Possibility of Deep Learning in Medical Imaging Focusing Improvement of Computed Tomography Image Quality

Improved vascular depiction and image quality through deep learning reconstruction of CT hepatic arteriography during transcatheter arterial chemoembolization

PURPOSE

To evaluate the effect of deep learning reconstruction (DLR) on vascular depiction, tumor enhancement, and image quality of computed tomography hepatic arteriography (CTHA) images acquired during transcatheter arterial chemoembolization (TACE).

METHODS

Institutional review board approval was obtained. Twenty-seven patients (18 men and 9 women, mean age, 75.7 years) who underwent CTHA immediately before TACE were enrolled. All images were reconstructed using three reconstruction algorithms: hybrid-iterative reconstruction (hybrid-IR), DLR with mild strength (DLR-M), and DLR with strong strength (DLR-S). Vascular depiction, tumor enhancement, feeder visualization, and image quality of CTHA were quantitatively and qualitatively assessed by two radiologists and compared between the three reconstruction algorithms.

RESULTS

The mean signal-to-noise ratios (SNR) of sub-segmental arteries and sub-sub-segmental arteries, and the contrast-to-noise ratio (CNR) of tumors, were significantly higher on DLR-S than on DLR-M and hybrid-IR (P < 0.001). The mean qualitative score for sharpness of sub-segmental and sub-sub-segmental arteries was significantly better on DLR-S than on DLR-M and hybrid-IR (P < 0.001). There was no significant difference in the feeder artery detection rate of automated feeder artery detection software among three reconstruction algorithms (P = 0.102). The contrast, continuity, and confidence level of feeder artery detection was significantly better on DLR-S than on DLR-M (P = 0.013, 0.005, and 0.001) and hybrid-IR (P < 0.001, P = 0.002, and P < 0.001). The weighted kappa values between two readers for qualitative scores of feeder artery visualization were 0.807-0.874. The mean qualitative scores for sharpness, granulation, and diagnostic acceptability of CTHA were better on DLR-S than on DLR-M and hybrid-IR (P < 0.001).

CONCLUSIONS

DLR significantly improved the SNR of small hepatic arteries, the CNR of tumor, and feeder artery visualization on CTHA images. DLR-S seems to be better suited to routine CTHA in TACE than does hybrid-IR.

Super-resolution deep learning image reconstruction: image quality and myocardial homogeneity in coronary computed tomography angiography

BACKGROUND

The recently introduced super-resolution (SR) deep learning image reconstruction (DLR) is potentially effective in reducing noise level and enhancing the spatial resolution. We aimed to investigate whether SR-DLR has advantages in the overall image quality and intensity homogeneity on coronary computed tomography (CT) angiography with four different approaches: filtered-back projection (FBP), hybrid iterative reconstruction (IR), DLR, and SR-DLR.

METHODS

Sixty-three patients (mean age, 61 ± 11 years; range, 18-81 years; 40 men) who had undergone coronary CT angiography between June and October 2022 were retrospectively included. Image noise, signal to noise ratio, and contrast to noise ratio were quantified in both proximal and distal segments of the major coronary arteries. The left ventricle myocardium contrast homogeneity was analyzed. Two independent reviewers scored overall image quality, image noise, image sharpness, and myocardial homogeneity.

RESULTS

Image noise in Hounsfield units (HU) was significantly lower (P < 0.001) for the SR-DLR (11.2 ± 2.0 HU) compared to those associated with other image reconstruction methods including FBP (30.5 ± 10.5 HU), hybrid IR (20.0 ± 5.4 HU), and DLR (14.2 ± 2.5 HU) in both proximal and distal segments. SR-DLR significantly improved signal to noise ratio and contrast to noise ratio in both the proximal and distal segments of the major coronary arteries. No significant difference was observed in the myocardial CT attenuation with SR-DLR among different segments of the left ventricle myocardium (P = 0.345). Conversely, FBP and hybrid IR resulted in inhomogeneous myocardial CT attenuation (P < 0.001). Two reviewers graded subjective image quality with SR-DLR higher than other image reconstruction techniques (P < 0.001).

CONCLUSIONS

SR-DLR improved image quality, demonstrated clearer delineation of distal segments of coronary arteries, and was seemingly accurate for quantifying CT attenuation in the myocardium.

Enhancing image quality in computed tomography angiography follow-ups after endovascular aneurysm repair: a comparative study of reconstruction techniques

BACKGROUND

The image quality of computed tomography angiography (CTA) images following endovascular aneurysm repair (EVAR) is not satisfactory, since artifacts resulting from metallic implants obstruct the clear depiction of stent and isolation lumens, and also adjacent soft tissues. However, current techniques to reduce these artifacts still need further advancements due to higher radiation doses, longer processing times and so on. Thus, the aim of this study is to assess the impact of utilizing Single-Energy Metal Artifact Reduction (SEMAR) alongside a novel deep learning image reconstruction technique, known as the Advanced Intelligent Clear-IQ Engine (AiCE), on image quality of CTA follow-ups conducted after EVAR.

MATERIALS

This retrospective study included 47 patients (mean age ± standard deviation: 68.6 ± 7.8 years; 37 males) who underwent CTA examinations following EVAR. Images were reconstructed using four different methods: hybrid iterative reconstruction (HIR), AiCE, the combination of HIR and SEMAR (HIR + SEMAR), and the combination of AiCE and SEMAR (AiCE + SEMAR). Two radiologists, blinded to the reconstruction techniques, independently evaluated the images. Quantitative assessments included measurements of image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the longest length of artifacts (AL), and artifact index (AI). These parameters were subsequently compared across different reconstruction methods.

