Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network

By Xin Yi, Paul S. Babyn. Journal of digital imaging, 2017

319 citations recorded by the source corpus.

Low-dose computed tomography (LDCT) has offered tremendous benefits in radiation-restricted applications, but the quantum noise as resulted by the insufficient number of photons could potentially harm the diagnostic performance. Current image-based denoising methods tend to produce a blur effect on the final reconstructed results especially in high noise levels. In this paper, a deep learning-based approach was proposed to mitigate this problem. An adversarially trained network and a sharpness detection network were trained to guide the training process. Experiments on both simulated and real dataset show that the results of the proposed method have very small resolution loss and achieves better performance relative to state-of-the-art methods both quantitatively and visually.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/85a4e653190df97732d10290a43f04cb71883d80

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

  1. Nassir Navab
  2. Peter B. Noël
  3. Martin J. Willemink
  4. B. van Ginneken

In Computer Vision and Pattern Recognition

  1. Shadi Albarqouni
  2. Christoph Baur
  3. B. van Ginneken
  4. Anirban Mukhopadhyay
  5. Nassir Navab
  6. Arjan Kuijper
  7. Peter B. Noël
  8. Martin J. Willemink

In Radiology, Nuclear Medicine and Imaging

  1. Nassir Navab
  2. Christoph Baur
  3. Shadi Albarqouni
  4. Peter B. Noël
  5. Martin J. Willemink
  6. B. van Ginneken

Citations in the corpus