Deep Learning Versus Iterative Reconstruction for CT Pulmonary Angiography in the Emergency Setting: Improved Image Quality and Reduced Radiation Dose

Low-tube-voltage whole-body CT angiography with extremely low iodine dose: a comparison between hybrid-iterative reconstruction and deep-learning image-reconstruction algorithms

AIM

To evaluate arterial enhancement, its depiction, and image quality in low-tube potential whole-body computed tomography (CT) angiography (CTA) with extremely low iodine dose and compare the results with those obtained by hybrid-iterative reconstruction (IR) and deep-learning image-reconstruction (DLIR) methods.

MATERIALS AND METHODS

This prospective study included 34 consecutive participants (27 men; mean age, 74.2 years) who underwent whole-body CTA at 80 kVp for evaluating aortic diseases between January and July 2020. Contrast material (240 mg iodine/ml) with simultaneous administration of its quarter volume of saline, which corresponded to 192 mg iodine/ml, was administered. CT raw data were reconstructed using adaptive statistical IR-Veo of 40% (hybrid-IR), DLIR with medium- (DLIR-M), and high-strength level (DLIR-H). A radiologist measured CT attenuation of the arteries and background noise, and the signal-to-noise ratio (SNR) was then calculated. Two reviewers qualitatively evaluated the arterial depictions and diagnostic acceptability on axial, multiplanar-reformatted (MPR), and volume-rendered (VR) images.

RESULTS

Mean contrast material volume and iodine weight administered were 64.1 ml and 15.4 g, respectively. The SNRs of the arteries were significantly higher in the following order of the DLIR-H, DLIR-M, and hybrid-IR (p<0.001). Depictions of six arteries on axial, three arteries on MPR, and four arteries on VR images were significantly superior in the DLIR-M or hybrid-IR than in the DLIR-H (p≤0.009 for each). Diagnostic acceptability was significantly better in the DLIR-M and DLIR-H than in the hybrid-IR (p<0.001-0.005).

CONCLUSION

DLIR-M showed well-balanced arterial depictions and image quality compared with the hybrid-IR and DLIR-H.

Deep learning-based algorithms for low-dose CT imaging: A review

The computed tomography (CT) technique is extensively employed as an imaging modality in clinical settings. The radiation dose of CT, however, is significantly high, thereby raising concerns regarding the potential radiation damage it may cause. The reduction of X-ray exposure dose in CT scanning may result in a significant decline in imaging quality, thereby elevating the risk of missed diagnosis and misdiagnosis. The reduction of CT radiation dose and acquisition of high-quality images to meet clinical diagnostic requirements have always been a critical research focus and challenge in the field of CT. Over the years, scholars have conducted extensive research on enhancing low-dose CT (LDCT) imaging algorithms, among which deep learning-based algorithms have demonstrated superior performance. In this review, we initially introduced the conventional algorithms for CT image reconstruction along with their respective advantages and disadvantages. Subsequently, we provided a detailed description of four aspects concerning the application of deep neural networks in LDCT imaging process: preprocessing in the projection domain, post-processing in the image domain, dual-domain processing imaging, and direct deep learning-based reconstruction (DLR). Furthermore, an analysis was conducted to evaluate the merits and demerits of each method. The commercial and clinical applications of the LDCT-DLR algorithm were also presented in an overview. Finally, we summarized the existing issues pertaining to LDCT-DLR and concluded the paper while outlining prospective trends for algorithmic advancement.

Comparison of two deep-learning image reconstruction algorithms on cardiac CT images: A phantom study

PURPOSE

The purpose of this study was to compare the performance of Precise IQ Engine (PIQE) and Advanced intelligent Clear-IQ Engine (AiCE) algorithms on image-quality according to the dose level in a cardiac computed tomography (CT) protocol.

MATERIALS AND METHODS

Acquisitions were performed using the CT ACR 464 phantom at three dose levels (volume CT dose indexes: 7.1/5.2/3.1 mGy) using a prospective cardiac CT protocol. Raw data were reconstructed using the three levels of AiCE and PIQE (Mild, Standard and Strong). The noise power spectrum (NPS) and task-based transfer function (TTF) for bone and acrylic inserts were computed. The detectability index (d') was computed to model the detectability of the coronary lumen (350 Hounsfield units and 4-mm diameter) and non-calcified plaque (40 Hounsfield units and 2-mm diameter).

RESULTS

Noise magnitude values were lower with PIQE than with AiCE (-13.4 ± 6.0 [standard deviation (SD)] % for Mild, -20.4 ± 4.0 [SD] % for Standard and -32.6 ± 2.6 [SD] % for Strong levels). The average NPS spatial frequencies shifted towards higher frequencies with PIQE than with AiCE (21.9 ± 3.5 [SD] % for Mild, 20.1 ± 3.0 [SD] % for Standard and 12.5 ± 3.5 [SD] % for Strong levels). The TTF values at fifty percent (f50) values shifted towards higher frequencies with PIQE than with AiCE for acrylic inserts but, for bone inserts, f50 values were found to be close. Whatever the dose and DLR level, d' values of both simulated cardiac lesions were higher with PIQE than with AiCE. For the simulated coronary lumen, d' values were better by 35.1 ± 9.3 (SD) % on average for all dose levels for Mild, 43.2 ± 5.0 (SD) % for Standard, and 62.6 ± 1.2 (SD) % for Strong levels.

CONCLUSION

Compared to AiCE, PIQE reduced noise, improved spatial resolution, noise texture and detectability of simulated cardiac lesions. PIQE seems to have a greater potential for dose reduction in cardiac CT acquisition.

Towards safer imaging: A comparative study of deep learning-based denoising and iterative reconstruction in intraindividual low-dose CT scans using an in-vivo large animal model

PURPOSE

Computed tomography (CT) scans are a significant source of medically induced radiation exposure. Novel deep learning-based denoising (DLD) algorithms have been shown to enable diagnostic image quality at lower radiation doses than iterative reconstruction (IR) methods. However, most comparative studies employ low-dose simulations due to ethical constraints. We used real intraindividual animal scans to investigate the dose-reduction capabilities of a DLD algorithm in comparison to IR.