RESULTS

The subjective results indicated that AiCE + SEMAR performed the best in terms of image quality. The mean image noise intensity was significantly lower in the AiCE + SEMAR group (25.35 ± 6.51 HU) than in the HIR (47.77 ± 8.76 HU), AiCE (42.93 ± 10.61 HU), and HIR + SEMAR (30.34 ± 4.87 HU) groups (p < 0.001). Additionally, AiCE + SEMAR exhibited the highest SNRs and CNRs, as well as the lowest AIs and ALs. Importantly, endoleaks and thrombi were most clearly visualized using AiCE + SEMAR.

CONCLUSIONS

In comparison to other reconstruction methods, the combination of AiCE + SEMAR demonstrates superior image quality, thereby enhancing the detection capabilities and diagnostic confidence of potential complications such as early minor endleaks and thrombi following EVAR. This improvement in image quality could lead to more accurate diagnoses and better patient outcomes.

Super resolution deep learning reconstruction for coronary CT angiography: A structured phantom study

Purpose

Super-resolution deep-learning-based reconstruction: SR-DLR is a newly developed and clinically available deep-learning-based image reconstruction method that can improve the spatial resolution of CT images. The image quality of the output from non-linear image reconstructions, such as DLR, is known to vary depending on the structure of the object being scanned, and a simple phantom cannot explicitly evaluate the clinical performance of SR-DLR. This study aims to accurately investigate the quality of the images reconstructed by SR-DLR by utilizing a structured phantom that simulates the human anatomy in coronary CT angiography.

Methods

The structural phantom had ribs and vertebrae made of plaster, a left ventricle filled with dilute contrast medium, a coronary artery with simulated stenosis, and an implanted stent graft. By scanning the structured phantom, we evaluated noise and spatial resolution on the images reconstructed with SR-DLR and conventional reconstructions.

Results

The spatial resolution of SR-DLR was higher than conventional reconstructions; the 10 % modulation transfer function of hybrid IR (HIR), DLR, and SR-DLR were 0.792-, 0.976-, and 1.379 cycle/mm, respectively. At the same time, image noise was lowest (HIR: 21.1-, DLR: 19.0-, and SR-DLR: 13.1 HU). SR-DLR could accurately assess coronary artery stenosis and the lumen of the implanted stent graft.

Conclusions

SR-DLR can obtain CT images with high spatial resolution and lower noise without special CT equipments, and will help diagnose coronary artery disease in CCTA and other CT examinations that require high spatial resolution.

Deep-learning reconstruction with low-contrast media and low-kilovoltage peak for CT of the liver

AIM

To compare images using reduced CM, low-kVp scanning and DLR reconstruction with conventional images (no CM reduction, normal tube voltage, reconstructed with HBIR. To compare images using reduced contrast media (CM), low kilovoltage peak (kVp) scanning and deep-learning reconstruction (DLR) with conventional image quality (no CM reduction, normal tube voltage, reconstructed with hybrid-type iterative reconstruction method [HBIR protocol]).

MATERIALS AND METHODS

A retrospective analysis was performed on 70 patients with liver disease and three-phase dynamic imaging using computed tomography (CT) from April 2020 to March 2022 at Oita University Hospital. Of these cases, 39 were reconstructed using the DLR protocol at a tube voltage of 80 kVp and CM of 300 mg iodine/kg while 31 were imaged at a tube voltage of 120 kVp with CM of 600 mg iodine/kg and were reconstructed by the usual HBIR protocol. Images from the DLR and HBIR protocols were analysed and compared based on the contrast-to-noise ratio (CNR), signal-to-noise ratio (SNR), figure-of-merit (FOM), and visual assessment. The CT dose index (CTDI)vol and size-specific dose estimates (SSDE) were compared with respect to radiation dose.

RESULTS

The DLR protocol was superior, with significant differences in CNR, SNR, and FOM except hepatic parenchyma in the arterial phase. For visual assessment, the DLR protocol had better values for vascular visualisation for the portal vein, image noise, and contrast enhancement of the hepatic parenchyma. Regarding comparison of the radiation dose, the DLR protocol was superior for all values of CTDIvol and SSDE, with significant differences (p<0.01; max. 52%).

CONCLUSION

Protocols using DLR with reduced CM and low kVp have better image quality and lower radiation dose compared to protocols using conventional HBIR.

Diagnostic CT of colorectal cancer with artificial intelligence iterative reconstruction: A clinical evaluation

OBJECTIVES

To investigate the clinical value of a novel deep-learning based CT reconstruction algorithm, artificial intelligence iterative reconstruction (AIIR), in diagnostic imaging of colorectal cancer (CRC).

METHODS

This study retrospectively enrolled 217 patients with pathologically confirmed CRC. CT images were reconstructed with the AIIR algorithm and compared with those originally obtained with hybrid iterative reconstruction (HIR). Objective image quality was evaluated in terms of the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). Subjective image quality was graded on the conspicuity of tumor margin and enhancement pattern as well as the certainty in diagnosing organ invasion and regional lymphadenopathy. In patients with surgical pathology (n = 116), the performance of diagnosing visceral peritoneum invasion was characterized using receiver operating characteristic (ROC) analysis. Changes of diagnostic thinking in diagnosing hepatic metastases were assessed through lesion classification confidence.

RESULTS

The SNRs and CNRs on AIIR images were significantly higher than those on HIR images (all p < 0.001). The AIIR was scored higher for all subjective metrics (all p < 0.001) except for the certainty of diagnosing regional lymphadenopathy (p = 0.467). In diagnosing visceral peritoneum invasion, higher area under curve (AUC) of the ROC was found for AIIR than HIR (0.87 vs 0.77, p = 0.001). In assessing hepatic metastases, AIIR was found capable of correcting the misdiagnosis and improving the diagnostic confidence provided by HIR (p = 0.01).

CONCLUSIONS

Compared to HIR, AIIR offers better image quality, improves the diagnostic performance regarding CRC, and thus has the potential for application in routine abdominal CT.

