TY - JOUR AU - Sengupta, Sourya AU - Zelek, John AU - Lakhsminarayanan, Vasudevan PY - 2020/01/02 Y2 - 2024/03/29 TI - Generative Modeling for Retinal Fundus Image Synthesis JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 5 IS - 1 SE - Articles DO - UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/1661 SP - 2 AB - <p>Medical imaging datasets typically do not contain many training images, usually being deficient for training deep learning networks.<br>We propose a deep residual variational auto-encoder and a generative adversarial network that can generate a synthetic retinal fundus image dataset with corresponding blood vessel annotation. Our<br>initial experiments produce results with higher scores than the state<br>of the art for verifying that the structural statistics of our generated<br>images are compatible with real fundus images. The successful application of generative models to generate synthetic medical data<br>will not only help to mitigate the small dataset problem but will also<br>address the privacy concerns associated with medical datasets.</p> ER -