MATERIALS AND METHODS

Fourteen veterinarian-sedated alive pigs underwent 2 CT scans on the same 3rd generation dual-source scanner with two months between each scan. Four additional scans ensued each time, with mAs reduced to 50 %, 25 %, 10 %, and 5 %. All scans were reconstructed ADMIRE levels 2 (IR2) and a novel DLD algorithm, resulting in 280 datasets. Objective image quality (CT numbers stability, noise, and contrast-to-noise ratio) was measured via consistent regions of interest. Three radiologists independently rated all possible dataset combinations per time point for subjective image quality (-1 = inferior, 0 = equal, 1 = superior). The points were averaged for a semiquantitative score, and inter-rater agreement was measured using Spearman's correlation coefficient and adequately corrected mixed-effects modeling analyzed objective and subjective image quality.

RESULTS

Neither dose-reduction nor reconstruction method negatively impacted CT number stability (p > 0.999). In objective image quality assessment, the lowest radiation dose achievable by DLD when comparing noise (p = 0.544) and CNR (p = 0.115) to 100 % IR2 was 25 %. Overall, inter-rater agreement of the subjective image quality ratings was strong (r ≥ 0.69, mean 0.93 ± 0.05, 95 % CI 0.92-0.94; each p < 0.001), and subjective assessments corroborated that DLD at 25 % radiation dose was comparable to 100 % IR2 in image quality, sharpness, and contrast (p ≥ 0.281).

CONCLUSIONS

The DLD algorithm can achieve image quality comparable to the standard IR method but with a significant dose reduction of up to 75%. This suggests a promising avenue for lowering patient radiation exposure without sacrificing diagnostic quality.

Measurement of solid size in early-stage lung adenocarcinoma by virtual 3D thin-section CT applied artificial intelligence

An artificial intelligence (AI) system that reconstructs virtual 3D thin-section CT (TSCT) images from conventional CT images by applying deep learning was developed. The aim of this study was to investigate whether virtual and real TSCT could measure the solid size of early-stage lung adenocarcinoma. The pair of original thin-CT and simulated thick-CT from the training data with TSCT images (thickness, 0.5-1.0 mm) of 2700 pulmonary nodules were used to train the thin-CT generator in the generative adversarial network (GAN) framework and develop a virtual TSCT AI system. For validation, CT images of 93 stage 0-I lung adenocarcinomas were collected, and virtual TSCTs were reconstructed from conventional 5-mm thick-CT images using the AI system. Two radiologists measured and compared the solid size of tumors on conventional CT and virtual and real TSCT. The agreement between the two observers showed an almost perfect agreement on the virtual TSCT for solid size measurements (intraclass correlation coefficient = 0.967, P < 0.001, respectively). The virtual TSCT had a significantly stronger correlation than that of conventional CT (P = 0.003 and P = 0.001, respectively). The degree of agreement between the clinical T stage determined by virtual TSCT and the clinical T stage determined by real TSCT was excellent in both observers (k = 0.882 and k = 0.881, respectively). The AI system developed in this study was able to measure the solid size of early-stage lung adenocarcinoma on virtual TSCT as well as on real TSCT.

A Systematic Literature Review of 3D Deep Learning Techniques in Computed Tomography Reconstruction

Computed tomography (CT) is used in a wide range of medical imaging diagnoses. However, the reconstruction of CT images from raw projection data is inherently complex and is subject to artifacts and noise, which compromises image quality and accuracy. In order to address these challenges, deep learning developments have the potential to improve the reconstruction of computed tomography images. In this regard, our research aim is to determine the techniques that are used for 3D deep learning in CT reconstruction and to identify the training and validation datasets that are accessible. This research was performed on five databases. After a careful assessment of each record based on the objective and scope of the study, we selected 60 research articles for this review. This systematic literature review revealed that convolutional neural networks (CNNs), 3D convolutional neural networks (3D CNNs), and deep learning reconstruction (DLR) were the most suitable deep learning algorithms for CT reconstruction. Additionally, two major datasets appropriate for training and developing deep learning systems were identified: 2016 NIH-AAPM-Mayo and MSCT. These datasets are important resources for the creation and assessment of CT reconstruction models. According to the results, 3D deep learning may increase the effectiveness of CT image reconstruction, boost image quality, and lower radiation exposure. By using these deep learning approaches, CT image reconstruction may be made more precise and effective, improving patient outcomes, diagnostic accuracy, and healthcare system productivity.

Three-dimensional CT imaging in extensor tendons using deep learning reconstruction: optimal reconstruction parameters and the influence of dose

The purpose of this study was to assess the optimal reconstruction parameters and the influence of tube current in extensor tendons three-dimensional computed tomography (3D CT) using deep learning reconstruction, using iterative reconstruction as a reference. In the phantom study, a cylindrical phantom with a 3 mm rod simulated an extensor tendon was used. The phantom images were acquired at tube current of 50, 100, 150, 200, and 250 mA. In the clinical study, CT scans of hand tendons were performed on nine hands from eight patients. All images were reconstructed using advanced intelligent clear-IQ engine (AiCE) parameters (body, body sharp, brain CTA, and brain LCD) and adaptive iterative dose reduction three dimensional (AIDR 3D). The objective image quality for tendon detectability was evaluated by calculating the low-contrast object specific contrast-to-noise ratio (CNRLO) in the phantom study and CNR and coefficient of variation (CV) in the clinical study. In the phantom study, CNRLO (at 200 mA) of AiCE parameters (body, body sharp, brain CTA, and brain LCD) and AIDR 3D were 5.2, 5.3, 5.3, 5.8, and 5.0, respectively. In the clinical study, AiCE brain CTA was higher CNR and lower CV values compared to other reconstruction parameters. AiCE without dose reduction may be an effective strategy for further improving the image quality of extensor tendons 3D CT. Our study suggests that the AiCE brain CTA is more suitable for extensor tendons 3D CT compared to other AiCE parameters.

Deep Learning Reconstruction Improves the Image Quality of CT Angiography Derived From 80-kVp Cerebral CT Perfusion Data

RATIONALE AND OBJECTIVE

To investigate the impact of the deep learning reconstruction (DLR) technique on the image quality of CT angiography (CTA) derived from 80-kVp cerebral CT perfusion (CTP) data and compare it with hybrid-iterative reconstruction (HIR).