AFEX-Net: Adaptive feature extraction convolutional neural network for classifying computerized tomography images

Purpose

Deep convolutional neural networks are favored methods that are widely used in medical image processing due to their demonstrated performance in this area. Recently, the emergence of new lung diseases, such as COVID-19, and the possibility of early detection of their symptoms from chest computerized tomography images has attracted many researchers to classify diseases by training deep convolutional neural networks on lung computerized tomography images. The trained networks are expected to distinguish between different lung indications in various diseases, especially at the early stages. The purpose of this study is to introduce and assess an efficient deep convolutional neural network, called AFEX-Net, that can classify different lung diseases from chest computerized tomography images.

Methods

We designed a lightweight convolutional neural network called AFEX-Net with adaptive feature extraction layers, adaptive pooling layers, and adaptive activation functions. We trained and tested AFEX-Net on a dataset of more than 10,000 chest computerized tomography slices from different lung diseases (CC dataset), using an effective pre-processing method to remove bias. We also applied AFEX-Net to the public COVID-CTset dataset to assess its generalizability. The study was mainly conducted based on data collected over approximately six months during the pandemic outbreak in Afzalipour Hospital, Iran, which is the largest hospital in Southeast Iran.

Results

AFEX-Net achieved high accuracy and fast training on both datasets, outperforming several state-of-the-art convolutional neural networks. It has an accuracy of 99.7 % and 98.8 % on the CC and COVID-CTset datasets, respectively, with a learning speed that is 3 times faster compared to similar methods due to its lightweight structure. AFEX-Net was able to extract distinguishing features and classify chest computerized tomography images, especially at the early stages of lung diseases.

Conclusion

The AFEX-Net is a high-performing convolutional neural network for classifying lung diseases from chest CT images. It is efficient, adaptable, and compatible with input data, making it a reliable tool for early detection and diagnosis of lung diseases.

Image Quality Improvement of Low-dose Abdominal CT using Deep Learning Image Reconstruction Compared with the Second Generation Iterative Reconstruction

BACKGROUND

Whether deep learning-based CT reconstruction could improve lesion conspicuity on abdominal CT when the radiation dose is reduced is controversial.

OBJECTIVES

To determine whether DLIR can provide better image quality and reduce radiation dose in contrast-enhanced abdominal CT compared with the second generation of adaptive statistical iterative reconstruction (ASiR-V).

AIMS

This study aims to determine whether deep-learning image reconstruction (DLIR) can improve image quality.

METHOD

In this retrospective study, a total of 102 patients were included, who underwent abdominal CT using a DLIR-equipped 256-row scanner and routine CT of the same protocol on the same vendor's 64-row scanner within four months. The CT data from the 256-row scanner were reconstructed into ASiR-V with three blending levels (AV30, AV60, and AV100), and DLIR images with three strength levels (DLIR-L, DLIR-M, and DLIR-H). The routine CT data were reconstructed into AV30, AV60, and AV100. The contrast-to-noise ratio (CNR) of the liver, overall image quality, subjective noise, lesion conspicuity, and plasticity in the portal venous phase (PVP) of ASiR-V from both scanners and DLIR were compared.

RESULTS

The mean effective radiation dose of PVP of the 256-row scanner was significantly lower than that of the routine CT (6.3±2.0 mSv vs. 2.4±0.6 mSv; p< 0.001). The mean CNR, image quality, subjective noise, and lesion conspicuity of ASiR-V images of the 256-row scanner were significantly lower than those of ASiR-V images at the same blending factor of routine CT, but significantly improved with DLIR algorithms. DLIR-H showed higher CNR, better image quality, and subjective noise than AV30 from routine CT, whereas plasticity was significantly better for AV30.

CONCLUSION

DLIR can be used for improving image quality and reducing radiation dose in abdominal CT, compared with ASIR-V.

Deep learning-based reconstruction can improve the image quality of low radiation dose head CT

OBJECTIVES

To evaluate the image quality of deep learning-based reconstruction (DLR), model-based (MBIR), and hybrid iterative reconstruction (HIR) algorithms for lower-dose (LD) unenhanced head CT and compare it with those of standard-dose (STD) HIR images.

METHODS

This retrospective study included 114 patients who underwent unenhanced head CT using the STD (n = 57) or LD (n = 57) protocol on a 320-row CT. STD images were reconstructed with HIR; LD images were reconstructed with HIR (LD-HIR), MBIR (LD-MBIR), and DLR (LD-DLR). The image noise, gray and white matter (GM-WM) contrast, and contrast-to-noise ratio (CNR) at the basal ganglia and posterior fossa levels were quantified. The noise magnitude, noise texture, GM-WM contrast, image sharpness, streak artifact, and subjective acceptability were independently scored by three radiologists (1 = worst, 5 = best). The lesion conspicuity of LD-HIR, LD-MBIR, and LD-DLR was ranked through side-by-side assessments (1 = worst, 3 = best). Reconstruction times of three algorithms were measured.

RESULTS

The effective dose of LD was 25% lower than that of STD. Lower image noise, higher GM-WM contrast, and higher CNR were observed in LD-DLR and LD-MBIR than those in STD (all, p ≤ 0.035). Compared with STD, the noise texture, image sharpness, and subjective acceptability were inferior for LD-MBIR and superior for LD-DLR (all, p < 0.001). The lesion conspicuity of LD-DLR (2.9 ± 0.2) was higher than that of HIR (1.2 ± 0.3) and MBIR (1.8 ± 0.4) (all, p < 0.001). Reconstruction times of HIR, MBIR, and DLR were 11 ± 1, 319 ± 17, and 24 ± 1 s, respectively.

CONCLUSION

DLR can enhance the image quality of head CT while preserving low radiation dose level and short reconstruction time.

