Superpixel Classification Based Optic Disc and Optic Cup Segmentation for Glaucoma Screening

By Jun Cheng, Jiang Liu, Yanwu Xu, F. Yin, Damon Wing Kee Wong, N. Tan, Dacheng Tao, Ching-Yu Cheng, T. Aung, Tien Yin Wong. IEEE Transactions on Medical Imaging, 2013

613 citations recorded by the source corpus.

Subfields: Ophthalmology, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/2d054c85a51f101b51f0427d332e22eb5c502165

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. Jordi Pont-Tuset
7. Luc Van Gool
8. Xiaochun Cao

In Radiology, Nuclear Medicine and Imaging

1. P. Heng
2. Huan Fu
3. Hao Chen
4. Lequan Yu
5. Jiang Liu
6. Jun Cheng
7. Damon Wing Kee Wong
8. Yanwu Xu

Citations in the corpus

• CNNs for automatic glaucoma assessment using fundus images: an extensive validation (2019, methodology): “Another approach for optic disc and optic cup segmentation is presented by Cheng et al. [9], who developed a technique to measure the CDR based on superpixel classification.”
• Deep Retinal Image Understanding (2016, methodology): “A superpixel classification method is proposed in [3].”
• A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images (2017, background): “Though classification based optic detection methods are proposed in [15][16][17], they are data dependent.”
• Medical Image Segmentation Using Deep Learning: A Survey (2020, background): “, [1,2,3], [3,4,5], [1,2,5], [5,9,17], and [1,2,5,9].”
• Disc-Aware Ensemble Network for Glaucoma Screening From Fundus Image (2018, methodology): “, superpixel method [10] takes 10 seconds, DeepCDR [12]”
• Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation (2019, methodology): “Early methods for medical image segmentation mainly focused on using thresholding [33], statistical shape models [34] and machine learning [35]–[37], while recent ones are mainly deep learning-based [38]–[40].”
• Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation (2018, methodology): “From the glaucoma screening results, we have the following observations: 1) The non-deep learning method, superpixel [10], produces a competitive performance (AUC = 0.”
• Uniqueness-Driven Saliency Analysis for Automated Lesion Detection with Applications to Retinal Diseases (2018, positive): “In this work, the vessel segmentation outlined in [14] and the optic disc detection method discussed in [15] were employed.”