Retinal Image Analysis

We have proposed automated methods to segment retinal cyst regions from OCT images and methods to classify artery and vein from fundus images of eye. Our contributions in this area can be read from the following papers.

1. Chetan L Srinidhi, Aparna P and Jeny Rajan, Automated Method for Retinal Artery/Vein Separation via Graph Search Metaheuristic Approach, IEEE Transactions on Image Processing (In Press), 2019.

2. Chetan L Srinidhi, Aparna P, Jeny Rajan, A visual attention guided unsupervised feature learning for robust vessel delineation in retinal images, Biomedical Signal Processing and Control, Vol. 44, pp: 110-126, July 2018.

3. G N Girish, Bibhash Thakur, Sohini Roy Chowdhury, Abhishek R Kothari, Jeny Rajan, Segmentation of Intra-Retinal Cysts from Optical Coherence Tomography Images using a Fully Convolutional Neural Network Model, IEEE Journal of Biomedical and Health Informatics, In Press, 2018 [link]

4. GN Girish, VA Anima, Abhishek R Kothari, PV Sudeep, Sohini Roychowdhury, Jeny Rajan, A Benchmark Study of Automated Intra-retinal Cyst Segmentation Algorithms using Optical Coherence Tomography B-Scans, Computer Methods and Programs in Biomedicine, Vol 153, pp:105-114, 2018. [link]

5. Girish G.N, Abhishek R Kothari, Jeny Rajan, " Marker Controlled Watershed Transform for Intra-Retinal Cysts Segmentation from Optical Coherence Tomography B-Scans", Pattern Recognition Letters, In Press, 2017. [link]

Results of proposed method (intra-retinal cyst segmentation) on different vendor scans against the GT.

Artery/Vein separation results on DRIVE images. Top row: our method’s best result (Acc = 0:985). Bottom row: our method’s worst result (Acc = 0:889). (a) Original image; (b) binary vessel map; (c) identified vessel subtrees; (d) A/V separation results;(e) corresponding A/V ground truth. (Note: the correctly labeled arteries/veins are shown in red/blue, respectively. While, incorrectly labeled arteries/veins are shown in yellow/green, respectively).