KEY POINTS

• For unenhanced head CT, DLR reduced the image noise and improved the GM-WM contrast and lesion delineation without sacrificing the natural noise texture and image sharpness relative to HIR. • The subjective and objective image quality of DLR was better than that of HIR even at 25% reduced dose without considerably increasing the image reconstruction times (24 s vs. 11 s). • Despite the strong noise reduction and improved GM-WM contrast performance, MBIR degraded the noise texture, sharpness, and subjective acceptance with prolonged reconstruction times relative to HIR, potentially hampering its feasibility.

Low dose of contrast agent and low radiation liver computed tomography with deep-learning-based contrast boosting model in participants at high-risk for hepatocellular carcinoma: prospective, randomized, double-blind study

OBJECTIVE

To investigate the image quality and lesion conspicuity of a deep-learning-based contrast-boosting (DL-CB) algorithm on double-low-dose (DLD) CT of simultaneous reduction of radiation and contrast doses in participants at high-risk for hepatocellular carcinoma (HCC).

METHODS

Participants were recruited and underwent four-phase dynamic CT (NCT04722120). They were randomly assigned to either standard-dose (SD) or DLD protocol. All CT images were initially reconstructed using iterative reconstruction, and the images of the DLD protocol were further processed using the DL-CB algorithm (DLD-DL). The primary endpoint was the contrast-to-noise ratio (CNR), the secondary endpoint was qualitative image quality (noise, hepatic lesion, and vessel conspicuity), and the tertiary endpoint was lesion detection rate. The t-test or repeated measures analysis of variance was used for analysis.

RESULTS

Sixty-eight participants with 57 focal liver lesions were enrolled (20 with HCC and 37 with benign findings). The DLD protocol had a 19.8% lower radiation dose (DLP, 855.1 ± 254.8 mGy·cm vs. 713.3 ± 94.6 mGy·cm, p = .003) and 27% lower contrast dose (106.9 ± 15.0 mL vs. 77.9 ± 9.4 mL, p < .001) than the SD protocol. The comparative analysis demonstrated that CNR (p < .001) and portal vein conspicuity (p = .002) were significantly higher in the DLD-DL than in the SD protocol. There was no significant difference in lesion detection rate for all lesions (82.7% vs. 73.3%, p = .140) and HCCs (75.7% vs. 70.4%, p = .644) between the SD protocol and DLD-DL.

CONCLUSIONS

DL-CB on double-low-dose CT provided improved CNR of the aorta and portal vein without significant impairment of the detection rate of HCC compared to the standard-dose acquisition, even in participants at high risk for HCC.

KEY POINTS

• Deep-learning-based contrast-boosting algorithm on double-low-dose CT provided an improved contrast-to-noise ratio compared to standard-dose CT. • The detection rate of focal liver lesions was not significantly differed between standard-dose CT and a deep-learning-based contrast-boosting algorithm on double-low-dose CT. • Double-low-dose CT without a deep-learning algorithm presented lower CNR and worse image quality.

Deep Learning-Based Image Quality Improvement in Digital Positron Emission Tomography for Breast Cancer

We investigated whether ¹⁸F-fluorodeoxyglucose positron emission tomography (PET)/computed tomography images restored via deep learning (DL) improved image quality and affected axillary lymph node (ALN) metastasis diagnosis in patients with breast cancer. Using a five-point scale, two readers compared the image quality of DL-PET and conventional PET (cPET) in 53 consecutive patients from September 2020 to October 2021. Visually analyzed ipsilateral ALNs were rated on a three-point scale. The standard uptake values SUV_max and SUV_peak were calculated for breast cancer regions of interest. For "depiction of primary lesion", reader 2 scored DL-PET significantly higher than cPET. For "noise", "clarity of mammary gland", and "overall image quality", both readers scored DL-PET significantly higher than cPET. The SUV_max and SUV_peak for primary lesions and normal breasts were significantly higher in DL-PET than in cPET (p < 0.001). Considering the ALN metastasis scores 1 and 2 as negative and 3 as positive, the McNemar test revealed no significant difference between cPET and DL-PET scores for either reader (p = 0.250, 0.625). DL-PET improved visual image quality for breast cancer compared with cPET. SUV_max and SUV_peak were significantly higher in DL-PET than in cPET. DL-PET and cPET exhibited comparable diagnostic abilities for ALN metastasis.

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.

Convolutional Encoder-Decoder Networks for Volumetric Computed Tomography Surviews from Single- and Dual-View Topograms

Computed tomography (CT) is an extensively used imaging modality capable of generating detailed images of a patient's internal anatomy for diagnostic and interventional procedures. High-resolution volumes are created by measuring and combining information along many radiographic projection angles. In current medical practice, single and dual-view two-dimensional (2D) topograms are utilized for planning the proceeding diagnostic scans and for selecting favorable acquisition parameters, either manually or automatically, as well as for dose modulation calculations. In this study, we develop modified 2D to three-dimensional (3D) encoder-decoder neural network architectures to generate CT-like volumes from single and dual-view topograms. We validate the developed neural networks on synthesized topograms from publicly available thoracic CT datasets. Finally, we assess the viability of the proposed transformational encoder-decoder architecture on both common image similarity metrics and quantitative clinical use case metrics, a first for 2D-to-3D CT reconstruction research. According to our findings, both single-input and dual-input neural networks are able to provide accurate volumetric anatomical estimates. The proposed technology will allow for improved (i) planning of diagnostic CT acquisitions, (ii) input for various dose modulation techniques, and (iii) recommendations for acquisition parameters and/or automatic parameter selection. It may also provide for an accurate attenuation correction map for positron emission tomography (PET) with only a small fraction of the radiation dose utilized.

