LDCT image denoising algorithm based on two-dimensional variational mode decomposition and dictionary learning

Low-dose X-CT scanning method effectively reduces radiation hazards, however, reducing the radiation dose will introduce noise and artifacts during the projection process, resulting in a decrease in the quality of the reconstructed image. To address this problem, we combined 2D variational modal decomposition and dictionary learning. We proposed a low-dose CT (LDCT) image denoising algorithm based on an improved K-SVD algorithm with image decomposition. The dictionary obtained by K-SVD training lacks consideration of image structure information. To address this problem, we employ the two-dimensional variational mode decomposition (2D-VMD) method to decompose the image into distinct modal components. Through the adaptive learning of dictionaries based on the characteristics of each modal component, independent denoising processing is applied to each component, avoiding the loss of structural and detailed information in the image. In addition, we introduce the regularized orthogonal matching pursuit algorithm (ROMP) and dictionary atom optimization method to improve the sparse representation ability of the dictionary and reduce the impact of noise atoms on denoising performance. The experiments show that the proposed method outperforms other denoising methods regarding peak signal-to-noise ratio and structural similarity. The proposed method maintains the denoised image details and structural information while removing LDCT image noise and artifacts. The image quality after denoising is significantly improved and facilitates more accurate detection and analysis of lesion areas.

Superior objective and subjective image quality of deep learning reconstruction for low-dose abdominal CT imaging in comparison with model-based iterative reconstruction and filtered back projection

Objective:

This study aimed to conduct objective and subjective comparisons of image quality among abdominal computed tomography (CT) reconstructions with deep learning reconstruction (DLR) algorithms, model-based iterative reconstruction (MBIR), and filtered back projection (FBP).

Methods:

Datasets from consecutive patients who underwent low-dose liver CT were retrospectively identified. Images were reconstructed using DLR, MBIR, and FBP. Mean image noise and contrast-to-noise ratio (CNR) were calculated, and noise, artifacts, sharpness, and overall image quality were subjectively assessed. Dunnett’s test was used for statistical comparisons.

Results:

Ninety patients (67 ± 12.7 years; 63 males; mean body mass index [BMI], 25.5 kg/m²) were included. The mean noise in the abdominal aorta and hepatic parenchyma of DLR was lower than that in FBP and MBIR (p < .001). For FBP and MBIR, image noise was significantly higher for obese patients than for those with normal BMI. The CNR for the abdominal aorta and hepatic parenchyma was higher for DLR than for FBP and MBIR (p < .001). MBIR images were subjectively rated as superior to FBP images in terms of noise, artifacts, sharpness, and overall quality (p < .001). DLR images were rated as superior to MBIR images in terms of noise (p < .001) and overall quality (p = .03).

Conclusions:

Based on objective and subjective comparisons, the image quality of DLR was found to be superior to that of MBIR and FBP on low-dose abdominal CT. DLR was the only method for which image noise was not higher for obese patients than for those with a normal BMI.

Advances in knowledge:

This study provides previously unavailable information on the properties of DLR systems and their clinical utility.

Noise suppression-guided image filtering for low-SNR CT reconstruction

In practical computed tomography (CT) applications, projections with low signal-to-noise ratio (SNR) are often encountered due to the reduction of radiation dose or device limitations. In these situations, classical reconstruction algorithms, like simultaneous algebraic reconstruction technique (SART), cannot reconstruct high-quality CT images. Block-matching and 3D filtering (BM3D)-based iterative reconstruction algorithm (POCS-BM3D) has remarkable effect in dealing with CT reconstruction from noisy projections. However, BM3D may restrain noise with excessive loss of details in the case of low-SNR CT reconstruction. In order to achieve a preferable trade-off between noise suppression and edge preservation, we introduce guided image filtering (GIF) into low-SNR CT reconstruction, and propose noise suppression-guided image filtering reconstruction (NSGIFR) algorithm. In each iteration of NSGIFR, the output image of SART reserves more details and is used as input image of GIF, while the image denoised by BM3D serves as guidance image of GIF. Experimental results indicate that the proposed algorithm displays outstanding performance on preserving structures and suppressing noise for low-SNR CT reconstruction. NSGIFR can achieve more superior image quality than SART, POCS-TV and POCS-BM3D in terms of visual effect and quantitative analysis. Graphical abstract Block-matching and 3D filtering (BM3D)-based iterative reconstruction algorithm (POCS-BM3D) has remarkable effect in dealing with CT reconstruction from noisy projections. However, BM3D may restrain noise with excessive loss of details in the case of low-SNR CT reconstruction. In order to achieve a preferable trade-off between noise suppression and edge preservation, we introduce guided image filtering (GIF) into low-SNR CT reconstruction, and propose noise suppression-guided image filtering reconstruction (NSGIFR) algorithm.

