# Low Dose Helical CBCT denoising by using domain filtering with deep reinforcement learning

arXiv: https://arxiv.org/abs/2104.00889 · HTML: https://mlsanity.com/paper/2104.00889/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 14 references that are in the map.
- First posted on arXiv 2 Apr 2021.

## Builds on (most cited first, 3 of 3)

- [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss](https://mlsanity.com/paper/1708.00961/) (2017)
- [Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising](https://mlsanity.com/paper/1901.05593/) (2019)
- [JBFnet -- Low Dose CT Denoising by Trainable Joint Bilateral Filtering](https://mlsanity.com/paper/2007.04754/) (2020)

## Abstract (arXiv)

Cone Beam Computed Tomography(CBCT) is a now known method to conduct CT imaging. Especially, The Low Dose CT imaging is one of possible options to protect organs of patients when conducting CT imaging. Therefore Low Dose CT imaging can be an alternative instead of Standard dose CT imaging. However Low Dose CT imaging has a fundamental issue with noises within results compared to Standard Dose CT imaging. Currently, there are lots of attempts to erase the noises. Most of methods with artificial intelligence have many parameters and unexplained layers or a kind of black-box methods. Therefore, our research has purposes related to these issues. Our approach has less parameters than usual methods by having Iterative learn-able bilateral filtering approach with Deep reinforcement learning. And we applied The Iterative learn-able filtering approach with deep reinforcement learning to sinograms and reconstructed volume domains. The method and the results of the method can be much more explainable than The other black box AI approaches. And we applied the method to Helical Cone Beam Computed Tomography(CBCT), which is the recent CBCT trend. We tested this method with on 2 abdominal scans(L004, L014) from Mayo Clinic TCIA dataset. The results and the performances of our approach overtake the results of the other previous methods.