Understanding CT imaging findings based on the underlying pathophysiology in patients with small bowel ischemia

Because acute small bowel ischemia has a high mortality rate, it requires rapid intervention to avoid unfavorable outcomes. Computed tomography (CT) examination is important for the diagnosis of bowel ischemia. Acute small bowel ischemia can be the result of small bowel obstruction or mesenteric ischemia, including mesenteric arterial occlusion, mesenteric venous thrombosis, and non-occlusive mesenteric ischemia. The clinical significance of each CT finding is unique and depends on the underlying pathophysiology. This review describes the definition and mechanism(s) of bowel ischemia, reviews CT findings suggesting bowel ischemia, details factors involved in the development of small bowel ischemia, and presents CT findings with respect to the different factors based on the underlying pathophysiology. Such knowledge is needed for accurate treatment decisions.

Application of deep learning reconstruction of ultra-low-dose abdominal CT in the diagnosis of renal calculi

BACKGROUND

Renal calculi are a common and recurrent urological disease and are usually detected by CT. In this study, we evaluated the diagnostic capability, image quality, and radiation dose of abdominal ultra-low-dose CT (ULDCT) with deep learning reconstruction (DLR) for detecting renal calculi.

METHODS

Sixty patients with suspected renal calculi were prospectively enrolled. Low-dose CT (LDCT) images were reconstructed with hybrid iterative reconstruction (LD-HIR) and was regarded as the standard for stone and lesion detection. ULDCT images were reconstructed with HIR (ULD-HIR) and DLR (ULD-DLR). We then compared stone detection rate, abdominal lesion detection rate, image quality and radiation dose between LDCT and ULDCT.

RESULTS

A total of 130 calculi were observed on LD-HIR images. Stone detection rates of ULD-HIR and ULD-DLR images were 93.1% (121/130) and 95.4% (124/130). A total of 129 lesions were detected on the LD-HIR images. The lesion detection rate on ULD-DLR images was 92.2%, with 10 cysts < 5 mm in diameter missed. The CT values of organs on ULD-DLR were similar to those on LD-HIR and lower than those on ULD-HIR. Signal-to-noise ratio was highest and noise lowest on ULD-DLR. The subjective image quality of ULD-DLR was similar to that of LD-HIR and better than that of ULD-HIR. The effective radiation dose of ULDCT (0.64 ± 0.17 mSv) was 77% lower than that of LDCT (2.75 ± 0.50 mSv).

CONCLUSION

ULDCT combined with DLR could significantly reduce radiation dose while maintaining suitable image quality and stone detection rate in the diagnosis of renal calculi.

Deep Learning-Based Reconstruction vs. Iterative Reconstruction for Quality of Low-Dose Head-and-Neck CT Angiography with Different Tube-Voltage Protocols in Emergency-Department Patients

Objective: To compare the image quality of computed tomography angiography of the supra-aortic arteries (CTSA) at different tube voltages in low doses settings with deep learning-based image reconstruction (DLR) vs. hybrid iterative reconstruction (H-IR). Methods: We retrospectively reviewed 102 patients who underwent CTSA systematically reconstructed with both DLR and H-IR. We assessed the image quality both quantitatively and qualitatively at 11 arterial segmental levels and 3 regional levels. Radiation-dose parameters were recorded and the effective dose was calculated. Eighty-six patients were eligible for analysis Of these patients, 27 were imaged with 120 kVp, 30 with 100 kVp, and 29 with 80 kVp. Results: The effective dose in 120 kVp, 100 kVp and 80 kVp was 1.5 ± 0.4 mSv, 1.1 ± 0.3 mSv and 0.68 ± 0.1 mSv, respectively (p < 0.01). Comparing 80 kVp + DLR vs. 120 and 100 kVp + H-IR CT scans, the mean overall arterial attenuation was about 64% and 34% higher (625.9 ± 118.5 HU vs. 382.3 ± 98.6 HU and 468 ± 118.5 HU; p < 0.01) without a significant difference in terms of image noise (17.7 ± 4.9 HU vs. 17.5 ± 5.2; p = 0.7 and 18.1 ± 5.4; p = 0.3) and signal-to-ratio increased by 59% and 33%, respectively (37.9 ± 12.3 vs. 23.8 ± 9.7 and 28.4 ± 12.5). This protocol also provided superior image quality in terms of qualitative parameters, compared to standard-kVp protocols with H-IR. Highest subjective image-quality grades for vascular segments close to the aorta were obtained with the 100 kVp + DLR protocol. Conclusions: DLR significantly reduced image noise and improved the overall image quality of CTSA with both low and standard tube voltages and at all vascular segments. CT that was acquired with 80 kVp and reconstructed with DLR yielded better overall image quality compared to higher kVp values with H-IR, while reducing the radiation dose by half, but it has limitations for arteries that are close to the aortic arch.

Strain Analysis in Patients at High-Risk for COPD Using Four-Dimensional Dynamic-Ventilation CT

Purpose

To quantitatively identify abnormal lung motion in chronic obstructive pulmonary disease (COPD) using strain analysis, and further clarify the potential differences of deformation in COPD with different severity of airflow limitation.

Materials and Methods

Totally, 53 patients at high-risk for COPD were enrolled in this study. All CT examinations were performed on a 320-row MDCT scanner, and strain measurement based on dynamic-ventilation CT data was performed with a computational fluid dynamics analysis software (Micro Vec V3.6.2). The strain-related parameters derived from the whole expiration phase (PSmax-all, PSmean-all, Speedmax-all ), the first 2s of expiration phase (PSmax2s, PSmean2s, Speedmax2s ) were divided respectively by the changes in lung volume to adjust for the degree of expiration. Spearman rank correlation analysis was used to evaluate associations between the strain-related parameters and various spirometric parameters. Comparisons of the strain-related parameters between COPD and non-COPD patients, between GOLD I (mild airflow restriction) and GOLD II-IV (moderate to severe airflow restriction) were made using the Mann-Whitney U-test. Receiver-operating characteristic (ROC) analysis was performed to evaluate the diagnostic performance of the strain-related parameters for COPD. P <0.05 was considered statistically significant.

