1 code implementation • MIDL 2019 • Balamurali Murugesan, Sricharan Vijayarangan, Kaushik Sarveswaran, Keerthi Ram, Mohanasankar Sivaprakasam
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.
1 code implementation • 8 Jan 2020 • Balamurali Murugesan, Kaushik Sarveswaran, Vijaya Raghavan S, Sharath M. Shankaranarayana, Keerthi Ram, Mohanasankar Sivaprakasam
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.
1 code implementation • 25 Aug 2019 • Balamurali Murugesan, Vijaya Raghavan S, Kaushik Sarveswaran, Keerthi Ram, Mohanasankar Sivaprakasam
Our experiments show that the concept of a context discriminator can be extended to existing GAN based reconstruction models to offer better performance.
1 code implementation • 14 Aug 2019 • Balamurali Murugesan, Kaushik Sarveswaran, Sharath M. Shankaranarayana, Keerthi Ram, Jayaraj Joseph, Mohanasankar Sivaprakasam
For the task of medical image segmentation, fully convolutional network (FCN) based architectures have been extensively used with various modifications.
1 code implementation • 11 Feb 2019 • Balamurali Murugesan, Kaushik Sarveswaran, Sharath M. Shankaranarayana, Keerthi Ram, Mohanasankar Sivaprakasam
We also propose a new joint loss function for the proposed architecture.
no code implementations • 25 Jan 2019 • Balamurali Murugesan, Kaushik Sarveswaran, Sharath M. Shankaranarayana, Keerthi Ram, Mohanasankar Sivaprakasam
We modify the decoder part of the FCN to exploit class information and the structural information as well.