Performance Assessment of EyeNet Model in Glaucoma Diagnosis
Tóm tắt
Deep learning (DL) has recently gained increasing attention in biomedical data analytics, demonstrating robust performance and promising results. A deep network requires massive amount of data to learn meaningful patterns useful in solving complex problems. Data scarcity in medical field is a bottleneck for applying deep learning in this area. This has led to the popularity of pre-trained models, trained on huge source data to achieve reasonable accuracy in medical diagnosis even with less data in target domain. A wise choice of models trained with data similar to target data would ensure that relevant features are captured. In this work, the significance of choosing appropriate pre-trained models is demonstrated. The EyeNet model, originally trained for diagnosis of diabetic retinopathy (DR) using fundus image dataset, is used as a pre-trained model for building a convolutional neural network (CNN) – based DL architecture for glaucoma diagnosis using images from the same modality. The results are compared with glaucoma diagnosis using different pre-trained models that are less relevant to the problem considered. Different experiments including fine-tuning and transfer learning were performed. Results were validated using the benchmark Rim-one dataset. The EyeNet model outperformed all other models, achieving a maximum accuracy of 89% with transfer learning using support vector machines (SVM) combined with principal component analysis (PCA) for dimensionality reduction.
Tài liệu tham khảo
J. Liu, Z. Zhang, D. Wong, Y. Xu, F. Yin, J. Cheng, N. Tan, C. Kwoh, D. Xu, Y. Tham, T. Aung, and T. Wong, “Automatic glaucoma diagnosis through medical imaging informatics,” J. Am. Med. Inf. Assoc. 20 (6), 1021–1027 (2013).
L. Nanni, S. Ghidoni, and S. Brahnam, “Handcrafted vs. non-handcrafted features for computer vision classification,” J. Pattern Recognit. 71, 158–172 (2017).
G. J. Litjens, T. Kooi, B. E. Bejnordi, A. A. Setio, F. Ciompi, M. Ghafoorian, J. V. Laak, B. V. Ginneken, and C. I. Sánchez, “A survey on deep learning in medical image analysis,” Med. Image Anal. 42, 60–88 (2017).
R. Ramachandran, D. C. Rajeev, S. G. Krishnan, and P. Subathra, “Deep learning – An overview,” Int. J. Appl. Eng. Res. 10, 25433–25448 (2015).
S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Trans. Knowl. Data Eng. 22 (10), 1345–1359 (2010).
A. Issac, M. Partha Sarathi, and M. K. Dutta, “An adaptive threshold based image processing technique for improved glaucoma detection and classification,” J. Comput. Methods Programs Biomed. 122 (2), 229–244 (2015).
P. S. Mittapalli and G. B. Kande, “Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma,” J. Biomed. Signal Process. Control 24, 34–46 (2016).
X. Chen, Y. Xu, D. W. K. Wong, T. Y. Wong, and J. Liu, “Glaucoma detection based on deep convolutional neural network,” in Proceedings of the Thirty-Seventh Annual International Conference on the IEEE Engineering in Medicine and Biology Society (Milan, 2015), pp. 715–718.
U. Raghavendra, H. Fujita, S. V. Bhandary, A. Gudigar, J. H. Tan, and U. R. Acharya, “Deep convolutional neural network for accurate diagnosis of glaucoma using digital fundus images,” J. Inf. Sci. 441, 41–49 (2018).
Y. Chai, H. Liu, and J. Xu, “Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models,” Knowl.-Based Syst. 161, 147–156 (2018).
N. E. Benzebouchi, N. Azizi, and S. E. Bouziane, “Glaucoma diagnosis using cooperative convolutional neural networks,” J. Adv. Electron. Comput. Sci. 5 (1), 2018.
A. Cerentini, D. Welfer, M. Cordeiro d’Ornellas, C. J. Pereira Haygert, and G. N. Dotto, “Automatic identification of glaucoma using deep learning methods,” Stud. Health Technol. Inf. 245, 318–321 (2017).
M. Christopher, A. Belghith, and C. Bowd, “Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs,” Sci. Rep. 8, 16685 (2018).
S. Manas, G. Suguna, R. Lavanya, and M. Nirmala Devi, “Performance comparison of pre-trained deep neural networks for automated glaucoma detection,” Lect. Notes Comput. Vision Biomech. 30, 631–637 (2019).
J. J. Gómez-Valverde, A. Antón, G. Fatti, B. Liefers, A. Herranz, A. Santos, C. I. Sánchez, and M. J. Ledesma-Carbayo, “Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning,” Biomed. Opt. Express 10 (2), 892–913 (2019).
A. Diaz-Pinto, S. Morales, V. Naranjo, T. Köhler, J. M. Mossi, and A. Navea, “CNNs for automatic glaucoma assessment using fundus images: An extensive validation,” Biomed. Eng. Online 18 (1), 29 (2019).
A. C. Lima, L. B. Maia, R. M. Pereira, G. B. Junior, J. D. Almeida, and A. C. Paiva, “Glaucoma diagnosis over eye fundus image through deep features,” in 25th International Conference on Systems, Signals and Image Processing (IWSSIP) (Maribor, 2018), pp. 1–4.
B. Al-Bander, W. Al-Nuaimy, M. A. Al-Taee, and Y. Zheng, “Automated glaucoma diagnosis using deep learning approach,” in 14th International Multi-Conference on Systems, Signals and Devices (SSD) (Marrakech, 2017), pp. 207–210.
S. Phasuk, P. Poopresert, A. Yaemsuk, P. Suvannachart, R. Itthipanichpong, S. Chansangpetch, A. Manassakorn, V. Tantisevi, P. Rojanapongpun, and C. Tantibundhit, “Automated glaucoma screening from retinal fundus image using deep learning,” in 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (Berlin, 2019), pp. 904–907.
https://github.com/ritika26/dsi-capstone.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv (2014). arXiv:1409.1556