MATERIALS AND METHODS

Thirty-three patients underwent CTP at 80 kVp were prospectively enrolled. CTP data were reconstructed with HIR and DLR. Four image datasets were reconstructed: HIRpeak and DLRpeak were single arterial phase images derived from the time point showing the peak value, HIRtMIP and HIRtAve were time-resolved maximum intensity projection image and time-resolved average image derived from three time points with the greatest enhancement of HIR. The mean CT values, standard deviation, signal-to-noise ratio, and contrast-to-noise ratio of the internal carotid artery and basilar artery were compared among the four image dataset. Image quality was performed using a five-point rating scale. Arterial stenosis was evaluated.

RESULTS

DLRpeak had the highest CT value and contrast-to-noise ratio in the internal carotid artery and basilar artery (all p < 0.001). DLRpeak showed the best subjective image quality and had the highest score (4.93 ± 0.4) compared to the other three HIR CTA images (all p < 0.001). The degree of vascular stenosis was consistent among the four evaluated sequences (HIRtAve, HIRpeak, and HIRtMIP DLRpeak).

CONCLUSION

For CTA derived from 80-kVp cerebral CTP data, images reconstructed with deep learning showed better image quality and improved intracranial artery visualization than those processed with HIR and other currently used techniques.

[Opportunities for artificial intelligence in radiation protection : Improving safety of diagnostic imaging]

CLINICAL/METHODOLOGICAL ISSUE

Imaging of structures of internal organs often requires ionizing radiation, which is a health risk. Reducing the radiation dose can increase the image noise, which means that images provide less information.

STANDARD RADIOLOGICAL METHODS

This problem is observed in commonly used medical imaging modalities such as computed tomography (CT), positron emission tomography (PET), single photon emission computed tomography (SPECT), angiography, fluoroscopy, and any modality that uses ionizing radiation for imaging.

METHODOLOGICAL INNOVATIONS

Artificial intelligence (AI) can improve the quality of low-dose images and help minimize radiation exposure. Potential applications are explored, and frameworks and procedures are critically evaluated.

PERFORMANCE

The performance of AI models varies. High-performance models could be used in clinical settings in the near future. Several challenges (e.g., quantitative accuracy, insufficient training data) must be addressed for optimal performance and widespread adoption of this technology in the field of medical imaging.

PRACTICAL RECOMMENDATIONS

To fully realize the potential of AI and deep learning (DL) in medical imaging, research and development must be intensified. In particular, quality control of AI models must be ensured, and training and testing data must be uncorrelated and quality assured. With sufficient scientific validation and rigorous quality management, AI could contribute to the safe use of low-dose techniques in medical imaging.

Image quality comparison of lower extremity CTA between CT routine reconstruction algorithms and deep learning reconstruction

BACKGROUND

To evaluate the image quality of lower extremity computed tomography angiography (CTA) with deep learning-based reconstruction (DLR) compared to model-based iterative reconstruction (MBIR), hybrid-iterative reconstruction (HIR), and filtered back projection (FBP).

METHODS

Fifty patients (38 males, average age 59.8 ± 19.2 years) who underwent lower extremity CTA between January and May 2021 were included. Images were reconstructed with DLR, MBIR, HIR, and FBP. The standard deviation (SD), contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), noise power spectrum (NPS) curves, and the blur effect, were calculated. The subjective image quality was independently evaluated by two radiologists. The diagnostic accuracy of DLR, MBIR, HIR, and FBP reconstruction algorithms was calculated.

RESULTS

The CNR and SNR were significantly higher in DLR images than in the other three reconstruction algorithms, and the SD was significantly lower in DLR images of the soft tissues. The noise magnitude was the lowest with DLR. The NPS average spatial frequency (f_av) values were higher using DLR than HIR. For blur effect evaluation, DLR and FBP were similar for soft tissues and the popliteal artery, which was better than HIR and worse than MBIR. In the aorta and femoral arteries, the blur effect of DLR was worse than MBIR and FBP and better than HIR. The subjective image quality score of DLR was the highest. The sensitivity and specificity of the lower extremity CTA with DLR were the highest in the four reconstruction algorithms with 98.4% and 97.2%, respectively.

CONCLUSIONS

Compared to the other three reconstruction algorithms, DLR showed better objective and subjective image quality. The blur effect of the DLR was better than that of the HIR. The diagnostic accuracy of lower extremity CTA with DLR was the best among the four reconstruction algorithms.

Auto-Detection of Motion Artifacts on CT Pulmonary Angiograms with a Physician-Trained AI Algorithm

Purpose: Motion-impaired CT images can result in limited or suboptimal diagnostic interpretation (with missed or miscalled lesions) and patient recall. We trained and tested an artificial intelligence (AI) model for identifying substantial motion artifacts on CT pulmonary angiography (CTPA) that have a negative impact on diagnostic interpretation. Methods: With IRB approval and HIPAA compliance, we queried our multicenter radiology report database (mPower, Nuance) for CTPA reports between July 2015 and March 2022 for the following terms: "motion artifacts", "respiratory motion", "technically inadequate", and "suboptimal" or "limited exam". All CTPA reports were from two quaternary (Site A, n = 335; B, n = 259) and a community (C, n = 199) healthcare sites. A thoracic radiologist reviewed CT images of all positive hits for motion artifacts (present or absent) and their severity (no diagnostic effect or major diagnostic impairment). Coronal multiplanar images from 793 CTPA exams were de-identified and exported offline into an AI model building prototype (Cognex Vision Pro, Cognex Corporation) to train an AI model to perform two-class classification ("motion" or "no motion") with data from the three sites (70% training dataset, n = 554; 30% validation dataset, n = 239). Separately, data from Site A and Site C were used for training and validating; testing was performed on the Site B CTPA exams. A five-fold repeated cross-validation was performed to evaluate the model performance with accuracy and receiver operating characteristics analysis (ROC). Results: Among the CTPA images from 793 patients (mean age 63 ± 17 years; 391 males, 402 females), 372 had no motion artifacts, and 421 had substantial motion artifacts. The statistics for the average performance of the AI model after five-fold repeated cross-validation for the two-class classification included 94% sensitivity, 91% specificity, 93% accuracy, and 0.93 area under the ROC curve (AUC: 95% CI 0.89-0.97). Conclusion: The AI model used in this study can successfully identify CTPA exams with diagnostic interpretation limiting motion artifacts in multicenter training and test datasets. Clinical relevance: The AI model used in the study can help alert technologists about the presence of substantial motion artifacts on CTPA, where a repeat image acquisition can help salvage diagnostic information.

