Segmentation and Generation of Magnetic Resonance Images by Deep Neural Networks

Magnetic Resonance Images (MRIs) are extremely used in the medical field to detect and better understand diseases. In order to fasten automatic processing of scans and enhance medical research, this project focuses on automatically segmenting targeted parts of MRIs and generating new MRI datasets from random noise. More specifically, a Deep Neural Network architecture called U-net is used to segment bones and cartilages of Knee MRIs, and several Generative Adversarial Networks (GANs) are compared and tuned to create new realistic and high quality brain MRIs that can be used as training set for more advanced models. Three main architectures are described: Deep Convolution GAN (DCGAN), Super Resolution Residual GAN (SRResGAN) and Progressive GAN (ProGAN), and five loss functions are tested: the Original loss, LSGAN, WGAN, WGAN_GP and DRAGAN. Moreover, a quantitative benchmark is carried out thanks to evaluation measures using Principal Component Analysis. The results show that U-net can achieve state-of-the-art performance in segmenting bones and cartilages in Knee MRIs (Accuracy of more than 99.5%). Moreover, the three GAN architectures can successfully generate realistic brain MRIs even if some models have difficulties to converge. The main insights to stabilize the networks are using one-sided smoothing labels, regularization with gradient penalty in the loss function (like in WGAN_GP or DRAGAN), adding a minibatch similarity layer in the Discriminator and a long training time.