Towards the Localisation of Lesions in Diabetic Retinopathy
This work provides a method for ophthalmologists to identify discriminative regions in DR fundus images, aiding in early diagnosis and potentially saving lives, representing an incremental improvement in interpretability for a specific medical domain.
This study uses post-attention Grad-CAM on four pre-trained deep learning models to localize lesions in diabetic retinopathy (DR) fundus images. InceptionV3 achieved the best classification accuracy of 96.07% and better lesion localization compared to VGG16, ResNet50, and InceptionResNetV2.
Convolutional Neural Networks (CNNs) have successfully been used to classify diabetic retinopathy (DR) fundus images in recent times. However, deeper representations in CNNs may capture higher-level semantics at the expense of spatial resolution. To make predictions usable for ophthalmologists, we use a post-attention technique called Gradient-weighted Class Activation Mapping (Grad-CAM) on the penultimate layer of deep learning models to produce coarse localisation maps on DR fundus images. This is to help identify discriminative regions in the images, consequently providing evidence for ophthalmologists to make a diagnosis and potentially save lives by early diagnosis. Specifically, this study uses pre-trained weights from four state-of-the-art deep learning models to produce and compare localisation maps of DR fundus images. The models used include VGG16, ResNet50, InceptionV3, and InceptionResNetV2. We find that InceptionV3 achieves the best performance with a test classification accuracy of 96.07%, and localise lesions better and faster than the other models.