dibagi menjadi dua kelas, yaitu glaukoma positif dan negatif. kemudian kami menerapkan metode Contrast Limited Adaptive Histogram Equalization (CLAHE) dan segmentasi Grabcut. Hasil akurasi tertinggi dengan menggunakan data uji pada percobaan ini adalah 75.71%, precision sebesar 75.47%, recall sebesar 76.19%, dan F1- score sebesar 75.82% untuk arsitektur CNN InceptionV3. Kata kunci: convolutional neural network, CLAHE, pemrosesan gambar, segmentasi grabcutReferences
[1]. Tham. Y. C., Li. X, Wong. T. Y, Quigley. H. A, Aung. T, dan Cheng. C. Y. 2014. Global prevalence of glaucoma and projections of glaucoma burden through 2040. a systematic review and meta-analysis. Ophthalmology. 2014 Nov, 121(11), 2081-90. Doi: 10.1016/j.ophtha.2014.05.013.
[2]. Indonesia, 2019. INFODATIN Pusat Data dan Informasi Kementrian Kesehatan RI Situasi Glaukoma di Indonesia. Kementrian Kesehatan RI, Jakarta, Indonesia.
[3]. D. Yadav, M. P. Sarathi dan M. K. Dutta. 2014. "Classification of glaucoma based on texture features using neural networks," 2014 Seventh International Conference on Contemporary Computing (IC3), 2014, pp. 109-112, doi: 10.1109/IC3.2014.6897157.
[4]. Ahmad, M., M. P., Sarathi,, dan M. K., Dutta. (2016). Deteksi Penyakit Glaukoma pada Citra Fundus Retina Mata Menggunakan Adaptive Thresholding dan Support vector machine. JURNAL TEKNIK ITS Vol.5, No. 2. Doi: 10.12962/j23373539.v5i2.18929.
[5]. S. Adatrao dan M. Mittal. 2016. "An analysis of different image preprocessing techniques for determining the centroids of circular marks using hough transform." 2016 2nd International Conference on Frontiers of Signal Processing (ICFSP). pp. 110-115. doi: 10.1109/ICFSP.2016.7802966.
[6]. Tran. N. M., Mathieu. Sinn, Hoang. T. L, dan Martin. W. 2018. Automated Image Data Preprocessing with Deep Reinforcement Learning. [Online] Available at: https://arxiv.org/abs/1806.05886 (Accessed on December 25, 2021).
[7]. Keiron. O., dan Ryan, N. 2015. An Introduction to Convolutional Neural Networks. . [Online] Available at: https://arxiv.org/abs/1511.08458(Accessed on December 21, 2021).
[8]. F. Iraldi and W. F. Al Maki. 2021 "Damage Classification on Roads Using Machine Learning," 2021 International Conference on Data Science and Its Applications (ICoDSA). pp. 151-156. doi: 10.1109/ICoDSA53588.2021.9617520.
[9]. Purnawarman, M., F. Al Rafi, dan M. Lamsani. 2018. A Review: Contrast-Limited Adaptive Histogram Equalization (CLAHE) methods to help the application of face recognition. Third International Conference on Informatics and Computing (ICIC), pp. 1-6. Doi: 10.1109/IAC.2018.8780492.
[10]. Garima. Y., S. Maheshwari, dan A. Agarwal. (2014). Contrast limited adaptive histogram equalization based enhancement for real time video system. 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 2392-2397. Doi: 10.1109/ICACCI.2014.6968381.
[11]. Rosebrock, A. 2020. OpenCV GrabCut: Foreground Segmentation and Extraction. [Online] Available at: https://www.pyimagesearch.com/2020/07/27/opencv-grabcut-foreground-segmentation-and-extraction/ [Accessed 28 Januari 2022].
[12]. Tianmei. G, J. Dong, H. Li dan Y. Gao. 2017. Simple convolutional neural network on image classification. 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA). pp. 721-724’ doi: 10.1109/ICBDA.2017.8078730.
[13]. ASHWINI. R dan Shintal. . 2019. Deep Neural Network Regularization for Feature Selection in Learning-to-Rank. in IEEE Access, vol. 7, pp. 53988-54006. doi: 10.1109/ACCESS.2019.2902640.
[14]. Nitish. S., Geoffrey. H, Alex. K, Ilya. S, dan Ruslan. S. 2014. Dropout: a simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research, pp 1929-1958. [Online] Available at: https://dl.acm.org/doi/10.5555/2627435.2670313 (Accessed on January 1, 2022).
[15]. Kaggle, 2021 . Glaucoma Detection OCT Scans Retinal. [Online] Available at: Imaging.https://www.kaggle.com/sshikamaru/glaucoma-detection?select=Fundus_Train_Val_Data. (Accessed on October 19, 2021).
[16]. Qizhe, X., Minh-Thang. L, E. Hovy, dan Q. V. Le. 2020. Self-Training With Noisy Student Improves ImageNet Classification. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 10684-10695. Doi: 10.1109/CVPR42600.2020.01070.
