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

Wang, Zhe; Yin, Yanxin; Shi, Jianping; Fang, Wei; Li, Hongsheng; Wang, Xiaogang

doi:10.1007/978-3-319-66179-7_31

Cited by 220 publications

(128 citation statements)

References 19 publications

Supporting

Mentioning

127

Contrasting

Unclassified

Order By: Relevance

“…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.…”

mentioning

confidence: 99%

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

Cheng

et al. 2019

IEEE Trans. Med. Imaging

1,612

775

View full text Add to dashboard Cite

Medical image segmentation is an important step in medical image analysis. With the rapid development of convolutional neural network in image processing, deep learning has been used for medical image segmentation, such as optic disc segmentation, blood vessel detection, lung segmentation, cell segmentation, etc. Previously, U-net based approaches have been proposed. However, the consecutive pooling and strided convolutional operations lead to the loss of some spatial information. In this paper, we propose a context encoder network (referred to as CE-Net) to capture more high-level information and preserve spatial information for 2D medical image segmentation. CE-Net mainly contains three major components: a feature encoder module, a context extractor and a feature decoder module. We use pretrained ResNet block as the fixed feature extractor. The context extractor module is formed by a newly proposed dense atrous convolution (DAC) block and residual multi-kernel pooling (RMP) block. We applied the proposed CE-Net to different 2D medical image segmentation tasks. Comprehensive results show that the proposed method outperforms the original U-Net method and other state-of-the-art methods for optic disc segmentation, vessel detection, lung segmentation, cell contour segmentation and retinal optical coherence tomography layer segmentation.

show abstract

mentioning

confidence: 99%

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

Cheng

et al. 2019

IEEE Trans. Med. Imaging

1,612

775

View full text Add to dashboard Cite

show abstract

“…Wang et al [114] proposed a supervised image-level CNN-based approach that diagnosed DR and highlighted suspicious patches regions. They used a network called Zoom-in, which mimics the zoomin procedure of retinal clinical examination.…”

Section: Classification Of Fundus Images For Referralmentioning

confidence: 99%

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

Asiri

Hussain

Adel

et al. 2019

Artificial Intelligence in Medicine

220

View full text Add to dashboard Cite

Diabetic retinopathy (DR) results in vision loss if not treated early. A computer-aided diagnosis (CAD) system based on retinal fundus images is an efficient and effective method for early DR diagnosis and assisting experts. A computer-aided diagnosis (CAD) system involves various stages like detection, segmentation and classification of lesions in fundus images. Many traditional machine-learning (ML) techniques based on hand-engineered features have been introduced. The recent emergence of deep learning (DL) and its decisive victory over traditional ML methods for various applications motivated the researchers to employ it for DR diagnosis, and many deeplearning-based methods have been introduced. In this paper, we review these methods, highlighting their pros and cons. In addition, we point out the challenges to be addressed in designing and learning about efficient, effective and robust deep-learning algorithms for various problems in DR diagnosis and draw attention to directions for future research.

show abstract

“…Each image is labeled as {0, 1, 2, 3, 4} and the number represents the level of DR. Following the work [11], we also use the Kaggle dataset to evaluate our algorithm.…”

Section: A Experimental Setupmentioning

confidence: 99%

“…Parameter Initialization. Following the work [11], in our experiments, for BaseNet, it is initialized with parameters trained for ImageNet classification. For M 2 CNN, it is trained based on the weights of BaseNet+MT since it consists of BaseNet+MT and Multi-Cell.…”

Section: A Experimental Setupmentioning

confidence: 99%

See 1 more Smart Citation

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

Zhou

et al. 2018

2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

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.

show abstract

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

Cited by 220 publications

References 19 publications

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

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

Deep learning based computer-aided diagnosis systems for diabetic retinopathy: A survey

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

Contact Info

Product

Resources

About