Comparing feasibility of low-tube-voltage protocol with low-iodine-concentration contrast and high-tube-voltage protocol with high-iodine-concentration contrast in coronary computed tomography angiography

Background

To investigate the feasibility of a low tube voltage (80 kVp) protocol with low concentration contrast media (CM) (iodixanol 320 mgl/ml) as compared with a high tube voltage (100 kVp) protocol with high concentration CM (iomeprol 400 mgl/ml) in coronary CT angiography (CCTA) for patients with body mass index less than 30.

Materials and methods

A total of 93 patients were randomly assigned into three groups and underwent CCTA as follows: Group A) 100 kVp, 100–350 mAs, 400 mgl/ml CM at 4ml/s, and reconstructed with filtered back projection; Group B and C) 80 kVp, 100–450 mAs, 320 mgl/ml CM at 4 ml/s and 5 ml/s, respectively and reconstructed with iterative reconstruction. Objective and subjective image quality (IQ) was analyzed.

Results

The image noise, intravascular attenuation, signal-to-noise ratio and contrast-to-noise ratio of major coronary arteries did not differ significantly among three groups. Subjective IQ analyses on vascular attenuation and image noise did not differ significantly, either (all of p > 0.05). Qualitative IQ of Group B and C was non-inferior to that of Group A. Substantial reduction of radiation exposure was achieved in group B (2.60 ± 0.48 mSv) and C (2.72 ± 0.54 mSv), compared with group A (3.58 ± 0.67 mSv) (p < 0.05).

Conclusion

CCTA at 80 kVp with 320 mgl/ml CM and iterative reconstruction is feasible, achieving radiation dose reduction, while preserving IQ.

Feasibility of thin-slice abdominal CT in overweight patients using a vendor neutral image-based denoising algorithm: Assessment of image noise, contrast, and quality

The purpose of this study was to investigate whether the novel image-based noise reduction software (NRS) improves image quality, and to assess the feasibility of using this software in combination with hybrid iterative reconstruction (IR) in image quality on thin-slice abdominal CT. In this retrospective study, 54 patients who underwent dynamic liver CT between April and July 2017 and had a body mass index higher than 25 kg/m² were included. Three image sets of each patient were reconstructed as follows: hybrid IR images with 1-mm slice thickness (group A), hybrid IR images with 5-mm slice thickness (group B), and hybrid IR images with 1-mm slice thickness denoised using NRS (group C). The mean image noise and contrast-to-noise ratio relative to the muscle of the aorta and liver were assessed. Subjective image quality was evaluated by two radiologists for sharpness, noise, contrast, and overall quality using 5-point scales. The mean image noise was significantly lower in group C than in group A (p < 0.01), but no significant difference was observed between groups B and C. The contrast-to-noise ratio was significantly higher in group C than in group A (p < 0.01 and p = 0.01, respectively). Subjective image quality was also significantly higher in group C than in group A (p < 0.01), in terms of noise and overall quality, but not in terms of sharpness and contrast (p = 0.65 and 0.07, respectively). The contrast of images in group C was greater than that in group A, but this difference was not significant. Compared with hybrid IR alone, the novel NRS combined with a hybrid IR could result in significant noise reduction without sacrificing image quality on CT. This combined approach will likely be particularly useful for thin-slice abdominal CT examinations of overweight patients.

Low kV versus dual-energy virtual monoenergetic CT imaging for proven liver lesions: what are the advantages and trade-offs in conspicuity and image quality? A pilot study

PURPOSE

Single-energy low tube potential (SE-LTP) and dual-energy virtual monoenergetic (DE-VM) CT images both increase the conspicuity of hepatic lesions by increasing iodine signal. Our purpose was to compare the conspicuity of proven liver lesions, artifacts, and radiologist preferences in dose-matched SE-LTP and DE-VM images.

