paper-with-me

홈 › Papers

DR-GAN: Conditional Generative Adversarial Network for Fine-Grained Lesion Synthesis on Diabetic Retinopathy Images

2019-12-10 · Yi Zhou, Boyang Wang, Xiaodong He, Shanshan Cui, Ling Shao

Diabetic retinopathy (DR) is a complication of diabetes that severely affects eyes. It can be graded into five levels of severity according to international protocol. However, optimizing a grading model to have strong generalizability requires a large amount of balanced training data, which is difficult to collect particularly for the high severity levels. Typical data augmentation methods, including random flipping and rotation, cannot generate data with high diversity. In this paper, we propose a diabetic retinopathy generative adversarial network (DR-GAN) to synthesize high-resolution fundus images which can be manipulated with arbitrary grading and lesion information. Thus, large-scale generated data can be used for more meaningful augmentation to train a DR grading and lesion segmentation model. The proposed retina generator is conditioned on the structural and lesion masks, as well as adaptive grading vectors sampled from the latent grading space, which can be adopted to control the synthesized grading severity. Moreover, a multi-scale spatial and channel attention module is devised to improve the generation ability to synthesize details. Multi-scale discriminators are designed to operate from large to small receptive fields, and joint adversarial losses are adopted to optimize the whole network in an end-to-end manner. With extensive experiments evaluated on the EyePACS dataset connected to Kaggle, as well as the FGADR dataset, we validate the effectiveness of our method, which can both synthesize highly realistic (1280 x 1280) controllable fundus images and contribute to the DR grading task.

📄 PDF Abstract BibTeX arXiv:1912.04670

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGenerative Adversarial NetworkLesion Segmentation

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
Sigmoid Activation 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
How do i ask a question at Expedia?*AskExpertService To ask a question on Expedia, you can utilize their Help Center +1-888-829-0881, call customer service, use live chat, or reach out via social media. You can also find answers to…

Similar Papers 제목 키워드 기반

RADIOGAN: Deep Convolutional Conditional Generative adversarial Network To Generate PET Images

2020-03-19 · Amine Amyar, Su Ruan, Pierre Vera, Pierre Decazes 외

One of the most challenges in medical imaging is the lack of data. It is proven that classical data augmentation methods are useful but still limited due to the huge variation in images. Using generative adversarial netw…

Data AugmentationGenerative Adversarial Network

Conditional Generative Refinement Adversarial Networks for Unbalanced Medical Image Semantic Segmentation

2018-10-09 · Mina Rezaei, Haojin Yang, Christoph Meinel

We propose a new generative adversarial architecture to mitigate imbalance data problem in medical image semantic segmentation where the majority of pixels belongs to a healthy region and few belong to lesion or non-heal…

Cell SegmentationEnsemble LearningLesion SegmentationSegmentation+1

Data Augmentation for Skin Lesion using Self-Attention based Progressive Generative Adversarial Network

2019-10-25 · Ibrahim Saad Ali, Mamdouh Farouk Mohamed, Yousef Bassyouni Mahdy

Deep Neural Networks (DNNs) show a significant impact on medical imaging. One significant problem with adopting DNNs for skin cancer classification is that the class frequencies in the existing datasets are imbalanced. T…

Cancer ClassificationData AugmentationGeneral ClassificationGenerative Adversarial Network+1

Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning

2020-07-27 · Qiqi Xiao, Jiaxu Zou, Muqiao Yang, Alex Gaudio 외

Diabetic Retinopathy (DR) is a leading cause of blindness in working age adults. DR lesions can be challenging to identify in fundus images, and automatic DR detection systems can offer strong clinical value. Of the publ…

Generative Adversarial NetworkLesion SegmentationSegmentationSemantic Segmentation

Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images

2020-03-30 · Manohar Karki, Junghwan Cho

Data augmentation can effectively resolve a scarcity of images when training machine-learning algorithms. It can make them more robust to unseen images. We present a lesion conditional Generative Adversarial Network LcGA…

Computed Tomography (CT)Conditional Image GenerationData AugmentationGenerative Adversarial Network+3