Technical note: Phantom-based training framework for convolutional neural network CT noise reduction

BACKGROUND

Deep artificial neural networks such as convolutional neural networks (CNNs) have been shown to be effective models for reducing noise in CT images while preserving anatomic details. A practical bottleneck for developing CNN-based denoising models is the procurement of training data consisting of paired examples of high-noise and low-noise CT images. Obtaining these paired data are not practical in a clinical setting where the raw projection data is not available. This work outlines a technique to optimize CNN denoising models using methods that are available in a routine clinical setting.

PURPOSE

To demonstrate a phantom-based training framework for CNN noise reduction that can be efficiently implemented on any CT scanner.

METHODS

The phantom-based training framework uses supervised learning in which training data are synthesized using an image-based noise insertion technique. Ten patient image series were used for training and validation (9:1) and noise-only images obtained from anthropomorphic phantom scans. Phantom noise-only images were superimposed on patient images to imitate low-dose CT images for use in training. A modified U-Net architecture was used with mean-squared-error and feature reconstruction loss. The training framework was tested for clinically indicated whole-body-low-dose CT images, as well as routine abdomen-pelvis exams for which projection data was unavailable. Performance was assessed based on root-mean-square error, structural similarity, line profiles, and visual assessment.

RESULTS

When the CNN was tested on five reserved quarter-dose whole-body-low-dose CT images, noise was reduced by 75%, root-mean-square-error reduced by 34%, and structural similarity increased by 60%. Visual analysis and line profiles indicated that the method significantly reduced noise while maintaining spatial resolution of anatomic features.

CONCLUSION

The proposed phantom-based training framework demonstrated strong noise reduction while preserving spatial detail. Because this method is based within the image domain, it can be easily implemented without access to projection data.

Improvement in Image Quality and Visibility of Coronary Arteries, Stents, and Valve Structures on CT Angiography by Deep Learning Reconstruction

OBJECTIVE

This study aimed to investigate whether a deep learning reconstruction (DLR) method improves the image quality, stent evaluation, and visibility of the valve apparatus in coronary computed tomography angiography (CCTA) when compared with filtered back projection (FBP) and hybrid iterative reconstruction (IR) methods.

MATERIALS AND METHODS

CCTA images of 51 patients (mean age ± standard deviation [SD], 63.9 ± 9.8 years, 36 male) who underwent examination at a single institution were reconstructed using DLR, FBP, and hybrid IR methods and reviewed. CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and stent evaluation, including 10%-90% edge rise slope (ERS) and 10%-90% edge rise distance (ERD), were measured. Quantitative data are summarized as the mean ± SD. The subjective visual scores (1 for worst -5 for best) of the images were obtained for the following: overall image quality, image noise, and appearance of stent, vessel, and aortic and tricuspid valve apparatus (annulus, leaflets, papillary muscles, and chordae tendineae). These parameters were compared between the DLR, FBP, and hybrid IR methods.

RESULTS

DLR provided higher Hounsfield unit (HU) values in the aorta and similar attenuation in the fat and muscle compared with FBP and hybrid IR. The image noise in HU was significantly lower in DLR (12.6 ± 2.2) than in hybrid IR (24.2 ± 3.0) and FBP (54.2 ± 9.5) (p < 0.001). The SNR and CNR were significantly higher in the DLR group than in the FBP and hybrid IR groups (p < 0.001). In the coronary stent, the mean value of ERS was significantly higher in DLR (1260.4 ± 242.5 HU/mm) than that of FBP (801.9 ± 170.7 HU/mm) and hybrid IR (641.9 ± 112.0 HU/mm). The mean value of ERD was measured as 0.8 ± 0.1 mm for DLR while it was 1.1 ± 0.2 mm for FBP and 1.1 ± 0.2 mm for hybrid IR. The subjective visual scores were higher in the DLR than in the images reconstructed with FBP and hybrid IR.

CONCLUSION

DLR reconstruction provided better images than FBP and hybrid IR reconstruction.

Improved image quality and dose reduction in abdominal CT with deep-learning reconstruction algorithm: a phantom study

OBJECTIVES

To assess the impact of a new artificial intelligence deep-learning reconstruction (Precise Image; AI-DLR) algorithm on image quality against a hybrid iterative reconstruction (IR) algorithm in abdominal CT for different clinical indications.

METHODS

Acquisitions on phantoms were performed at 5 dose levels (CTDI_vol: 13/11/9/6/1.8 mGy). Raw data were reconstructed using level 4 of iDose⁴ (i4) and 3 levels of AI-DLR (Smoother/Smooth/Standard). Noise power spectrum (NPS), task-based transfer function (TTF) and detectability index (d') were computed: d' modelled detection of a liver metastasis (LM) and hepatocellular carcinoma at portal (HCCp) and arterial (HCCa) phases. Image quality was subjectively assessed on an anthropomorphic phantom by 2 radiologists.

RESULTS

From Standard to Smoother levels, noise magnitude and average NPS spatial frequency decreased and the detectability (d') of all simulated lesions increased. For both inserts, TTF values were similar for all three AI-DLR levels from 13 to 6 mGy but decreased from Standard to Smoother levels at 1.8 mGy. Compared to the i4 used in clinical practice, d' values were higher using the Smoother and Smooth levels and close for the Standard level. For all dose levels, except at 1.8 mGy, radiologists considered images satisfactory for clinical use for the 3 levels of AI-DLR, but rated images too smooth using the Smoother level.

CONCLUSION

Use of the Smooth and Smoother levels of AI-DLR reduces the image noise and improves the detectability of lesions and spatial resolution for standard and low-dose levels. Using the Smooth level is apparently the best compromise between the lowest dose level and adequate image quality.

KEY POINTS

• Evaluation of the impact of a new artificial intelligence deep-learning reconstruction (AI-DLR) on image quality and dose compared to a hybrid iterative reconstruction (IR) algorithm. • The Smooth and Smoother levels of AI-DLR reduced the image noise and improved the detectability of lesions and spatial resolution for standard and low-dose levels. • The Smooth level seems the best compromise between the lowest dose level and adequate image quality.