METHODS

Thirty-one patients with 72 proven liver lesions (21 benign, 51 malignant) underwent full-dose contrast-enhanced dual-energy CT (DECT). Half-dose images were obtained using single tube reconstruction of the dual-source SE-LTP projection data (80 or 100 kV), and by inserting noise into dual-energy projection data, with DE-VM images reconstructed from 40 to 70 keV. Three blinded gastrointestinal radiologists evaluated half-dose SE-LTP and DE-VM images, ranking and grading liver lesion conspicuity and diagnostic confidence (4-point scale) on a per-lesion basis. Image quality (noise, artifacts, sharpness) was evaluated, and overall image preference was ranked on per-patient basis. Lesion-to-liver contrast-to-noise ratio (CNR) was compared between techniques.

RESULTS

Mean lesion size was 1.5 ± 1.2 cm. Across the readers, the mean conspicuity ratings for 40, 45, and 50 keV half-dose DE-VM images were superior compared to other half-dose image sets (p < 0.0001). Per-lesion diagnostic confidence was similar between half-dose SE-LTP compared to half-dose DE-VM images (p ≥ 0.05; 1.19 vs. 1.24-1.32). However, SE-LTP images had less noise and artifacts and were sharper compared to DE-VM images less than 70 keV (p < 0.05). On a per-patient basis, radiologists preferred SE-LTP images the most and preferred 40-50 keV the least (p < 0.0001). Lesion CNR was also higher in SE-LTP images than DE-VM images (p < 0.01).

CONCLUSION

For the same applied dose level, liver lesions were more conspicuous using DE-VM compared to SE-LTP; however, SE-LTP images were preferred more than any single DE-VM energy level, likely due to lower noise and artifacts.

Evaluation of a projection-domain lung nodule insertion technique in thoracic computed tomography

Task-based assessment of computed tomography (CT) image quality requires a large number of cases with ground truth. Prospective case acquisition can be time-consuming. Inserting lesions into existing cases to simulate positive cases is a promising alternative. The aim was to evaluate a recently developed projection-based lesion insertion technique in thoracic CT. In total, 32 lung nodules of various attenuations were segmented from 21 patient cases, forward projected, inserted into projections, and reconstructed. Two experienced radiologists and two residents independently evaluated these nodules in two substudies. First, the 32 inserted and the 32 original nodules were presented in a randomized order and each received a score from 1 to 10 (1 = absolutely artificial to 10 = absolutely realistic). Second, the inserted and the corresponding original lesions were presented side-by-side to each reader. For the randomized evaluation, discrimination of real versus inserted nodules was poor with areas under the receiver operative characteristic curves being 0.57 [95% confidence interval (CI): 0.46 to 0.68], 0.69 (95% CI: 0.58 to 0.78), and 0.62 (95% CI: 0.54 to 0.69) for the two residents, two radiologists, and all four readers, respectively. Our projection-based lung nodule insertion technique provides a robust method to artificially generate positive cases that prove to be difficult to differentiate from real cases.

Discriminative feature representation: an effective postprocessing solution to low dose CT imaging

This paper proposes a concise and effective approach termed discriminative feature representation (DFR) for low dose computerized tomography (LDCT) image processing, which is currently a challenging problem in medical imaging field. This DFR method assumes LDCT images as the superposition of desirable high dose CT (HDCT) 3D features and undesirable noise-artifact 3D features (the combined term of noise and artifact features induced by low dose scan protocols), and the decomposed HDCT features are used to provide the processed LDCT images with higher quality. The target HDCT features are solved via the DFR algorithm using a featured dictionary composed by atoms representing HDCT features and noise-artifact features. In this study, the featured dictionary is efficiently built using physical phantom images collected from the same CT scanner as the target clinical LDCT images to process. The proposed DFR method also has good robustness in parameter setting for different CT scanner types. This DFR method can be directly applied to process DICOM formatted LDCT images, and has good applicability to current CT systems. Comparative experiments with abdomen LDCT data validate the good performance of the proposed approach.

