A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction

By Eunhee Kang, Junhong Min, Jong Chul Ye. Medical Physics (Lancaster), 2016

820 citations recorded by the source corpus.

Purpose: Due to the potential risk of inducing cancer, radiation exposure by X‐ray CT devices should be reduced for routine patient scanning. However, in low‐dose X‐ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high‐quality reconstruction method from low‐dose X‐ray CT data has become a major research topic in the CT community. Conventional model‐based de‐noising approaches are, however, computationally very expensive, and image‐domain de‐noising approaches cannot readily remove CT‐specific noise patterns. To tackle these problems, we want to develop a new low‐dose X‐ray CT algorithm based on a deep‐learning approach. Method: We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low‐dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra‐ and inter‐ band correlations, our deep network can effectively suppress CT‐specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. Results: Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X‐ray dose. In addition, we show that the wavelet‐domain CNN is efficient when used to remove noise from low‐dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 “Low‐Dose CT Grand Challenge.” Conclusions: To the best of our knowledge, this work is the first deep‐learning architecture for low‐dose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model‐based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low‐dose CT research.

Subfields: Biomedical Engineering, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/5bc52b33c3a0555025c9bc1a71eb533cd2702bbc

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. Jong Chul Ye
2. Paul S. Babyn
3. Xin Yi
4. Ozan Öktem
5. Yoseob Han
6. Jonas Adler
7. Jaejun Yoo
8. E. Cha

In Radiology, Nuclear Medicine and Imaging

1. Jong Chul Ye
2. Paul S. Babyn
3. Xin Yi
4. Yoseob Han
5. Ozan Öktem
6. Jonas Adler
7. Hyungjin Chung
8. Ge Wang

Citations in the corpus

• Improving Diffusion Models for Inverse Problems using Manifold Constraints (2022, methodology): “For experiments with CT, we train our model based on ncsnpp as a VE-SDE from score-SDE [41], on the 2016 American Association of Physicists in Medicine (AAPM) grand challenge dataset, and we process the data as in [23].”
• Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network (2017, methodology): “It is unclear howmuch dose reduction was achieved for the other deep learning based approaches [13, 33, 65, 67].”
• Deep Learning with Domain Adaptation for Accelerated Projection Reconstruction MR (2017, background): “Kang et al [15] provided the first systematic study of deep CNN for low-dose CT and showed that a deep CNN using directional wavelets is more efficient in removing low-dose related CT noises.”
• Model-Based Learning for Accelerated, Limited-View 3-D Photoacoustic Tomography (2017, background): “quality and corrupted images and then train a convolutional neural network (CNN) on removing those artefacts, see [19], [20] for an application to CT, [21] for PAT, and MRI [22].”
• Deep D-Bar: Real-Time Electrical Impedance Tomography Imaging With Deep Neural Networks (2017, background): “studied for several linear inverse problems in medical imaging, including CT [14], [15], MRI [16], and PAT [17], [18].”
• Generative Adversarial Networks for Noise Reduction in Low-Dose CT (2017, methodology): “λ1 > 0, λ2 = 0, as was previously proposed in [13] and [14].”
• Deep learning in medical imaging and radiation therapy. (2018, methodology): “This is important in modalities with ionizing radiation such as CT or PET for limiting patient dose, 237 – 239 , 241 or for limiting damage to samples in synchrotron-based After training with a limited number of high-dose training examples, they used the trained network to predict high-dose…”
• Deep learning in radiology: an overview of the concepts and a survey of the state of the art with focus on MRI (2018, methodology): “In contrast, a deep CNN has been trained with low-dose abdominal CT images for reconstruction of normal-dose CT.(102) Deep learning has also been applied to synthesizing images of different modalities.”
• Framing U-Net via Deep Convolutional Framelets: Application to Sparse-View CT (2017, background): “In CT applications, Kang et al [8] provided the first systematic study of deep convolutional neural network (CNN) for low-dose CT and showed that a deep CNN using directional wavelets is more efficient in removing low-dose related CT noises.”
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss (2017, methodology): “In the future, we plan to incorporate the WGANVGG network with more complicated generators such as the networks reported in [26] and [27] and extend these networks for image reconstruction from raw data by making a neural network counterpart of the FBP process.”
• Low-dose CT image and projection dataset (2020, methodology): “A deep convolutional neural network using directional wavelets for low-dose x-ray CT reconstruction.(25) 2.”
• Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks (2018, background): “[22] provided the first systematic study of deep CNN for low dose x-ray computed tomography (CT), and showed that a deep CNN using directional wavelets was more efficient in removing low dose related CT noise.”