Deep learning versus iterative reconstruction on image quality and dose reduction in abdominal CT: a live animal study

Objective. While simulated low-dose CT images and phantom studies cannot fully approximate subjective and objective effects of deep learning (DL) denoising on image quality, live animal models may afford this assessment. This study is to investigate the potential of DL in CT dose reduction on image quality compared to iterative reconstruction (IR). Approach. The upper abdomen of a live 4 year old sheep was scanned on a CT scanner at different exposure levels. Images were reconstructed using FBP and ADMIRE with 5 strengths. A modularized DL network with 5 modules was used for image reconstruction via progressive denoising. Radiomic features were extracted from a region over the liver. Concordance correlation coefficient (CCC) was applied to quantify agreement between any two sets of radiomic features. Coefficient of variation was calculated to measure variation in a radiomic feature series. Structural similarity index (SSIM) was used to measure the similarity between any two images. Diagnostic quality, low-contrast detectability, and image texture were qualitatively evaluated by two radiologists. Pearson correlation coefficient was computed across all dose-reconstruction/denoising combinations. Results. A total of 66 image sets, with 405 radiomic features extracted from each, are analyzed. IR and DL can improve diagnostic quality and low-contrast detectability and similarly modulate image texture features. In terms of SSIM, DL has higher potential in preserving image structure. There is strong correlation between SSIM and radiologists’ evaluations for diagnostic quality (0.559) and low-contrast detectability (0.635) but moderate correlation for texture (0.313). There is moderate correlation between CCC of radiomic features and radiologists’ evaluation for diagnostic quality (0.397), low-contrast detectability (0.417), and texture (0.326), implying that improvement of image features may not relate to improvement of diagnostic quality. Conclusion. DL shows potential to further reduce radiation dose while preserving structural similarity, while IR is favored by radiologists and more predictably alters radiomic features.

Can deep learning improve image quality of low-dose CT: a prospective study in interstitial lung disease

OBJECTIVES

To investigate whether deep learning reconstruction (DLR) could keep image quality and reduce radiation dose in interstitial lung disease (ILD) patients compared with HRCT reconstructed with hybrid iterative reconstruction (hybrid-IR).

METHODS

Seventy ILD patients were prospectively enrolled and underwent HRCT (120 kVp, automatic tube current) and LDCT (120 kVp, 30 mAs) scans. HRCT images were reconstructed with hybrid-IR (Adaptive Iterative Dose Reduction 3-Dimensional [AIDR3D], standard-setting); LDCT images were reconstructed with DLR (Advanced Intelligence Clear-IQ Engine [AiCE], lung/bone, mild/standard/strong setting). Image noise, streak artifact, overall image quality, and visualization of normal and abnormal features of ILD were evaluated.

RESULTS

The mean radiation dose of LDCT was 38% of HRCT. Objective image noise of reconstructed LDCT images was 33.6 to 111.3% of HRCT, and signal-to-noise ratio (SNR) was 0.9 to 3.1 times of the latter (p < 0.001). LDCT-AiCE was not significantly different from or even better than HRCT in overall image quality and visualization of normal lung structures. LDCT-AiCE (lung, mild/standard/strong) showed progressively better recognition of ground glass opacity than HRCT-AIDR3D (p < 0.05, p < 0.01, p < 0.001), and LDCT-AiCE (lung, mild/standard/strong; bone, mild) was superior to HRCT-AIDR3D in visualization of architectural distortion (p < 0.01, p < 0.01, p < 0.01; p < 0.05). LDCT-AiCE (bone, strong) was better than HRCT-AIDR3D in the assessment of bronchiectasis and/or bronchiolectasis (p < 0.05). LDCT-AiCE (bone, mild/standard/strong) was significantly better at the visualization of honeycombing than HRCT-AIDR3D (p < 0.05, p < 0.05, p < 0.01).

CONCLUSION

Deep learning reconstruction could effectively reduce radiation dose and keep image quality in ILD patients compared to HRCT with hybrid-IR.

KEY POINTS

• Deep learning reconstruction was a novel image reconstruction algorithm based on deep convolutional neural networks. It was applied in chest CT studies and received auspicious results. • HRCT plays an essential role in the whole process of diagnosis, treatment efficacy evaluation, and follow-ups for interstitial lung disease patients. However, cumulative radiation exposure could increase the risks of cancer. • Deep learning reconstruction method could effectively reduce the radiation dose and keep the image quality compared with HRCT reconstructed with hybrid iterative reconstruction in patients with interstitial lung disease.

Impact of an artificial intelligence deep-learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study

Background

Recently, computed tomography (CT) manufacturers have developed deep‐learning‐based reconstruction algorithms to compensate for the limitations of iterative reconstruction (IR) algorithms, such as image smoothing and the spatial resolution's dependence on contrast and dose levels.

Purpose

To assess the impact of an artificial intelligence deep‐learning reconstruction (AI‐DLR) algorithm on image quality and dose reduction compared with a hybrid IR algorithm in chest CT for different clinical indications.

Methods

Acquisitions on the CT American College of Radiology (ACR) 464 and CT Torso CTU‐41 phantoms were performed at five dose levels (CTDI_vol: 9.5/7.5/6/2.5/0.4 mGy) used for chest CT conditions. Raw data were reconstructed using filtered backprojection, two levels of IR (iDose⁴ levels 4 (i4) and 7 (i7)), and five levels of AI‐DLR (Precise Image; Smoother, Smooth, Standard, Sharp, Sharper). Noise power spectrum (NPS), task‐based transfer function, and detectability index (d′) were computed: d′‐modeled detection of a soft tissue mediastinal nodule (low‐contrast soft tissue chest nodule within the mediastinum [LCN]), ground‐glass opacity (GGO), or high‐contrast pulmonary (HCP) lesion. The subjective image quality of chest anthropomorphic phantom images was independently evaluated by two radiologists. They assessed image noise, image smoothing, contrast between vessels and fat in the mediastinum for mediastinal images, visual border detection between bronchus and lung parenchyma for parenchymal images, and overall image quality using a commonly used four‐ or five‐point scale.

Results

From Standard to Smoother levels, on average, the noise magnitude decreased (for all dose levels: −66.3% ± 0.5% for mediastinal images and −63.1% ± 0.1% for parenchymal images), the average NPS spatial frequency decreased (for all dose levels: −35.3% ± 2.2% for mediastinal images and −13.3% ± 2.2% for parenchymal images), and the detectability (d′) of the three lesions increased. The opposite pattern was found from Standard to Sharper levels. From Smoother to Sharper levels, the spatial resolution increased for the low‐contrast polyethylene insert and the opposite for the high‐contrast air insert. Compared to the i4 used in clinical practice, d′ values were higher using Smoother (mean for all dose levels: 338.7% ± 29.4%), Smooth (103.4% ± 11.2%), and Standard (34.1% ± 6.6%) levels for the LCN on mediastinal images and Smoother (169.5% ± 53.2% for GGO and 136.9% ± 1.6% for HCP) and Smooth (36.4% ± 22.1% and 24.1% ± 0.9%, respectively) levels for parenchymal images. Radiologists considered the images satisfactory for clinical use at these levels, but adaptation to the dose level of the protocol is required.