Improving Low-dose Cardiac CT Images based on 3D Sparse Representation

Cardiac computed tomography (CCT) is a reliable and accurate tool for diagnosis of coronary artery diseases and is also frequently used in surgery guidance. Low-dose scans should be considered in order to alleviate the harm to patients caused by X-ray radiation. However, low dose CT (LDCT) images tend to be degraded by quantum noise and streak artifacts. In order to improve the cardiac LDCT image quality, a 3D sparse representation-based processing (3D SR) is proposed by exploiting the sparsity and regularity of 3D anatomical features in CCT. The proposed method was evaluated by a clinical study of 14 patients. The performance of the proposed method was compared to the 2D spares representation-based processing (2D SR) and the state-of-the-art noise reduction algorithm BM4D. The visual assessment, quantitative assessment and qualitative assessment results show that the proposed approach can lead to effective noise/artifact suppression and detail preservation. Compared to the other two tested methods, 3D SR method can obtain results with image quality most close to the reference standard dose CT (SDCT) images.

Methods for clinical evaluation of noise reduction techniques in abdominopelvic CT

Most noise reduction methods involve nonlinear processes, and objective evaluation of image quality can be challenging, since image noise cannot be fully characterized on the sole basis of the noise level at computed tomography (CT). Noise spatial correlation (or noise texture) is closely related to the detection and characterization of low-contrast objects and may be quantified by analyzing the noise power spectrum. High-contrast spatial resolution can be measured using the modulation transfer function and section sensitivity profile and is generally unaffected by noise reduction. Detectability of low-contrast lesions can be evaluated subjectively at varying dose levels using phantoms containing low-contrast objects. Clinical applications with inherent high-contrast abnormalities (eg, CT for renal calculi, CT enterography) permit larger dose reductions with denoising techniques. In low-contrast tasks such as detection of metastases in solid organs, dose reduction is substantially more limited by loss of lesion conspicuity due to loss of low-contrast spatial resolution and coarsening of noise texture. Existing noise reduction strategies for dose reduction have a substantial impact on lowering the radiation dose at CT. To preserve the diagnostic benefit of CT examination, thoughtful utilization of these strategies must be based on the inherent lesion-to-background contrast and the anatomy of interest. The authors provide an overview of existing noise reduction strategies for low-dose abdominopelvic CT, including analytic reconstruction, image and projection space denoising, and iterative reconstruction; review qualitative and quantitative tools for evaluating these strategies; and discuss the strengths and limitations of individual noise reduction methods.

Artifact suppressed dictionary learning for low-dose CT image processing

Low-dose computed tomography (LDCT) images are often severely degraded by amplified mottle noise and streak artifacts. These artifacts are often hard to suppress without introducing tissue blurring effects. In this paper, we propose to process LDCT images using a novel image-domain algorithm called "artifact suppressed dictionary learning (ASDL)." In this ASDL method, orientation and scale information on artifacts is exploited to train artifact atoms, which are then combined with tissue feature atoms to build three discriminative dictionaries. The streak artifacts are cancelled via a discriminative sparse representation operation based on these dictionaries. Then, a general dictionary learning processing is applied to further reduce the noise and residual artifacts. Qualitative and quantitative evaluations on a large set of abdominal and mediastinum CT images are carried out and the results show that the proposed method can be efficiently applied in most current CT systems.

Optimizing image quality for pediatric torso computed tomography: the use of advanced iterative reconstruction and wide-detector scanning techniques

OBJECTIVES

To compare radiation exposure and image quality in children undergoing torso helical acquisition computed tomography (CT) using filtered back projection (FBP) or adaptive iterative dose reduction (AIDR) 3D reconstruction algorithms. A secondary purpose is to compare radiation exposure and image quality in children undergoing torso CT acquired with helical or wide-detector techniques reconstructed with AIDR 3D.

METHODS

The study was approved by the institutional review board. Phase 1 included 200 helical torso CT studies: 100 using FBP and 100 using AIDR 3D. The size-specific dose estimate (SSDE) was calculated for each study. Region of interest (ROI) noise measurements were recorded in the thorax, abdomen, and pelvis for each study. Unpaired t tests compared SSDE and image noise for each group. Phase 2 included 100 wide-detector CT torso studies using AIDR 3D. Size-specific dose estimate and ROI noise measurements were calculated. Unpaired t tests compared helical and wide-detector SSDE and ROI. Additional t tests looked for age- and weight-specific differences in the helical and wide-detector groups.

