Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction

Xie, Sihong; Zheng, Xinyu; Chen, Yang; Xie, Lizhe; Liu, Jin; Zhang, Yudong; Yan, Jun; Zhu, Hu; Hu, Yining

doi:10.1038/s41598-018-25153-w

Cited by 133 publications

(63 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to recently published work on neural network‐based low‐dose CT methods, some promising results were achieved, for example, CNN‐based networks such as Xie et al . and Thaler et al .…”

Section: Discussionmentioning

confidence: 99%

“…In addition, a variety of networks have been derived from basic convolutional neural networks (CNNs), including the U‐shaped network, the residual encoder–decoder convolutional neural network (RED‐CNN), and the wavelet network . In contrast to the above CNN‐based approaches that learn the transformation from a low‐quality to a high‐quality CT image, some studies, for example, Xie et al ,. try to extract artifacts from the FBP image, and these artifacts are then subtracted from the FBP image to obtain the clean reconstruction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks

Jiang

Sun

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Purpose: In recent years, health risks concerning high-dose x-ray radiation have become a major concern in dental computed tomography (CT) examinations. Therefore, adopting low-dose computed tomography (LDCT) technology has become a major focus in the CT imaging field. One of these LDCT technologies is downsampling data acquisition during low-dose x-ray imaging processes. However, reducing the radiation dose can adversely affect CT image quality by introducing noise and artifacts in the resultant image that can compromise diagnostic information. In this paper, we propose an artifact correction method for downsampling CT reconstruction based on deep learning. Method: We used clinical dental CT data with low-dose artifacts reconstructed by conventional filtered back projection (FBP) as inputs to a deep neural network and corresponding high-quality labeled normal-dose CT data during training. We trained a generative adversarial network (GAN) with Wasserstein distance (WGAN) and mean squared error (MSE) loss, called m-WGAN, to remove artifacts and obtain high-quality CT dental images in a clinical dental CT examination environment. Results: The experimental results confirmed that the proposed algorithm effectively removes lowdose artifacts from dental CT scans. In addition, we showed that the proposed method is efficient for removing noise from low-dose CT scan images compared to existing approaches. We compared the performances of the general GAN, convolutional neural networks, and m-WGAN. Through quantitative and qualitative analysis of the results, we concluded that the proposed m-WGAN method resulted in better artifact correction performance preserving the texture in dental CT scanning. Conclusions: The image quality evaluation metrics indicated that the proposed method effectively improves image quality when used as a postprocessing technique for dental CT images. To the best of our knowledge, this work is the first deep learning architecture used with a commercial cone-beam dental CT scanner. The artifact correction performance was rigorously evaluated and demonstrated to be effective. Therefore, we believe that the proposed algorithm represents a new direction in the research area of low-dose dental CT artifact correction.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks

Jiang

Sun

et al. 2019

Medical Physics

View full text Add to dashboard Cite

show abstract

“…To the best of our knowledge, there are few reported studies on MAR for dental CT using deep learning techniques. Recently, Xie et al [27] used a deep learning technique in reducing streak artifacts caused by sparse view sampling in a low-dose CT scan. They used an improved version of the GoogleNet (inception network) to reduce the streak artifacts in the CT images.…”

Section: Discussionmentioning

confidence: 99%

“…Currently, deep learning techniques are widely employed for medical image analysis. In the field of CT, deep learning techniques have been employed to reduce various kinds of artifacts caused by photon starvation, sparse view sampling, and metal objects [25][26][27][28][29][30][31], and are also employed to reduce noise in low-dose CT images [25,26]. To achieve MAR with deep learning, the deep learning network may be trained to estimate artifact-free CT images from the artifact-corrupted images if a huge number of artifact-corrupted images are available for network training, with the corresponding artifact-free images.…”

Section: Introductionmentioning

confidence: 99%

U-net based metal segmentation on projection domain for metal artifact reduction in dental CT

Hegazy

Cho

et al. 2019

Biomed. Eng. Lett.

View full text Add to dashboard Cite

Unlike medical computed tomography (CT), dental CT often suffers from severe metal artifacts stemming from high-density materials employed for dental prostheses. Despite the many metal artifact reduction (MAR) methods available for medical CT, those methods do not sufficiently reduce metal artifacts in dental CT images because MAR performance is often compromised by the enamel layer of teeth, whose X-ray attenuation coefficient is not so different from that of prosthetic materials. We propose a deep learning-based metal segmentation method on the projection domain to improve MAR performance in dental CT. We adopted a simplified U-net for metal segmentation on the projection domain without using any information from the metal-artifacts-corrupted CT images. After training the network with the projection data of five patients, we segmented the metal objects on the projection data of other patients using the trained network parameters. With the segmentation results, we corrected the projection data by applying region filling inside the segmented region. We fused two CT images, one from the corrected projection data and the other from the original raw projection data, and then we forward-projected the fused CT image to get the fused projection data. To get the final corrected projection data, we replaced the metal regions in the original projection data with the ones in the fused projection data. To evaluate the efficacy of the proposed segmentation method on MAR, we compared the MAR performance of the proposed segmentation method with a conventional MAR method based on metal segmentation on the CT image domain. For the MAR performance evaluation, we considered the three primary MAR performance metrics: the relative error (REL), the sum of square difference (SSD), and the normalized absolute difference (NAD). The proposed segmentation method improved MAR performances by around 5.7% for REL, 6.8% for SSD, and 8.2% for NAD. The proposed metal segmentation method on the projection domain showed better MAR performance than the conventional segmentation on the CT image domain. We expect that the proposed segmentation method can improve the performance of the existing MAR methods that are based on metal segmentation on the CT image domain.

show abstract

“…However, other complex algorithms are needed to reconstruct high-quality images from sparser datasets, such as model-based iterative reconstruction. Rather than employing complex iterative algorithms, we implemented a deep learning approach to reconstruct sparsely sampled sinograms as this technique has been demonstrated to compare favorably to state-of-the-art iterative algorithms for sparse-view image reconstruction [8,7]. We implemented FBPConvNet, a modified U-net [18] with multiresolution decomposition and residual learning as proposed by a prior work [8].…”

Section: Image Reconstructionmentioning

confidence: 99%

Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction

Lee

Huang

Yune

et al. 2019

Sci Rep

View full text Add to dashboard Cite

Recent advancements in deep learning for automated image processing and classification have accelerated many new applications for medical image analysis. However, most deep learning algorithms have been developed using reconstructed, human-interpretable medical images. While image reconstruction from raw sensor data is required for the creation of medical images, the reconstruction process only uses a partial representation of all the data acquired. Here, we report the development of a system to directly process raw computed tomography (CT) data in sinogram-space, bypassing the intermediary step of image reconstruction. Two classification tasks were evaluated for their feasibility of sinogram-space machine learning: body region identification and intracranial hemorrhage (ICH) detection. Our proposed SinoNet, a convolutional neural network optimized for interpreting sinograms, performed favorably compared to conventional reconstructed image-space-based systems for both tasks, regardless of scanning geometries in terms of projections or detectors. Further, SinoNet performed significantly better when using sparsely sampled sinograms than conventional networks operating in image-space. As a result, sinogram-space algorithms could be used in field settings for triage (presence of ICH), especially where low radiation dose is desired. These findings also demonstrate another strength of deep learning where it can analyze and interpret sinograms that are virtually impossible for human experts.

show abstract

Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction

Cited by 133 publications

References 23 publications

Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks

Artifact correction in low‐dose dental CT imaging using Wasserstein generative adversarial networks

U-net based metal segmentation on projection domain for metal artifact reduction in dental CT

Machine Friendly Machine Learning: Interpretation of Computed Tomography Without Image Reconstruction

Contact Info

Product

Resources

About