Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2203.14794v1
• Date: Mon, 28 Mar 2022 14:30:43 GMT
• Title: Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning
• Authors: Mayank Patwari, Ralf Gutjahr, Rainer Raupach, Andreas Maier
• Abstract summary: We introduce a novel CT denoising framework, which has interpretable behaviour, and provides useful results with limited data. Our experiments were carried out on abdominal scans for the Mayo Clinic TCIA dataset, and the AAPM Low Dose CT Grand Challenge. Our denoising framework has excellent denoising performance increasing the PSNR from 28.53 to 28.93, and increasing the SSIM from 0.8952 to 0.9204.
• Score: 7.909848251752742
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The use of deep learning has successfully solved several problems in the field of medical imaging. Deep learning has been applied to the CT denoising problem successfully. However, the use of deep learning requires large amounts of data to train deep convolutional networks (CNNs). Moreover, due to large parameter count, such deep CNNs may cause unexpected results. In this study, we introduce a novel CT denoising framework, which has interpretable behaviour, and provides useful results with limited data. We employ bilateral filtering in both the projection and volume domains to remove noise. To account for non-stationary noise, we tune the $\sigma$ parameters of the volume for every projection view, and for every volume pixel. The tuning is carried out by two deep CNNs. Due to impracticality of labelling, the two deep CNNs are trained via a Deep-Q reinforcement learning task. The reward for the task is generated by using a custom reward function represented by a neural network. Our experiments were carried out on abdominal scans for the Mayo Clinic TCIA dataset, and the AAPM Low Dose CT Grand Challenge. Our denoising framework has excellent denoising performance increasing the PSNR from 28.53 to 28.93, and increasing the SSIM from 0.8952 to 0.9204. We outperform several state-of-the-art deep CNNs, which have several orders of magnitude higher number of parameters (p-value (PSNR) = 0.000, p-value (SSIM) = 0.000). Our method does not introduce any blurring, which is introduced by MSE loss based methods, or any deep learning artifacts, which are introduced by WGAN based models. Our ablation studies show that parameter tuning and using our reward network results in the best possible results.

Related papers

• Learning Provably Robust Estimators for Inverse Problems via Jittering [51.467236126126366]
  We investigate whether jittering, a simple regularization technique, is effective for learning worst-case robust estimators for inverse problems. We show that jittering significantly enhances the worst-case robustness, but can be suboptimal for inverse problems beyond denoising.
  arXiv  Detail & Related papers  (2023-07-24T14:19:36Z)
• Multi-stage image denoising with the wavelet transform [125.2251438120701]
  Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
  arXiv  Detail & Related papers  (2022-09-26T03:28:23Z)
• Ultra Low-Parameter Denoising: Trainable Bilateral Filter Layers in Computed Tomography [7.405782253585339]
  This work presents an open-source CT denoising framework based on the idea of bilateral filtering. We propose a bilateral filter that can be incorporated into a deep learning pipeline and optimized in a purely data-driven way. Denoising performance is achieved on x-ray microscope bone data (0.7053 and 33.10) and the 2016 Low Dose CT Grand Challenge dataset (0.9674 and 43.07) in terms of SSIM and PSNR.
  arXiv  Detail & Related papers  (2022-01-25T14:33:56Z)
• Deep neural networks-based denoising models for CT imaging and their efficacy [0.3058685580689604]
  We aim to examine the image quality of the Deep Neural Networks (DNNs) results from a holistic viewpoint for low-dose CT image denoising. We build a library of advanced DNN denoising architectures such as the DnCNN, U-Net, Red-Net, GAN, etc. Each network is modeled, as well as trained, such that it yields its best performance in terms of the PSNR and SSIM.
  arXiv  Detail & Related papers  (2021-11-18T06:18:26Z)
• Deep Networks for Direction-of-Arrival Estimation in Low SNR [89.45026632977456]
  We introduce a Convolutional Neural Network (CNN) that is trained from mutli-channel data of the true array manifold matrix. We train a CNN in the low-SNR regime to predict DoAs across all SNRs. Our robust solution can be applied in several fields, ranging from wireless array sensors to acoustic microphones or sonars.
  arXiv  Detail & Related papers  (2020-11-17T12:52:18Z)
• EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising [27.86840312836051]
  We propose the Edge enhancement based Densely connected Convolutional Neural Network (EDCNN) We construct a model with dense connections to fuse the extracted edge information and realize end-to-end image denoising. Compared with the existing low-dose CT image denoising algorithms, our proposed model has a better performance in preserving details and suppressing noise.
  arXiv  Detail & Related papers  (2020-10-30T23:12:09Z)
• Unrolling of Deep Graph Total Variation for Image Denoising [106.93258903150702]
  In this paper, we combine classical graph signal filtering with deep feature learning into a competitive hybrid design. We employ interpretable analytical low-pass graph filters and employ 80% fewer network parameters than state-of-the-art DL denoising scheme DnCNN.
  arXiv  Detail & Related papers  (2020-10-21T20:04:22Z)
• Deep learning for gravitational-wave data analysis: A resampling white-box approach [62.997667081978825]
  We apply Convolutional Neural Networks (CNNs) to detect gravitational wave (GW) signals of compact binary coalescences, using single-interferometer data from LIGO detectors. CNNs were quite precise to detect noise but not sensitive enough to recall GW signals, meaning that CNNs are better for noise reduction than generation of GW triggers.
  arXiv  Detail & Related papers  (2020-09-09T03:28:57Z)
• Accurate and Efficient Intracranial Hemorrhage Detection and Subtype Classification in 3D CT Scans with Convolutional and Long Short-Term Memory Neural Networks [20.4701676109641]
  We present our system for the RSNA Intracranial Hemorrhage Detection challenge. The proposed system is based on a lightweight deep neural network architecture composed of a convolutional neural network (CNN) We report a weighted mean log loss of 0.04989 on the final test set, which places us in the top 30 ranking (2%) from a total of 1345 participants.
  arXiv  Detail & Related papers  (2020-08-01T17:28:25Z)
• Low Dose CT Denoising via Joint Bilateral Filtering and Intelligent Parameter Optimization [7.909848251752742]
  Current clinically approved methods use iterative reconstruction methods to reduce the noise in CT images. Deep learning methods have been successfully used to denoise CT images. In this paper, we use a Joint Bilateral Filter (JBF) to denoise our CT images.
  arXiv  Detail & Related papers  (2020-07-09T13:17:36Z)
• Deep Learning on Image Denoising: An overview [92.07378559622889]
  We offer a comparative study of deep techniques in image denoising. We first classify the deep convolutional neural networks (CNNs) for additive white noisy images. Next, we compare the state-of-the-art methods on public denoising datasets in terms of quantitative and qualitative analysis.
  arXiv  Detail & Related papers  (2019-12-31T05:03:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.