Medinoid: Computer-Aided Diagnosis and Localization of Glaucoma Using Deep Learning †
Source abstract
Abstract
Glaucoma is a leading eye disease, causing vision loss by gradually affecting peripheral vision if left untreated. Current diagnosis of glaucoma is performed by ophthalmologists, human experts who typically need to analyze different types of medical images generated by different types of medical equipment: fundus, Retinal Nerve Fiber Layer (RNFL), Optical Coherence Tomography (OCT) disc, OCT macula, perimetry, and/or perimetry deviation. Capturing and analyzing these medical images is labor intensive and time consuming. In this paper, we present a novel approach for glaucoma diagnosis and localization, only relying on fundus images that are analyzed by making use of state-of-the-art deep learning techniques. Specifically, our approach towards glaucoma diagnosis and localization leverages Convolutional Neural Networks (CNNs) and Gradient-weighted Class Activation Mapping (Grad-CAM), respectively. We built and evaluated different predictive models using a large set of fundus images, collected and labeled by ophthalmologists at Samsung Medical Center (SMC). Our experimental results demonstrate that our most effective predictive model is able to achieve a high diagnosis accuracy of 96%, as well as a high sensitivity of 96% and a high specificity of 100% for Dataset-Optic Disc (OD), a set of center-cropped fundus images highlighting the optic disc. Furthermore, we present Medinoid, a publicly-available prototype web application for computer-aided diagnosis and localization of glaucoma, integrating our most effective predictive model in its back-end.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Retinal Imaging and Analysis · Glaucoma and retinal disorders · Digital Imaging for Blood Diseases
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Center for Biotech Data Science, Ghent University Global Campus, Incheon 21985, Korea
IDLab, ELIS, Ghent University, 9000 Gent, Belgium
Department of Ophthalmology, Samsung Medical Center, Seoul 06351, Korea
Sungkyunkwan University School of Medicine, Seoul 06351, Korea
Department of Nuclear Medicine, Medical AI Research Lab, Samsung Medical Center, Seoul 06351, Korea
References (53)
Show source-provided references
1. The optic nerve head as a biomechanical structure: A new paradigm for understanding the role of IOP-related stress and strain in the pathophysiology of glaucomatous optic nerve head damage10.1016/j.preteyeres.2004.06.001 ↗
2. Optic nerve damage in human glaucoma: II. The site of injury and susceptibility to damage10.1001/archopht.1981.03930010635009 ↗
3. Global prevalence of glaucoma and projections of glaucoma burden through 2040: A systematic review and meta-analysis10.1016/j.ophtha.2014.05.013 ↗
4. An evaluation of optic disc and nerve fiber layer examinations in monitoring progression of early glaucoma damage10.1016/S0161-6420(92)32018-4 ↗
5. Quantification of nerve fiber layer thickness in normal and glaucomatous eyes using optical coherence tomography: A pilot study10.1001/archopht.1995.01100050054031 ↗
6. Discriminating between normal and glaucomatous eyes using the Heidelberg retina tomograph, GDx nerve fiber analyzer, and optical coherence tomograph10.1001/archopht.119.7.985 ↗
7. Correlation between retinal nerve fibre layer thickness and optic nerve head size: An optical coherence tomography study10.1136/bjo.2004.052498 ↗
8. Does optic nerve head size variation affect circumpapillary retinal nerve fiber layer thickness measurement by optical coherence tomography?10.1167/iovs.11-8214 ↗
9. Differences in optic nerve structure between individuals of predominantly African and European ancestry: Implications for disease detection and pathogenesis10.2147/OPTH.S1628 ↗
10. Automated glaucoma detection using hybrid feature extraction in retinal fundus images10.1142/S0219519413500115 ↗
11. Bock, R., Meier, J., Michelson, G., Nyúl, L.G., and Hornegger, J. (2007). Classifying glaucoma with image-based features from fundus photographs. Joint Pattern Recognition Symposium, Springer.10.1007/978-3-540-74936-3_36 ↗
12. Automated diagnosis of glaucoma using texture and higher order spectra features10.1109/TITB.2011.2119322 ↗
13. Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image10.1016/j.cmpb.2015.10.010 ↗
14. Wavelet-based energy features for glaucomatous image classification10.1109/TITB.2011.2176540 ↗
15. An adaptive threshold based image processing technique for improved glaucoma detection and classification10.1016/j.cmpb.2015.08.002 ↗
16. Automated diagnosis of glaucoma using digital fundus images10.1007/s10916-008-9195-z ↗
17. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation10.1016/j.compmedimag.2016.07.012 ↗
18. Yin, F., Liu, J., Wong, D.W.K., Tan, N.M., Cheung, C., Baskaran, M., Aung, T., and Wong, T.Y. (2012, January 20–22). Automated segmentation of optic disc and optic cup in fundus images for glaucoma diagnosis. Proceedings of the 2012 25th International Symposium on Computer-Based Medical Systems (CBMS), Rome, Italy.10.1109/CBMS.2012.6266344 ↗
19. Li, H., and Chutatape, O. (2001, January 7–10). Automatic location of optic disk in retinal images. Proceedings of the 2001 International Conference on Image Processing, Thessaloniki, Greece.
