Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection

By Zhe Wang, Yanxin Yin, Jianping Shi, Wei Fang, Hongsheng Li, Xiaogang Wang. 2017

275 citations recorded by the source corpus.

We propose a convolution neural network based algorithm for simultaneously diagnosing diabetic retinopathy and highlighting suspicious regions. Our contributions are two folds: (1) a network termed Zoom-in-Net which mimics the zoom-in process of a clinician to examine the retinal images. Trained with only image-level supervisions, Zoom-in-Net can generate attention maps which highlight suspicious regions, and predicts the disease level accurately based on both the whole image and its high resolution suspicious patches. (2) Only four bounding boxes generated from the automatically learned attention maps are enough to cover 80% of the lesions labeled by an experienced ophthalmologist, which shows good localization ability of the attention maps. By clustering features at high response locations on the attention maps, we discover meaningful clusters which contain potential lesions in diabetic retinopathy. Experiments show that our algorithm outperform the state-of-the-art methods on two datasets, EyePACS and Messidor.

Subfields: Computer Vision and Pattern Recognition, Ophthalmology, Radiology, Nuclear Medicine and Imaging, Medical Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Fanjie Kong
2. Kang Zhou
3. Ricardo Henao
4. Along He
5. Shenghua Gao
6. Ning Li
7. Huan Fu
8. Yitian Zhao

In Ophthalmology

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Kai Wang
5. Tao Li

In Radiology, Nuclear Medicine and Imaging

1. Huan Fu
2. Jiang Liu
3. Jun Cheng
4. Kai Wang
5. Tao Li

In Medical Imaging

1. Fanjie Kong
2. Ricardo Henao
3. Huan Fu
4. Jiang Liu
5. Jun Cheng

Citations in the corpus

• Efficient Classification of Very Large Images with Tiny Objects (2021, methodology): “In the modern era of deep learning, it has been used very successfully in various problems [9,12,49,53].”
• CE-Net: Context Encoder Network for 2D Medical Image Segmentation (2019, background): “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.”
• CABNet: Category Attention Block for Imbalanced Diabetic Retinopathy Grading (2020, background): “Wang et al. [27] proposed a CNN based algorithm with an attention mechanism for simultaneously diagnosing DR and highlighting suspicious regions based on small high resolution patches with image-level labels.”
• Applications of Deep Learning in Fundus Images: A Review (2021, methodology): “Wang et al. (2017) proposed a Zoom-in-Net that can simultaneously perform fiveclass DR grading and generate attention maps highlighting lesions.”