In our work, we propose a knowledge distillation (KD) framework for the image to image problems in the MRI workflow in order to develop compact, low-parameter models without a significant drop in performance.
Foreground-background class imbalance is a common occurrence in medical images, and U-Net has difficulty in handling class imbalance because of its cross entropy (CE) objective function.
Our experiments show that the concept of a context discriminator can be extended to existing GAN based reconstruction models to offer better performance.
For the task of medical image segmentation, fully convolutional network (FCN) based architectures have been extensively used with various modifications.
We also propose a new joint loss function for the proposed architecture.
We modify the decoder part of the FCN to exploit class information and the structural information as well.