Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation

A survey on deep learning in medical image analysis

“…Kisilev et al (2016) used a completely different approach and predicted categorical BI-RADS descriptors for breast lesions. In their work they focused on three descriptors used in mammography: shape, margin, and density, Fu et al (2016a) Blood vessel segmentation; extending the approach by Fu et al (2016b) by reformulating CRF as RNN Mahapatra et al (2016) Image quality assessment; classification output using CNN-based features combined with the output using saliency maps Maninis et al (2016) Segmentation of blood vessels and optic disk; VGG-19 network extended with specialized layers for each segmentation task Wu et al (2016) Blood vessel segmentation; patch-based CNN followed by mapping PCA solution of last layer feature maps to full segmentation Zilly et al (2017) Segmentation of the optic disk and the optic cup; simple CNN with filters sequentially learned using boosting Color fundus images: detection of abnormalities and diseases Chen et al (2015d) Glaucoma detection; end-to-end CNN, the input is a patch centered at the optic disk Abràmoff et al (2016) Diabetic retinopathy detection; end-to-end CNN, outperforms traditional method, evaluated on a public dataset Burlina et al (2016) Age-related macular degeneration detection; uses overfeat pretrained network for feature extraction van Grinsven et al (2016) Hemorrhage detection; CNN dynamically trained using selective data sampling to perform hard negative mining Gulshan et al (2016) Diabetic retinopathy detection; Inception network, performance comparable to a panel of seven certified ophthalmologists Hard exudate detection; end-to-end CNN combined with the outputs of traditional classifiers for detection of landmarks Worrall et al (2016) Retinopathy of prematurity detection; fine-tuned ImageNet trained GoogLeNet, feature map visualization to highlight disease Work in other imaging modalities Gao et al (2015) Cataract classification in slit lamp images; CNN followed by a set of recursive neural networks to extract higher order features Schlegl et al (2015) Fluid segmentation in OCT; weakly supervised CNN improved with semantic descriptors from clinical reports Blood vessel segmentation in OCT angiography; simple CNN, segmentation of several capillary networks where each have their own class label. The system was fed with the image data and region proposals and predicts the correct label for each descriptor (e.g.…”

Quadratic divergence regularized SVM for optic disc segmentation

“…Our results are better than 12.0% by Giachetti's method [5] and comparable to 11.0% by Dashtbozorg's method [6]. Zilly's method in [17] achieves the best result of 10.0%, but the labelled information in the target domain is used in the training while we do not use such information in our method. …”

“…By first over-segmenting the images into superpixels, the approach significantly reduce the amount of data in both training and testing. Recently, ensemble sampling based convolutional neural network is also used to learn the model for disc segmentation [17], where a entropy based sampling technique is proposed to identify most informative samples for training.…”

“…In recent years, OD segmentation has received much attention and many algorithms have been proposed. Existing methods for OD segmentation are mainly based on template matching [2][3][4][5][6][7], deformable models [8][9][10][11][12][13] or learning [14][15][16][17].…”

The Future of Imaging in Detecting Glaucoma Progression

“…This method was developed to imitate multilevel processing performed by the human brain using linear and non-linear models. DL has been shown to be valuable in improving image quality (88) (89), enhancing reliability of automated segmentation (90) and diagnosing glaucoma (91) (92). …”