CVAug 1, 2017

Deep Generative Adversarial Neural Networks for Realistic Prostate Lesion MRI Synthesis

arXiv:1708.00129v131 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the need for realistic medical image synthesis in the prostate lesion domain, but it is incremental as it applies existing GAN techniques to a new dataset.

The paper tackled the problem of generating realistic synthetic prostate lesion MRI images by applying Deep Convolutional Generative Adversarial Neural Networks (DCGANs) to 330 MRI scans from the SPIE ProstateX Challenge 2016, resulting in synthetic outputs compared to real images and exploration of latent representations.

Generative Adversarial Neural Networks (GANs) are applied to the synthetic generation of prostate lesion MRI images. GANs have been applied to a variety of natural images, is shown show that the same techniques can be used in the medical domain to create realistic looking synthetic lesion images. 16mm x 16mm patches are extracted from 330 MRI scans from the SPIE ProstateX Challenge 2016 and used to train a Deep Convolutional Generative Adversarial Neural Network (DCGAN) utilizing cutting edge techniques. Synthetic outputs are compared to real images and the implicit latent representations induced by the GAN are explored. Training techniques and successful neural network architectures are explained in detail.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes