Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior

Chen, Yang; Gao, Da-Zhi; Nie, Cong; Luo, Limin; Chen, Wufan; Xia, Yin; Yi, Lin

doi:10.1016/j.compmedimag.2008.12.007

Cited by 130 publications

(103 citation statements)

References 12 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…Thus to limit the radiation dose, low-dose computed tomography (LDCT) could be applied for screening in patients at high risk for developing lung cancer [4]. Low dose CT can be achieved by decreasing the milliamperage and the voltage [5][6], which, however, leads to a degraded signal to noise ratio [7][8][9][10][11]. This is due to a severe increase of the quantum and electronic noise.…”

Section: Introductionmentioning

confidence: 99%

Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means

Chen¹,

Zhou²,

Hu³

et al. 2012

Phys. Med. Biol.

Self Cite

129

View full text Add to dashboard Cite

The x-ray exposure to patients has become a major concern in Computed Tomography (CT) and minimizing the radiation exposure has been one of the major efforts in CT field. Due to the plenty high-attenuation tissues in human chest, under low dose scan protocols, thoracic low-dose CT (LDCT) images tend to be severely degraded by excessive mottled noise and non-stationary streak artifacts. Their removal is rather a challenging task because the streak artifacts with directional prominence are often hard to be well discriminated from the attenuation information of normal tissues. This paper describes a two-step processing scheme called "Artifact Suppressed Large-scale Nonlocal Means" (AS-LNLM) for suppressing both noise and artifacts in thoracic LDCT images. Specific scale and direction properties were exploited to discriminate the noise and artifacts from image structures. Parallel implementation has been introduced to speed up the whole processing by more than 100 times. Phantom and patient CT images were both acquired for evaluation purpose. Comparative qualitative and quantitative analyses were both performed that allows concluding on the efficacy of our method in improving thoracic LDCT data.

show abstract

Section: Introductionmentioning

confidence: 99%

Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means

Chen¹,

Zhou²,

Hu³

et al. 2012

Phys. Med. Biol.

Self Cite

129

View full text Add to dashboard Cite

show abstract

“…Commonly used local regularization methods, such as local quadratic or non-quadratic regularization functions, are based on Gibbs' distribution functions, have a simple implementation form and can easily capture local image properties [8,12,13]. However, these functions produce overly smoothed image regions [8], induce staircase or piecewise blocky artefacts and result in contrast loss because they can provide indiscriminate local prior information available in the image and are less efficient due to their local behaviour [12,14].…”

Section: Introductionmentioning

confidence: 99%

“…This is generally modelled in the form of an explicitly defined regularization function, which is added to the data modelling term [5][6][7]. These methods can reduce reconstruction-based noise through better conditioning of the reconstruction problem using an emission object model [1,8]. A priori knowledge about object distribution properties can easily be included through regularization functions in order to obtain some user-defined characteristics of the resultant images, for example images bearing the highest required userdefined resolution, with an extra control over these properties through these functions [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

“…However, these functions produce overly smoothed image regions [8], induce staircase or piecewise blocky artefacts and result in contrast loss because they can provide indiscriminate local prior information available in the image and are less efficient due to their local behaviour [12,14]. Recently, several non-local regularization schemes have been introduced to combat these issues of local regularization [2,12,[14][15][16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

“…Recently, several non-local regularization schemes have been introduced to combat these issues of local regularization [2,12,[14][15][16][17][18][19][20]. Non-local regularization makes use of the global image connectivity and continuity available in the objective image and can prevent, somehow, over-smoothness with robust edge preservation at the same time, without appreciable staircase effects or contrast loss [2,8,[17][18][19][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Local and Non-local Regularization Techniques in Emission (PET/SPECT) Tomographic Image Reconstruction Methods

et al. 2015

View full text Add to dashboard Cite

Emission tomographic image reconstruction is an ill-posed problem due to limited and noisy data and various image-degrading effects affecting the data and leads to noisy reconstructions. Explicit regularization, through iterative reconstruction methods, is considered better to compensate for reconstruction-based noise. Local smoothing and edgepreserving regularization methods can reduce reconstructionbased noise. However, these methods produce overly smoothed images or blocky artefacts in the final image because they can only exploit local image properties. Recently, non-local regularization techniques have been introduced, to overcome these problems, by incorporating geometrical global continuity and connectivity present in the objective image. These techniques can overcome drawbacks of local regularization methods; however, they also have certain limitations, such as choice of the regularization function, neighbourhood size or calibration of several empirical parameters involved. This work compares different local and non-local regularization techniques used in emission tomographic imaging in general and emission computed tomography in specific for improved quality of the resultant images.

show abstract

Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising

Wang

Liu

Cheng

et al. 2023

J Applied Clin Med Phys

View full text Add to dashboard Cite

BackgroundDeep learning has been successfully applied to low‐dose CT (LDCT) denoising. But the training of the model is very dependent on an appropriate loss function. Existing denoising models often use per‐pixel loss, including mean abs error (MAE) and mean square error (MSE). This ignores the difference in denoising difficulty between different regions of the CT images and leads to the loss of large texture information in the generated image.PurposeIn this paper, we propose a new hybrid loss function that adapts to the noise in different regions of CT images to balance the denoising difficulty and preserve texture details, thus acquiring CT images with high‐quality diagnostic value using LDCT images, providing strong support for condition diagnosis.MethodsWe propose a hybrid loss function consisting of weighted patch loss (WPLoss) and high‐frequency information loss (HFLoss). To enhance the model's denoising ability of the local areas which are difficult to denoise, we improve the MAE to obtain WPLoss. After the generated image and the target image are divided into several patches, the loss weight of each patch is adaptively and dynamically adjusted according to its loss ratio. In addition, considering that texture details are contained in the high‐frequency information of the image, we use HFLoss to calculate the difference between CT images in the high‐frequency information part.ResultsOur hybrid loss function improves the denoising performance of several models in the experiment, and obtains a higher peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM). Moreover, through visual inspection of the generated results of the comparison experiment, the proposed hybrid function can effectively suppress noise and retain image details.ConclusionsWe propose a hybrid loss function for LDCT image denoising, which has good interpretation properties and can improve the denoising performance of existing models. And the validation results of multiple models using different datasets show that it has good generalization ability. By using this loss function, high‐quality CT images with low radiation are achieved, which can avoid the hazards caused by radiation and ensure the disease diagnosis for patients.

show abstract

Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior

Cited by 130 publications

References 12 publications

Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means

Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means

Local and Non-local Regularization Techniques in Emission (PET/SPECT) Tomographic Image Reconstruction Methods

Self‐adaption and texture generation: A hybrid loss function for low‐dose CT denoising

Contact Info

Product

Resources

About