Multi-Cell Multi-Task Convolutional Neural Networks for Diabetic Retinopathy Grading

Abstract

Diabetic Retinopathy (DR) is a non-negligible eye disease among patients with Diabetes Mellitus, and automatic retinal image analysis algorithm for the DR screening is in high demand. Considering the resolution of retinal image is very high, where small pathological tissues can be detected only with large resolution image and large local receptive field are required to identify those late stage disease, but directly training a neural network with very deep architecture and high resolution image is both time computational expensive and difficult because of gradient vanishing/exploding problem, we propose a Multi-Cell architecture which gradually increases the depth of deep neural network and the resolution of input image, which both boosts the training time but also improves the classification accuracy. Further, considering the different stages of DR actually progress gradually, which means the labels of different stages are related. To considering the relationships of images with different stages, we propose a Multi-Task learning strategy which predicts the label with both classification and regression. Experimental results on the Kaggle dataset show that our method achieves a Kappa of 0.841 on test set which is the 4th rank of all state-of-the-arts methods. Further, our Multi-Cell Multi-Task Convolutional Neural Networks (M 2 CNN) solution is a general framework, which can be readily integrated with many other deep neural network architectures.

BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading

“…Ever since the California Healthcare Foundation put forward a challenge with an available dataset in Kaggle [14], more and more research has been put into investigating a multi-class prediction of DR [15][16][17]. Bravo et al [16] explored the influence of different pre-processing methods and combined them using VGG16-based architecture to achieve good performance in diabetic retinopathy grading.…”

CE-Net: Context Encoder Network for 2D Medical Image Segmentation

“…With the development of convolutional neural network (CNN) in image and video processing [36] and medical image analysis [37], [38], automatic feature learning algorithms using deep learning have emerged as feasible approaches for medical image segmentation. Deep learning based segmentation methods are pixel-classification based learning approaches.…”

ResBCDU-Net: A Deep Learning Framework for Lung CT Image Segmentation

“…Previous deep learning methods purposed for medical image segmentation are mostly based on the patches of images. Convolutional neural network (CNN) is the most successful and widely used approach among many deep learning architectures community for medical image analysis [ 34 ]. It is easy to use CNN to classify each pixel in the image separately by offering the extracted neighboring regions of a particular pixel.…”