Optic Disc, Cup and Fovea Detection from Retinal Images Using U-Net++ with EfficientNet Encoder

20 Nov 2020  ·  Ravi Kamble, Pranab Samanta, Nitin Singhal ·

The accurate detection of retinal structures like an optic disc (OD), cup, and fovea is crucial for the analysis of Age-related Macular Degeneration (AMD), Glaucoma, and other retinal conditions. Most segmentation methods rely on separate detection of these retinal structures due to which a combined analysis for computer-aided ophthalmic diagnosis and screening is challenging. To address this issue, the paper introduces an approach incorporating OD, cup, and fovea analysis together. The paper presents a novel method for the detection of OD with a cup and fovea using modified U-Net++ architecture with the EfficientNet-B4 model as a backbone. The extracted features from the EfficientNet are utilized using skip connections in U-Net++ for precise segmentation. Datasets from ADAM and REFUGE challenges are used for evaluating the performance. The proposed method achieved a success rate of 94.74% and 95.73% dice value for OD segmentation on ADAM and REFUGE data, respectively. For fovea detection, the average Euclidean distance of 26.17 pixels is achieved for the ADAM dataset. The proposed method stood first for OD detection and segmentation tasks in ISBI ADAM 2020 challenge.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Optic Disc Segmentation Drishti-GS EfficientNet+U-Net++ DiceOC 0.9381 # 1
DiceOD 0.9784 # 1
mIoU 0.8820 # 1
Fovea Detection REFUGE Challenge EfficientNet+U-Net++ Euclidean Distance (ED) 35.18 # 1
Optic Cup Detection REFUGE Challenge EfficientNet+U-Net++ IoU 0.8128 # 1
Optic Disc Detection REFUGE Challenge EfficientNet+U-Net++ IoU 0.8847 # 1
Optic Cup Segmentation REFUGE Challenge EfficientNet+U-Net++ Dice 0.8762 # 1
Optic Disc Segmentation REFUGE Challenge EfficientNet+U-Net++ Dice 0.9573 # 2