Conclusion

With AI‐DLR, the smoothest levels reduced the noise and improved the detectability of chest lesions but increased the image smoothing. The opposite was found with the sharpest levels. The choice of level depends on the dose level and type of image: mediastinal or parenchymal.

Feasibility of Deep Learning-Based Noise and Artifact Reduction in Coronal Reformation of Contrast-Enhanced Chest Computed Tomography

PURPOSE

This study aimed to evaluate the feasibility of a deep learning method for imaging artifact and noise reduction in coronal reformation of contrast-enhanced chest computed tomography (CT).

METHODS

A total of 19,052 coronal reformatted chest CT images of 110 CT image sets (55 pairs of concordant 16- and 320-row CT image sets) were included and used to train a deep learning algorithm for artifact and noise correction. For internal validation, 4093 coronal reformatted CT images of 25 patients from 16-row CT images underwent correction processing. For external validation, chest CT images of 30 patients (1028 coronal reformatted CT images), acquired in other institutions using different scanners, were subjected to correction processing. For both validations, image quality was compared between original ("CTorigin") and deep learning-based corrected ("CTcorrect") CT images. Quantitative analysis for stair-step artifact (coefficient of variance of CT density on coronal reformation), image noise, signal-to-noise ratio, and contrast-to-noise ratio were evaluated. Subjective image quality scores were assigned for image contrast, artifact, and conspicuity of major structures.

RESULTS

CTcorrect showed significantly reduced stair-step artifact (mean coefficient of variance: CTorigin 7.35 ± 2.0 vs CTcorrect 5.17 ± 2.4, P < 0.001) and image noise and improved signal-to-noise ratio and contrast-to-noise ratio in the aorta, pulmonary artery, and liver, compared with those of CTorigin (P < 0.01). On subjective analysis, CTcorrect had higher image contrast, lower artifact, and better conspicuity than CTorigin. Most results of the external validation were consistent with those obtained from the internal validation, except for those concerning the pulmonary artery.

CONCLUSIONS

Deep learning-based artifact correction significantly improved the image quality of coronal reformation chest CT by reducing image noise and artifacts.

Deep learning reconstruction allows low-dose imaging while maintaining image quality: comparison of deep learning reconstruction and hybrid iterative reconstruction in contrast-enhanced abdominal CT

We aimed to compare the radiation dose and image quality of a low-dose abdominal computed tomography (CT) protocol reconstructed with deep learning reconstruction (DLR) with those of a routine-dose protocol reconstructed with hybrid-iterative reconstruction. This retrospective study enrolled 71 patients [61 men; average age, 71.9 years; mean body mass index (BMI), 24.3 kg/m2] who underwent both low-dose abdominal CT with DLR [advanced intelligent clear-IQ engine (AiCE)] and routine-dose abdominal CT with hybrid-iterative reconstruction [adaptive iterative dose reduction 3D (AIDR 3D)]. Radiation dose parameters included volume CT dose index (CTDIvol), effective dose (ED), and size-specific dose estimate (SSDE). Mean image noise and contrast-to-noise ratio (CNR) were calculated. Image noise was measured in the hepatic parenchyma and bilateral erector spinae muscles. Moreover, subjective assessment of perceived image quality and diagnostic acceptability was performed. The low-dose protocol helped reduce the CTDIvol by 44.3%, ED by 43.7%, and SSDE by 44.9%. Moreover, the noise was significantly lower and CNR significantly higher with the low-dose protocol than with the normal-dose protocol (P<0.001). In the subjective assessment of image quality, there was no significant difference between the protocols with regard to image noise. Overall, AiCE was superior to AIDR 3D in terms of diagnostic acceptability (P=0.001). The use of AiCE can reduce overall radiation dose by more than 40% without loss of image quality compared to routine-dose abdominal CT with AIDR 3D.

Artificial Intelligence (Enhanced Super-Resolution Generative Adversarial Network) for Calcium Deblooming in Coronary Computed Tomography Angiography: A Feasibility Study

Background: The presence of heavy calcification in the coronary artery always presents a challenge for coronary computed tomography angiography (CCTA) in assessing the degree of coronary stenosis due to blooming artifacts associated with calcified plaques. Our study purpose was to use an advanced artificial intelligence (enhanced super-resolution generative adversarial network [ESRGAN]) model to suppress the blooming artifact in CCTA and determine its effect on improving the diagnostic performance of CCTA in calcified plaques. Methods: A total of 184 calcified plaques from 50 patients who underwent both CCTA and invasive coronary angiography (ICA) were analysed with measurements of coronary lumen on the original CCTA, and three sets of ESRGAN-processed images including ESRGAN-high-resolution (ESRGAN-HR), ESRGAN-average and ESRGAN-median with ICA as the reference method for determining sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Results: ESRGAN-processed images improved the specificity and PPV at all three coronary arteries (LAD-left anterior descending, LCx-left circumflex and RCA-right coronary artery) compared to original CCTA with ESRGAN-median resulting in the highest values being 41.0% (95% confidence interval [CI]: 30%, 52.7%) and 26.9% (95% CI: 22.9%, 31.4%) at LAD; 41.7% (95% CI: 22.1%, 63.4%) and 36.4% (95% CI: 28.9%, 44.5%) at LCx; 55% (95% CI: 38.5%, 70.7%) and 47.1% (95% CI: 38.7%, 55.6%) at RCA; while corresponding values for original CCTA were 21.8% (95% CI: 13.2%, 32.6%) and 22.8% (95% CI: 20.8%, 24.9%); 12.5% (95% CI: 2.6%, 32.4%) and 27.6% (95% CI: 24.7%, 30.7%); 17.5% (95% CI: 7.3%, 32.8%) and 32.7% (95% CI: 29.6%, 35.9%) at LAD, LCx and RCA, respectively. There was no significant effect on sensitivity and NPV between the original CCTA and ESRGAN-processed images at all three coronary arteries. The area under the receiver operating characteristic curve was the highest with ESRGAN-median images at the RCA level with values being 0.76 (95% CI: 0.64, 0.89), 0.81 (95% CI: 0.69, 0.93), 0.82 (95% CI: 0.71, 0.94) and 0.86 (95% CI: 0.76, 0.96) corresponding to original CCTA and ESRGAN-HR, average and median images, respectively. Conclusions: This feasibility study shows the potential value of ESRGAN-processed images in improving the diagnostic value of CCTA for patients with calcified plaques.

