End-to-End Adversarial Retinal Image Synthesis

By Pedro Costa, Adrian Galdran, Maria Inês Meyer, Meindert Niemeijer, Michael David Abràmoff, Ana Maria Mendonça, Aurélio J. C. Campilho. 2018

396 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biophysics, Radiology, Nuclear Medicine and Imaging, Generative Models, 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 Artificial Intelligence

In Biophysics

In Radiology, Nuclear Medicine and Imaging

In Generative Models

In Medical Imaging

Citations in the corpus

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs (2017, neutral): “, medical imaging [17] and biology [8]).”
Deep learning in medical imaging and radiation therapy. (2018, methodology): “357 Costa et al. 358 proposed to generate retinal images by using corresponding vessel tree images.”
Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks (2018, methodology): “Costa et al [4] used GAN to generate synthetic retinal images with labels, but the ability to represent more diverse pathological pattern was limited compared to this work.”
Image Synthesis in Multi-Contrast MRI With Conditional Generative Adversarial Networks (2018, methodology): “sis [29], [40], MR to CT synthesis [28], [33], [38], [42], [48], CT to MR synthesis [36], and retinal vessel map to image synthesis [35], [41].”
DEEP NEURAL (neutral): “Some examples are statistical parametric speech synthesis [9], learning representations of emotional speech [10], noise reduction in low-dose computed tomography (CT) [11], and retinal image synthesis [12].”
Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 (2018, methodology): “The breast phantom is extracted from OA-Breast Database [7] and projected to two dimensions.”
Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis (2020, neutral): “In addition, GAN-based methods have also achieved promising results in synthesizing various types of medical images, such as CT images [15], retinal images [34], [35], MR images [19], ultrasound images [36], [37] and so on.”
Chest x-ray generation and data augmentation for cardiovascular abnormality classification (2018, background): “As the availability of medical images is limited, the most immediate use of GANs has been in medical image synthesis [9-11].”
Deep Learning for Multigrade Brain Tumor Classification in Smart Healthcare Systems: A Prospective Survey (2020, background): “…are among the advanced data-enrichment techniques and are widely used for many applications in diverse domains, such as medical image synthesis [127], [128], compressive sensing MRI [129], [130], superresolution [130], security [131], classi-ﬁcation [132], image-to-image transformation [133],…”
Contrastive learning of global and local features for medical image segmentation with limited annotations (2020, neutral): “Augmentation through random affine [14], elastic [47] and contrast transformations [29, 45], Mixup [59, 19] and synthetic data generation via GANs [22, 15, 50, 8] have been explored.”
Synthetic Medical Images from Dual Generative Adversarial Networks (2017, methodology): “Stacking GANs has been shown to be effective in reﬁning the images produced by a GAN, as seen with Zhang et al [18].”
GANs for Medical Image Analysis (2018, background): “In follow-up work, [35] further introduces an adversarial autoencoder (AAE), which is trained to compress vessel tree images into a multivariate normal distribution and also consecutively to reconstruct them.”