RESULTS

Phase 1: AIDR 3D showed significant reduction in SSDE (P = 0.0001) and significant improvement in image quality. Phase 2: no significant difference in SSDE was observed. Children younger than 6 years had a significant reduction in SSDE with wide-detector technique (P = 0.0445) with no loss in image quality.

CONCLUSIONS

Adaptive iterative dose reduction 3D produces significant reduction in radiation dose without degradation to image quality compared with FBP. Significant dose reduction without loss of image quality can also be obtained in younger, smaller children using wide-detector technique.

Improving abdomen tumor low-dose CT images using dictionary learning based patch processing and unsharp filtering

Reducing patient radiation dose, while maintaining a high-quality image, is a major challenge in Computed Tomography (CT). The purpose of this work is to improve abdomen tumor low-dose CT (LDCT) image quality by using a two-step strategy: a first patch-wise non linear processing is first applied to suppress the noise and artifacts, that is based on a sparsity prior in term of a learned dictionary, then an unsharp filtering aiming to enhance the contrast of tissues and compensate the contrast loss caused by the DL processing. Preliminary results show that the proposed method is effective in suppressing mottled noise as well as improving tumor detectability.

Automatic selection of tube potential for radiation dose reduction in vascular and contrast-enhanced abdominopelvic CT

OBJECTIVE

The purpose of this study is to assess the ability of a novel automatic tube potential selection tool to reduce radiation dose while maintaining diagnostic quality in CT angiography (CTA) and contrast-enhanced abdominopelvic CT.

MATERIALS AND METHODS

One hundred one CTA examinations and 90 contrastenhanced abdominopelvic examinations were performed using an automatic tube potential selection tool on a 128-MDCT scanner. Two vascular radiologists and two abdominal radiologists evaluated the image quality for sharpness, noise, artifact, and diagnostic confidence. In a subset of patients who had undergone prior studies (CTA, 28 patients; abdominopelvic CT, 25 patients), a side-by-side comparison was performed by a separate radiologist. Dose reduction and iodine contrast-to-noise ratio resulting from use of the tool were calculated.

RESULTS

For CTA, 80 or 100 kV was selected for 73% of the scans, with a mean dose reduction of 36% relative to the reference 120-kV protocol. For abdominopelvic CT examinations, 80 or 100 kV was used for 55% of the scans, with a mean dose reduction of 25%. Overall dose reduction relative to the reference 120-kV protocol was 25% and 13% for CTA and abdominopelvic CT scans, respectively. Over 98% of scans had acceptable sharpness, noise texture, artifact, and diagnostic confidence for both readers and diagnostic tasks; 94-100% of scans had acceptable noise. Iodine contrast-to-noise ratio was significantly higher than (p < 0.001) or similar to (p = 0.11) that of prior scans, and equivalent quality was achieved despite the dose reduction.

CONCLUSION

Automatic tube potential selection provides an efficient and quantitativeway to guide the selection of the optimal tube potential for CTA and abdominopelvic CT examinations.

Low tube voltage intermediate tube current liver MDCT: sinogram-affirmed iterative reconstruction algorithm for detection of hypervascular hepatocellular carcinoma

OBJECTIVE

The purpose of this study was to compare image quality and lesion detectability in the evaluation of hypervascular hepatocellular carcinoma (HCC) on low-tube-voltage half-dose liver CT scans subjected to sinogram-affirmed iterative reconstruction (SAFIRE) with the quality and detectability on full-dose scans reconstructed with filtered back projection (FBP).

MATERIALS AND METHODS

A total of 126 patients with suspected HCC who underwent liver CT including arterial phase scanning at 80 kVp in the dual-source mode (300 mAs for each tube) were included in the study. The half-dose arterial scans were reconstructed with FBP, iterative reconstruction in image space (IRIS), and five SAFIRE strengths (S1-S5) and were compared with full-dose virtual scans (600 mA) reconstructed with FBP. We assessed image noise, contrast-to-noise ratio (CNR) of the liver and blood vessels, and lesionto-liver CNR. Two radiologists evaluated image quality and lesion detectability attained with the different imaging sets.