Artificial intelligence in functional imaging of the lung

Artificial intelligence (AI) is transforming the way we perform advanced imaging. From high-resolution image reconstruction to predicting functional response from clinically acquired data, AI is promising to revolutionize clinical evaluation of lung performance, pushing the boundary in pulmonary functional imaging for patients suffering from respiratory conditions. In this review, we overview the current developments and expound on some of the encouraging new frontiers. We focus on the recent advances in machine learning and deep learning that enable reconstructing images, quantitating, and predicting functional responses of the lung. Finally, we shed light on the potential opportunities and challenges ahead in adopting AI for functional lung imaging in clinical settings.

Effect of a new deep learning image reconstruction algorithm for abdominal computed tomography imaging on image quality and dose reduction compared with two iterative reconstruction algorithms: a phantom study

Background

New reconstruction algorithms based on deep learning have been developed to correct the image texture changes related to the use of iterative reconstruction algorithms. The purpose of this study was to evaluate the impact of a new deep learning image reconstruction [Advanced intelligent Clear-IQ Engine (AiCE)] algorithm on image-quality and dose reduction compared to a hybrid iterative reconstruction (AIDR 3D) algorithm and a model-based iterative reconstruction (FIRST) algorithm.

Methods

Acquisitions were carried out using the ACR 464 phantom (and its body ring) at six dose levels (volume computed tomography dose index 15/10/7.5/5/2.5/1 mGy). Raw data were reconstructed using three levels (Mild/Standard/Strong) of AIDR 3D, of FIRST and AiCE. Noise-power-spectrum (NPS) and task-based transfer function (TTF) were computed. Detectability index was computed to model the detection of a small calcification (1.5-mm diameter and 500 HU) and a large mass in the liver (25-mm diameter and 120 HU).

Results

NPS peaks were lower with AiCE than with AIDR 3D (-41%±6% for all levels) or FIRST (-15%±6% for Strong level and -41%±11% for both other levels). The average NPS spatial frequency was lower with AICE than AIDR 3D (-9%±2% using Mild and -3%±2% using Strong) but higher than FIRST for Standard (6%±3%) and Strong (25%±3%) levels. For acrylic insert, values of TTF at 50 percent were higher with AICE than AIDR 3D and FIRST, except for Mild level (-6%±6% and -13%±3%, respectively). For bone insert, values of TTF at 50 percent were higher with AICE than AIDR 3D but lower than FIRST (-19%±14%). For both simulated lesions, detectability index values were higher with AICE than AIDR 3D and FIRST (except for Strong level and for the small feature; -21%±14%). Using the Standard level, dose could be reduced by -79% for the small calcification and -57% for the large mass using AICE compared to AIDR 3D.

Conclusions

The new deep learning image reconstruction algorithm AiCE generates an image-quality with less noise and/or less smudged/smooth images and a higher detectability than the AIDR 3D or FIRST algorithms. The outcomes of our phantom study suggest a good potential of dose reduction using AiCE but it should be confirmed clinically in patients.

Clinical evaluation of a phantom-based deep convolutional neural network for whole-body-low-dose and ultra-low-dose CT skeletal surveys

OBJECTIVE

This study evaluated the clinical utility of a phantom-based convolutional neural network noise reduction framework for whole-body-low-dose CT skeletal surveys.

MATERIALS AND METHODS

The CT exams of ten patients with multiple myeloma were retrospectively analyzed. Exams were acquired with routine whole-body-low-dose CT protocol and projection noise insertion was used to simulate 25% dose exams. Images were reconstructed with either iterative reconstruction or filtered back projection with convolutional neural network post-processing. Diagnostic quality and structure visualization were blindly rated (subjective scale ranging from 0 [poor] to 100 [excellent]) by three musculoskeletal radiologists for iterative reconstruction and convolutional neural network images at routine whole-body-low-dose and 25% dose CT.

RESULTS

For the diagnostic quality rating, the convolutional neural network outscored iterative reconstruction at routine whole-body-low-dose CT (convolutional neural network: 95 ± 5, iterative reconstruction: 85 ± 8) and at the 25% dose level (convolutional neural network: 79 ± 10, iterative reconstruction: 22 ± 13). Convolutional neural network applied to 25% dose was rated inferior to iterative reconstruction applied to routine dose. Similar trends were observed in rating experiments focusing on structure visualization.

CONCLUSION

Results indicate that the phantom-based convolutional neural network noise reduction framework can improve visualization of critical structures within CT skeletal surveys. At matched dose level, the convolutional neural network outscored iterative reconstruction for all conditions studied. The image quality improvement of convolutional neural network applied to 25% dose indicates a potential for dose reduction; however, the 75% dose reduction condition studied is not currently recommended for clinical implementation.

Performance of a deep learning-based CT image denoising method: Generalizability over dose, reconstruction kernel and slice thickness

PURPOSE

Deep learning (DL) is rapidly finding applications in low-dose CT image denoising. While having the potential to improve image quality (IQ) over the filtered back projection method (FBP) and produce images quickly, performance generalizability of the data-driven DL methods is not fully understood yet. The main purpose of this work is to investigate the performance generalizability of a low-dose CT image denoising neural network in data acquired under different scan conditions, particularly relating to these three parameters: reconstruction kernel, slice thickness and dose (noise) level. A secondary goal is to identify any underlying data property associated with the CT scan settings that might help predict the generalizability of the denoising network.

METHODS

We select the residual encoder-decoder convolutional neural network (REDCNN) as an example of a low-dose CT image denoising technique in this work. To study how the network generalizes on the three imaging parameters, we grouped the CT volumes in the Low-Dose Grand Challenge (LDGC) data into three pairs of training datasets according to their imaging parameters, changing only one parameter in each pair. We trained REDCNN with them to obtain six denoising models. We test each denoising model on datasets of matching and mismatching parameters with respect to its training sets regarding dose, reconstruction kernel and slice thickness, respectively, to evaluate the denoising performance changes. Denoising performances are evaluated on patient scans, simulated phantom scans and physical phantom scans using IQ metrics including mean squared error (MSE), contrast-dependent modulation transfer function (MTF), pixel-level noise power spectrum (pNPS) and low-contrast lesion detectability (LCD).