Results

Strain-related parameters demonstrated positive correlations with spirometric parameters (ρ=0.275~0.687, P<0.05), suggesting that heterogeneity in lung motion was related to abnormal spirometric results. Strain-related parameters can quantitatively distinguish COPD from non-COPD patients with moderate diagnostic significance with the AUC values ranged from 0.821 to 0.894. Furthermore, parameters of the whole expiration phase (PSmax-all, Speedmax-all) demonstrated significant differences (P=0.005; P=0.04) between COPD patients with mild and moderate to severe airflow limitation.

Conclusion

Strain-related parameters derived from dynamic-ventilation CT data covering the whole lung associated with lung function changes in COPD, reflecting the severity of airflow limitation in some degree, even though its utility in severe COPD patients remains to be investigated.

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.

Application of deep learning image reconstruction in low-dose chest CT scan

OBJECTIVE

Deep learning image reconstruction (DLIR) is a new reconstruction method for maintaining image quality at reduced radiation dose. The purpose of this study was to compare image quality of reduced-dose DLIR images with the standard-dose adaptive statistical iterative reconstruction (ASIR-V) images in chest CT.

METHODS

Our prospective study included 48 adult patients (30 women and 18 men, mean age ±SD, 49.8 ± 14.3 years) who underwent both the standard-dose CT (SDCT) and low-dose CT (LDCT) on a GE Revolution CT scanner. All patients gave written informed consent. All scans were reconstructed with ASIR-V40%. Additionally, LDCT scans were reconstructed with DLIR with high-setting (DLIR-H) and medium-setting (DLIR-M). Image noise and contrast-noise-ratio (CNR) of thoracic aorta with different reconstruction modes were measured and compared.

RESULTS

LDCT reduced radiation dose by 96% compared with SDCT (CTDIvol: 0.54mGy vs 12.46mGy). In LDCT, DLIR significantly reduced image noise compared with the state-of-the-art ASIR-V40% with DLIR-H provided the lowest image noise and highest image quality score. In addition, the image noise, CNR of aorta and overall image quality of the low-dose DLIR-H images did not have significant difference compared with the SDCT ASIR-V40% images (all p > 0.05).

CONCLUSION

DLIR significantly reduces image noise in LDCT chest scans and provides similar image quality as the SDCT ASIR-V images at 4% of the radiation dose.

ADVANCES IN KNOWLEDGE

DLIR uses high-quality FBP data to train deep neural networks to learn how to distinguish between signal and noise, and effectively suppresses noise without affecting anatomical and pathological structures. It opens a new era of CT image reconstruction. DLIR significantly reduces image noise and improves image quality compared with ASIR-V40% under same radiation dose condition. DLIR-H achieves similar image quality at 4% radiation dose as ASIR-V40% at standard-dose level in non-contrast chest CT.

Deep learning versus iterative image reconstruction algorithm for head CT in trauma

PURPOSE

To compare the image quality between a deep learning-based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT.

METHODS

Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the different reconstruction algorithms. Inter-reader agreement was assessed by weighted kappa.

RESULTS

DLIR-M and DLIR-H demonstrated lower image noise (p < 0.001 for all pairwise comparisons), higher SNR of up to 82.9% (p < 0.001), and higher CNR of up to 53.3% (p < 0.001) compared to ASiR-V. DLIR-H outperformed other DLIR strengths (p ranging from < 0.001 to 0.016). DLIR-M outperformed DLIR-L (p < 0.001) and ASiR-V (p < 0.001). The distribution of reader scores for DLIR-M and DLIR-H shifted towards higher scores compared to DLIR-L and ASiR-V. There was a tendency towards higher scores with increasing DLIR strengths. There were fewer non-diagnostic CT series for DLIR-M and DLIR-H compared to ASiR-V and DLIR-L. No images were graded as non-diagnostic for DLIR-H regarding intracranial hemorrhage. The inter-reader agreement was fair-good between the second most and the less experienced reader, poor-moderate between the most and the less experienced reader, and poor-fair between the most and the second most experienced reader.

CONCLUSION

The image quality of trauma head CT series reconstructed with DLIR outperformed those reconstructed with ASiR-V. In particular, DLIR-M and DLIR-H demonstrated significantly improved image quality and fewer non-diagnostic images. The improvement in qualitative image quality was greater for the second most and the less experienced readers compared to the most experienced reader.

Artificial intelligence in musculoskeletal imaging: a perspective on value propositions, clinical use, and obstacles

Artificial intelligence and deep learning (DL) offer musculoskeletal radiology exciting possibilities in multiple areas, including image reconstruction and transformation, tissue segmentation, workflow support, and disease detection. Novel DL-based image reconstruction algorithms correcting aliasing artifacts, signal loss, and noise amplification with previously unobtainable effectiveness are prime examples of how DL algorithms deliver promised value propositions in musculoskeletal radiology. The speed of DL-based tissue segmentation promises great efficiency gains that may permit the inclusion of tissue compositional-based information routinely into radiology reports. Similarly, DL algorithms give rise to a myriad of opportunities for workflow improvements, including intelligent and adaptive hanging protocols, speech recognition, report generation, scheduling, precertification, and billing. The value propositions of disease-detecting DL algorithms include reduced error rates and increased productivity. However, more studies using authentic clinical workflow settings are necessary to fully understand the value of DL algorithms for disease detection in clinical practice. Successful workflow integration and management of multiple algorithms are critical for translating the value propositions of DL algorithms into clinical practice but represent a major roadblock for which solutions are critically needed. While there is no consensus about the most sustainable business model, radiology departments will need to carefully weigh the benefits and disadvantages of each commercially available DL algorithm. Although more studies are needed to understand the value and impact of DL algorithms on clinical practice, DL technology will likely play an important role in the future of musculoskeletal imaging.

