Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network

By Artem Sevastopolsky. Pattern Recognition and Image Analysis, 2017

405 citations recorded by the source corpus.

Glaucoma is the second leading cause of blindness all over the world, with approximately 60 million cases reported worldwide in 2010. If undiagnosed in time, glaucoma causes irreversible damage to the optic nerve leading to blindness. The optic nerve head examination, which involves measurement of cup-todisc ratio, is considered one of the most valuable methods of structural diagnosis of the disease. Estimation of cup-to-disc ratio requires segmentation of optic disc and optic cup on eye fundus images and can be performed by modern computer vision algorithms. This work presents universal approach for automatic optic disc and cup segmentation, which is based on deep learning, namely, modification of U-Net convolutional neural network. Our experiments include comparison with the best known methods on publicly available databases DRIONS-DB, RIM-ONE v.3, DRISHTI-GS. For both optic disc and cup segmentation, our method achieves quality comparable to current state-of-the-art methods, outperforming them in terms of the prediction time.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/b7ac1d4ebdb3350433eae7bae8d4ccc0df17e8a5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Ophthalmology

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Damon Wing Kee Wong
5. Yanwu Xu
6. Xiaochun Cao
7. Gary G. Yen
8. Yao Zhou

In Radiology, Nuclear Medicine and Imaging

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Damon Wing Kee Wong
5. Yanwu Xu
6. Xiaochun Cao
7. Gary G. Yen
8. Yao Zhou

Citations in the corpus

• CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, background): “It has becomes a popular neural network architecture for biomedical image segmentation tasks [42], [43], [44], [45].”
• Evolutionary Compression of Deep Neural Networks for Biomedical Image Segmentation (2020, background): “on a similar dataset, then find a smaller one by gradually pruning and fine-tuning the model on your own dataset [16]–[18].”
• CPFNet: Context Pyramid Fusion Network for Medical Image Segmentation (2020, background): “many medical image segmentation applications [10], [14]–[16] for each single stage, the capability of context information”
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs (2019, neutral): “Most of existing methods use a surrogate segmentation/detection approach to first localize the ONH area and them crop the images around it (Edupuganti et al., 2018; Fu et al., 2018; Lim et al., 2015; Sevastopolsky, 2017; Zilly et al., 2015).”
• Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation (2018, methodology): “In [28], a modified U-Net deep network is introduced to segment the OD and OC.”