Skip to content

Latest commit

 

History

History
31 lines (19 loc) · 940 Bytes

README.md

File metadata and controls

31 lines (19 loc) · 940 Bytes

MRI Style Transfer using GAN

To build a Generative Adversarial Network model to generate artificial MRI images of different contrast levels (T1-weighted vs T2-weighted Images) from existing MRI scans.

It can save MRI scan time while still enabling expert radiologists to properly give opinions using both T1-weighted as well as T2-weighted images.

Table of Contents

Dataset Information

The training data consists of both T1-weighted as well as T2-weighted images in pair.

Training Dataset Sample

Hardware Accelerator Used

Nvidia V100 Tensor Core GPU

  • CUDA Version: 12.0
  • Driver: NVIDIA-SMI 525.85.12
  • GPU RAM: 16 GB

Project Collaborators

  • Sachin Shekhar
  • Bipul Kumar
  • Divya Tyagi