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.

Deep Learning Image Processing Enables 40% Faster Spinal MR Scans Which Match or Exceed Quality of Standard of Care : A Prospective Multicenter Multireader Study

OBJECTIVE

This prospective multicenter multireader study evaluated the performance of 40% scan-time reduced spinal magnetic resonance imaging (MRI) reconstructed with deep learning (DL).

METHODS

A total of 61 patients underwent standard of care (SOC) and accelerated (FAST) spine MRI. DL was used to enhance the accelerated set (FAST-DL). Three neuroradiologists were presented with paired side-by-side datasets (666 series). Datasets were blinded and randomized in sequence and left-right display order. Image features were preference rated. Structural similarity index (SSIM) and per pixel L1 was assessed for the image sets pre and post DL-enhancement as a quantitative assessment of image integrity impact.

RESULTS

FAST-DL was qualitatively better than SOC for perceived signal-to-noise ratio (SNR) and artifacts and equivalent for other features. Quantitative SSIM was high, supporting the absence of image corruption by DL processing.

CONCLUSION

DL enables 40% spine MRI scan time reduction while maintaining diagnostic integrity and image quality with perceived benefits in SNR and artifact reduction, suggesting potential for clinical practice utility.

Deep learning-based Hounsfield unit value measurement method for bolus tracking images in cerebral computed tomography angiography

BACKGROUND

Patient movement during bolus tracking (BT) impairs the accuracy of Hounsfield unit (HU) measurements. This study assesses the accuracy of measuring HU values in the internal carotid artery (ICA) using an original deep learning (DL)-based method as compared with using the conventional region of interest (ROI) setting method.

METHOD

A total of 722 BT images of 127 patients who underwent cerebral computed tomography angiography were selected retrospectively and divided into groups for training data, validation data, and test data. To segment the ICA using our proposed method, DL was performed using a convolutional neural network. The HU values in the ICA were obtained using our DL-based method and the ROI setting method. The ROI setting was performed with and without correcting for patient body movement (corrected ROI and settled ROI). We compared the proposed DL-based method with settled ROI to evaluate HU value differences from the corrected ROI, based on whether or not patients experienced involuntary movement during BT image acquisition.

RESULTS

Differences in HU values from the corrected ROI in the settled ROI and the proposed method were 23.8 ± 12.7 HU and 9.0 ± 6.4 HU in patients with body movement and 1.1 ± 1.6 HU and 3.9 ± 4.7 HU in patients without body movement, respectively. There were significant differences in both comparisons (P < 0.01).

CONCLUSION

DL-based method can improve the accuracy of HU value measurements for ICA in BT images with patient involuntary movement.

Advanced CT techniques for assessing hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the sixth-most common cancer in the world, and hepatic dynamic CT studies are routinely performed for its evaluation. Ongoing studies are examining advanced imaging techniques that may yield better findings than are obtained with conventional hepatic dynamic CT scanning. Dual-energy CT-, perfusion CT-, and artificial intelligence-based methods can be used for the precise characterization of liver tumors, the quantification of treatment responses, and for predicting the overall survival rate of patients. In this review, the advantages and disadvantages of conventional hepatic dynamic CT imaging are reviewed and the general principles of dual-energy- and perfusion CT, and the clinical applications and limitations of these technologies are discussed with respect to HCC. Finally, we address the utility of artificial intelligence-based methods for diagnosing HCC.

Additive manufacturing pertaining to bone: Hopes, reality and future challenges for clinical applications

For the past 20 years, the democratization of additive manufacturing (AM) technologies has made many of us dream of: low cost, waste-free, and on-demand production of functional parts; fully customized tools; designs limited by imagination only, etc. As every patient is unique, the potential of AM for the medical field is thought to be considerable: AM would allow the division of dedicated patient-specific healthcare solutions entirely adapted to the patients' clinical needs. Pertinently, this review offers an extensive overview of bone-related clinical applications of AM and ongoing research trends, from 3D anatomical models for patient and student education to ephemeral structures supporting and promoting bone regeneration. Today, AM has undoubtably improved patient care and should facilitate many more improvements in the near future. However, despite extensive research, AM-based strategies for bone regeneration remain the only bone-related field without compelling clinical proof of concept to date. This may be due to a lack of understanding of the biological mechanisms guiding and promoting bone formation and due to the traditional top-down strategies devised to solve clinical issues. Indeed, the integrated holistic approach recommended for the design of regenerative systems (i.e., fixation systems and scaffolds) has remained at the conceptual state. Challenged by these issues, a slower but incremental research dynamic has occurred for the last few years, and recent progress suggests notable improvement in the years to come, with in view the development of safe, robust and standardized patient-specific clinical solutions for the regeneration of large bone defects.

A novel fast kilovoltage switching dual-energy CT with deep learning: Accuracy of CT number on virtual monochromatic imaging and iodine quantification

PURPOSE

A novel fast kilovoltage switching dual-energy CT with deep learning [Deep learning based-spectral CT (DL-Spectral CT)], which generates a complete sinogram for each kilovolt using deep learning views that complement the measured views at each energy, was commercialized in 2020. The purpose of this study was to evaluate the accuracy of CT numbers in virtual monochromatic images (VMIs) and iodine quantifications at various radiation doses using DL-Spectral CT.

MATERIALS AND METHODS

Two multi-energy phantoms (large and small) using several rods representing different materials (iodine, calcium, blood, and adipose) were scanned by DL-Spectral CT at varying radiation doses. Images were reconstructed using three reconstruction parameters (body, lung, bone). The absolute percentage errors (APEs) for CT numbers on VMIs at 50, 70, and 100 keV and iodine quantification were compared among different radiation dose protocols.