20. Optic disc detection from normalized digital fundus images by means of a vessels’ direction matched filter10.1109/TMI.2007.900326 ↗
21. Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching10.1109/42.963823 ↗
22. Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review10.1016/j.compmedimag.2013.09.005 ↗
23. Stapor, K., Świtonski, A., Chrastek, R., and Michelson, G. (2004, January 6–9). Segmentation of fundus eye images using methods of mathematical morphology for glaucoma diagnosis. Proceedings of the International Conference on Computational Science, Kraków, Poland.10.1007/978-3-540-25944-2_6 ↗
24. Optic disk and cup segmentation from monocular color retinal images for glaucoma assessment10.1109/TMI.2011.2106509 ↗
25. Novel fractal feature-based multiclass glaucoma detection and progression prediction10.1109/TITB.2012.2218661 ↗
26. Nyúl, L.G. (November, January 30). Retinal image analysis for automated glaucoma risk evaluation. Proceedings of the MIPPR 2009: Medical Imaging, Parallel Processing of Images, and Optimization Techniques, International Society for Optics and Photonics, Yichang, China.10.1117/12.851179 ↗
27. Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation10.1109/TMI.2018.2791488 ↗
28. Estimation of the relative amount of hemoglobin in the cup and neuroretinal rim using stereoscopic color fundus images10.1167/iovs.14-15592 ↗
29. Kim, M.J., Park, H.M., Zuallaert, J., Janssens, O., Van Hoecke, S., and De Neve, W. (2018, January 3–6). Computer-aided diagnosis and localization of glaucoma using deep learning. Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.10.1109/BIBM.2018.8621168 ↗
30. Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer.10.1007/978-3-319-24574-4_28 ↗
31. Inception-v4, inception-resnet and the impact of residual connections on learning
32. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
33. Imagenet large scale visual recognition challenge10.1007/s11263-015-0816-y ↗
34. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning10.1109/TMI.2016.2528162 ↗
35. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs10.1001/jama.2016.17216 ↗
36. Bar, Y., Diamant, I., Wolf, L., Lieberman, S., Konen, E., and Greenspan, H. (2015, January 16–19). Chest pathology detection using deep learning with non-medical training. Proceedings of the 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), New York, NY, USA.10.1109/ISBI.2015.7163871 ↗
37. Tang, Y.X., Tang, Y.B., Han, M., Xiao, J., and Summers, R.M. (2019, January 16–21). Deep adversarial one-class learning for normal and abnormal chest radiograph classification. Proceedings of the Medical Imaging 2019: Computer-Aided Diagnosis, International Society for Optics and Photonics, San Diego, CA, USA.10.1117/12.2511787 ↗
38. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
39. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 27). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
40. (2018, April 06). TensorFlow-Slim Image Classification Model Library. Available online: https://github.com/tensorflow/models/tree/master/research/slim.
41. Yosinski, J., Clune, J., Bengio, Y., and Lipson, H. (2014, January 8–13). How transferable are features in deep neural networks?. Proceedings of the Advances in Neural Information Processing Systems, Montreal, QC, Canada.
42. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
43. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 8–10). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
44. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude
45. Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. arXiv.10.1109/ICCV.2017.74 ↗
46. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., and Torralba, A. (2016, January 27–30). Learning deep features for discriminative localization. Proceedings of the 2016 IEEE Conference on IEEE, Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.319 ↗
47. Nair, V., and Hinton, G.E. (2010, January 27–30). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Las Vegas, NV, USA.
48. Differential data augmentation techniques for medical imaging classification tasks
49. Torrey, L., and Shavlik, J. (2010). Transfer learning. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, IGI Global.10.4018/978-1-60566-766-9.ch011 ↗
50. Superpixel classification based optic disc and optic cup segmentation for glaucoma screening10.1109/TMI.2013.2247770 ↗
51. Level-set based automatic cup-to-disc ratio determination using retinal fundus images in ARGALI
52. The earliest observable defect in glaucoma?10.1016/S0140-6736(72)90500-4 ↗
53. The nerve fiber layer in the diagnosis of glaucoma10.1001/archopht.1977.04450120055003 ↗