CT scan Reconstruction Using Generative Adversarial Network

@article{1703911,
      author = {Rajlaxmi Patil, Tanvi Khare, Sanika Inamdar, Madhuri Mane},
      title = {CT scan Reconstruction Using Generative Adversarial Network},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {6},
      number = {6},
      pages = {31-36},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1703911.pdf},
      abstract = {Computer Vision and Image Enhancement through Artificial Intelligence is being used for the improvement in the resolution of the images obtained from variety of sources such as surveillance camera, PAUS , CT scans, radiology results. Implemented method uses a machine learning algorithm, Gen-erative Adversarial Networks (GAN) for achieving the goal of enhancement and reconstruction of images. Super resolution of images allows us to obtain images with better resolution and less noise . Existing models tend to add artifacts to reconstructed im-ages or remove important details from enhanced scans. Cleaner images are obtained at cost of some information loss. Noise in scans should be removed while keeping important information intact and providing a better resolution.In this paper we explore research that has been done for reconstruction of CT scans using various methods.},
      keywords = {Generative Adversarial Network, Image Enhancement, Computer Vision, noise reduction, Computed tomography, CNN},
      month = {December},
  }