RESULTS

Image noise on SAFIRE images was significantly lower than that on the other images, and the CNRs on SAFIRE images were higher than those on half-dose FBP images (p < 0.001). In addition, lesion-to-liver CNR on the half-dose S5 SAFIRE images was higher than on IRIS and full-dose FBP images (p < 0.05). Among the half-dose scans, SAFIRE images had significantly better image quality than FBP images (p < 0.05). Regarding lesion detection, half-dose SAFIRE images were better than half-dose FBP images and were comparable with full-dose FBP images (observer 1, 91.8% vs 96%; observer 2, 98% vs 98%; p > 0.05).

CONCLUSION

Performing half-dose 80-kVp liver CT with SAFIRE technique may increase image quality and afford comparable lesion detectability of hypervascular HCC at a reduced radiation dose compared with full-dose CT with FBP.

Perspective on radiation risk in CT imaging

Awareness of and communication about issues related to radiation dose are beneficial for patients, clinicians, and radiology departments. Initiating and facilitating discussions of the net benefit of CT by enlisting comparisons to more familiar activities, or by conveying that the anticipated radiation dose to an exam is similar to or much less than annual background levels help resolve the concerns of many patients and providers. While radiation risk estimates at the low doses associated with CT contain considerable uncertainty, we choose to err on the side of safety by assuming a small risk exists, even though the risk at these dose levels may be zero. Thus, radiologists should individualize CT scans according to patient size and diagnostic task to ensure that maximum benefit and minimum risk is achieved. However, because the magnitude of net benefit is driven by the potential benefit of a positive exam, radiation dose should not be reduced if doing so may compromise making an accurate diagnosis. The benefits and risks of CT are also highly individualized, and require consideration of many factors by patients, clinicians, and radiologists. Radiologists can assist clinicians and patients with understanding many of these factors, including test performance, potential patient benefit, and estimates of potential risk.

Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing

In abdomen computed tomography (CT), repeated radiation exposures are often inevitable for cancer patients who receive surgery or radiotherapy guided by CT images. Low-dose scans should thus be considered in order to avoid the harm of accumulative x-ray radiation. This work is aimed at improving abdomen tumor CT images from low-dose scans by using a fast dictionary learning (DL) based processing. Stemming from sparse representation theory, the proposed patch-based DL approach allows effective suppression of both mottled noise and streak artifacts. The experiments carried out on clinical data show that the proposed method brings encouraging improvements in abdomen low-dose CT images with tumors.

New paradigm for management of hepatocellular carcinoma by imaging

Based on recent clinical practice guidelines, imaging is largely replacing pathology as the preferred diagnostic method for determination of hepatocellular carcinoma (HCC). A variety of imaging modalities, including ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), nuclear medicine, and angiography, are currently used to examine patients with chronic liver disease and suspected HCC. Advancements in imaging techniques such as perfusion imaging, diffusion imaging, and elastography along with the development of new contrast media will further improve the ability to detect and characterize HCC. Early diagnosis of HCC is essential for prompt treatment, which may in turn improve prognosis. Considering the process of hepatocarcinogenesis, it is important to evaluate sequential changes via imaging which would help to differentiate HCC from premalignant or benign lesions. Recent innovations including multiphasic examinations, high-resolution imaging, and the increased functional capabilities available with contrast-enhanced US, multidetector row CT, and MRI have raised the standards for HCC diagnosis. Although hemodynamic features of nodules in the cirrhotic liver remain the main diagnostic criterion, newly developed cellspecific contrast agents have shown great possibilities for improved HCC diagnosis and may overcome the diagnostic dilemma associated with small or borderline hepatocellular lesions. In the 20th century paradigm of medical imaging, radiological diagnosis was based on morphological characteristics, but in the 21st century, a paradigm shift to include biomedical, physiological, functional, and genetic imaging is needed. A multidisciplinary team approach is necessary to foster an integrated approach to HCC imaging. By developing and combining new imaging modalities, all phases of HCC patient care, including screening, diagnosis, treatment, and therapy, can be dramatically improved.