Deep Residual Network based Automatic Image Grading for Diabetic Macular Edema
Diabetic Macular Edema (DME) is an advanced symptom of diabetic retinopathy that affects central vision of diabetes patients. An automated system for early detection of DME symptom has been proposed herein to elude vision impairment and assist in effective treatment. Transfer learning based on Deep Residual Networks (ResNets) which has proven to be a very successful model in many image classification applications and is used in the proposed system for automatic grading of DME images. Validation of the developed system on Indian Diabetic Retinopathy Image Dataset (IDRID 2018) results in 86.56 % detection accuracy.
PDF
Datasets
IDRiD
Results from the Paper
Ranked #1 on
Medical Image Classification
on IDRiD
(Accuracy (% ) metric)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Medical Image Classification | IDRiD | ResNet-152 | Accuracy (% ) | 86.56 | # 1 |