RESULTS

The APEs of the CT numbers on VMIs were <15% in both the large and small phantoms, except at the minimum dose in the large phantom. There were no significant differences among radiation dose protocols in computed tomography dose index volumes of 12.3 mGy or larger. The accuracy of iodine quantification provided by the body parameter was significantly better than those obtained with the lung and bone parameters. Increasing the radiation dose did not always improve the accuracy of iodine quantification, regardless of the reconstruction parameter and phantom size.

CONCLUSION

The accuracy of iodine quantification and CT numbers on VMIs in DL-Spectral CT was not affected by the radiation dose, except for an extremely low radiation dose for body size.

Diagnostic value of deep learning reconstruction for radiation dose reduction at abdominal ultra-high-resolution CT

OBJECTIVES

We evaluated lower dose (LD) hepatic dynamic ultra-high-resolution computed tomography (U-HRCT) images reconstructed with deep learning reconstruction (DLR), hybrid iterative reconstruction (hybrid-IR), or model-based IR (MBIR) in comparison with standard-dose (SD) U-HRCT images reconstructed with hybrid-IR as the reference standard to identify the method that allowed for the greatest radiation dose reduction while preserving the diagnostic value.

METHODS

Evaluated were 72 patients who had undergone hepatic dynamic U-HRCT; 36 were scanned with the standard radiation dose (SD group) and 36 with 70% of the SD (lower dose [LD] group). Hepatic arterial and equilibrium phase (HAP, EP) images were reconstructed with hybrid-IR in the SD group, and with hybrid-IR, MBIR, and DLR in the LD group. One radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise. The overall image quality was assessed by 3 other radiologists; they used a 5-point confidence scale ranging from 1 (unacceptable) to 5 (excellent). Superiority and equivalence with prespecified margins were assessed.

RESULTS

With respect to the image noise, in the HAP and EP, LD DLR and LD MBIR images were superior to SD hybrid-IR images; LD hybrid-IR images were neither superior nor equivalent to SD hybrid-IR images. With respect to the quality scores, only LD DLR images were superior to SD hybrid-IR images.

CONCLUSIONS

DLR preserved the quality of abdominal U-HRCT images even when scanned with a reduced radiation dose.

KEY POINTS

• Lower dose DLR images were superior to the standard-dose hybrid-IR images quantitatively and qualitatively at abdominal U-HRCT. • Neither hybrid-IR nor MBIR may allow for a radiation dose reduction at abdominal U-HRCT without compromising the image quality. • Because DLR allows for a reduction in the radiation dose and maintains the image quality even at the thinnest slice section, DLR should be applied to abdominal U-HRCT scans.

Technical development in cardiac CT: current standards and future improvements-a narrative review

Non-invasive depiction of coronary arteries has been a great challenge for imaging specialists since the introduction of computed tomography (CT). Technological development together with improvements in spatial, temporal, and contrast resolution, progressively allowed implementation of the current clinical role of the CT assessment of coronary arteries. Several technological evolutions including hardware and software solutions of CT scanners have been developed to improve spatial and temporal resolution. The main challenges of cardiac computed tomography (CCT) are currently plaque characterization, functional assessment of stenosis and radiation dose reduction. In this review, we will discuss current standards and future improvements in CCT.

Difference in Local Lung Movement During Tidal Breathing Between COPD Patients and Asthma Patients Assessed by Four-dimensional Dynamic-ventilation CT Scan

Background

The validity of four-dimensional dynamic-ventilation CT scan for distinguishing COPD from asthma has not been established.

Purpose

To assess whether four-dimensional dynamic-ventilation CT scan can aid in the diagnosis of COPD by comparing local lung movement during tidal breathing between COPD and asthma.

Patients and Methods

Thirty-three COPD patients (30 males and three females; median age 74; range 44-89 years) and 11 asthma patients (five males and six females; median age 55; range: 32-75 years) underwent whole-lung dynamic-ventilation CT scan. CT data were reconstructed, one respiratory cycle to 10 phases, and in addtion we reconstructed threefold new phase data sets. We then analyzed local lung movement during tidal breathing using unpaired t-tests and chi-squared tests.

Results

The local lung movement in COPD patients was significantly smaller than in asthma patients, especially in the ventral part of the lung. This was so even in patients who had mild emphysema (Goddard score <8).

Conclusion

Quantitative evaluation using four-dimensional dynamic-ventilation CT scan demonstrated that local lung movement during tidal breathing, particularly in the ventral lung, was smaller in COPD than in asthma patients, which may help distinguish COPD from asthma.

Deep learning reconstruction of equilibrium phase CT images in obese patients

PURPOSE

To compare abdominal equilibrium phase (EP) CT images of obese and non-obese patients to identify the reconstruction method that preserves the diagnostic value of images obtained in obese patients.

METHODS

We compared EP images of 50 obese patients whose body mass index (BMI) exceeded 25 (group 1) with EP images of 50 non-obese patients (BMI < 25, group 2). Group 1 images were subjected to deep learning reconstruction (DLR), hybrid iterative reconstruction (hybrid-IR), and model-based IR (MBIR), group 2 images to hybrid-IR; group 2 hybrid-IR images served as the reference standard. A radiologist recorded the standard deviation of attenuation in the paraspinal muscle as the image noise. The overall image quality was assessed by 3 other radiologists; they used a confidence scale ranging from 1 (unacceptable) to 5 (excellent). Non-inferiority and potential superiority were assessed.

RESULTS

With respect to the image noise, group 1 DLR- were superior to group 2 hybrid-IR images; group 1 hybrid-IR- and MBIR images were neither superior nor non-inferior to group 2 hybrid-IR images. The quality scores of only DLR images in group 1 were superior to hybrid-IR images of group 2 while the quality scores of group 1 hybrid-IR- and MBIR images were neither superior nor non-inferior to group 2 hybrid-IR images.

CONCLUSIONS

DLR preserved the quality of EP images obtained in obese patients.