RESULTS

REDCNN had larger MSE when the testing data was different from the training data in reconstruction kernel, but no significant MSE difference when varying slice thickness in the testing data. REDCNN trained with quarter-dose data had slightly worse MSE in denoising higher-dose images than that trained with mixed-dose data (17-80%). The MTF tests showed that REDCNN trained with the two reconstruction kernels and slice thicknesses yielded images of similar image resolution. However, REDCNN trained with mixed-dose data preserved the low-contrast resolution better compared to REDCNN trained with quarter-dose data. In the pNPS test, it was found that REDCNN trained with smooth-kernel data could not remove high-frequency noise in the test data of sharp kernel, possibly because the lack of high-frequency noise in the smooth-kernel data limited the ability of the trained model in removing high-frequency noise. Finally, in the LCD test, REDCNN improved the lesion detectability over the original FBP images regardless of whether the training and testing data had matching reconstruction kernels.

CONCLUSIONS

REDCNN is observed to be poorly generalizable between reconstruction kernels, more robust in denoising data of arbitrary dose levels when trained with mixed-dose data, and not highly sensitive to slice thickness. It is known that reconstruction kernel affects the in-plane pNPS shape of a CT image whereas slice thickness and dose level do not, so it is possible that the generalizability performance of this CT image denoising network highly correlates to the pNPS similarity between the testing and training data. This article is protected by copyright. All rights reserved.

Performance evaluation of using shorter contrast injection and 70 kVp with deep learning image reconstruction for reduced contrast medium dose and radiation dose in coronary CT angiography for children: a pilot study

Background

Iterative reconstruction algorithms are often used to reduce image noise in low-dose coronary computed tomography angiography (CCTA) but encounter limitations. The newly introduced deep learning image reconstruction (DLIR) algorithm may provide new opportunities. We assessed the image quality and diagnostic performance of DLIR in low radiation dose and contrast medium dose CCTA of pediatric patients with 70 kVp and a shortened injection protocol.

Methods

This was a prospective study. A total of 27 consecutive arrhythmic pediatric patients were enrolled in the study group and underwent CCTA using a prospective ECG-triggered single-beat protocol: tube voltage 70 kVp, automatic tube current modulation for a noise index (NI) of 22, and contrast dose of 0.4-0.6 mL/kg. Images were reconstructed with DLIR. They were compared with 27 matched patients in the control group scanned with 80 kVp, a lower NI setting (NI =19), and a higher contrast dose (0.8-1.2 mL/kg). The images in the control group were reconstructed using the adaptive statistical iterative reconstruction (ASIR-V) algorithm. The image contrast, image quality, and diagnostic confidence were assessed by 2 experienced radiologists using a 5-point scale (1: nondiagnostic and 5: excellent). The CT value and standard deviation of the aorta and perivascular tissue were measured, and the contrast-to-noise ratio (CNR) for the aorta was calculated. The contrast medium and radiation doses were compared.

Results

The study and control groups had similar image contrast scores (4.75±0.57 vs. 4.78±0.42), image quality scores (3.67±0.47 vs. 3.44±0.51), and diagnostic confidence (4.74±0.44 vs. 4.74±0.45) (all P>0.05). There was an adequate enhancement in the aorta (614.74±127.73 vs. 705.89±111.20 HU) and similar CNR (20.34±4.64 vs. 20.99±4.14) in both groups. The image noise of the study group was lower in the aorta (30.61±3.88 vs. 34.77±3.49) and similar in perivascular tissue (27.66±6.24 vs. 27.55±3.33) compared with the control group. The study group reduced the total contrast medium dose by 53% to 15.07±3.68 mL and radiation dose by 36% to 0.57±0.31 mSv.

Conclusions

The DLIR algorithm in CCTA for children using 70 kVp tube voltage with a shortened contrast medium injection protocol maintains image quality and diagnostic confidence while significantly reducing contrast medium dose and radiation dose compared with the use of the conventional CCTA protocol.

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.

White Nail as a Static Physical Finding: Revitalization of Physical Examination

Physical examinations are critical for diagnosis and should be differentiated into static and dynamic categories. One of the static findings is white nail, such as Terry’s and Lindsay’s nails. Here, we report the cases of two older patients with acute diseases who had nail changes that aided evaluation of their clinical course. Two elderly women who presented with acute conditions were initially thought to have normal serum albumin levels. They were found to have white nail with differences in nail involvement of the first finger, which subsequently revealed their hypoalbuminemia. The clinical courses were different following the distribution of nail whitening. Our findings show that examination of a white nail could indicate the previous clinical status more clearly than laboratory data. It can be useful for evaluating preclinical conditions in patients with acute diseases. Further evaluation is needed to establish the relationship between clinical outcomes and the presence of white nail in acute conditions among older patients.

[Noise Reduction Effect of Deep-learning-based Image Reconstruction Algorithms in Thin-section Chest CT]

OBJECTIVE

To evaluate the noise reduction effect of deep learning-based reconstruction algorithms in thin-section chest CT images by analyzing images reconstructed with filtered back projection (FBP), adaptive statistical iterative reconstruction (ASIR), and deep learning image reconstruction (DLIR) algorithms.

METHODS

The chest CT scan raw data of 47 patients were included in this study. Images of 0.625 mm were reconstructed using six reconstruction methods, including FBP, ASIR hybrid reconstruction (ASIR50%, ASIR70%), and deep learning low, medium and high modes (DL-L, DL-M, and DL-H). After the regions of interest were outlined in the aorta, skeletal muscle and lung tissue of each group of images, the CT values, SD values and signal-to-noise ratio (SNR) of the regions of interest were measured, and two radiologists evaluated the image quality.

RESULTS

CT values, SD values and SNR of the images obtained by the six reconstruction methods showed statistically significant difference ( P<0.001). There were statistically significant differences in the image quality scores of the six reconstruction methods ( P<0.001). Images reconstruced with DL-H have the lowest noise and the highest overall quality score.

CONCLUSION

The model based on deep learning can effectively reduce the noise of thin-section chest CT images and improve the image quality. Among the three deep-learning models, DL-H showed the best noise reduction effect.