Reduced-Dose Deep Learning Reconstruction for Abdominal CT of Liver Metastases

Advances in spatial resolution and radiation dose reduction using super-resolution deep learning-based reconstruction for abdominal computed tomography: A phantom study

RATIONALE AND OBJECTIVES

This study evaluated the performance of super-resolution deep learning-based reconstruction (SR-DLR) and compared with it that of hybrid iterative reconstruction (HIR) and normal-resolution DLR (NR-DLR) for enhancing image quality in computed tomography (CT) images across various field of view (FOV) sizes, radiation doses, and noise reduction strengths.

MATERIALS AND METHODS

A Catphan phantom equipped with an external body ring was used. CT images were reconstructed using filtered back-projection (FBP), HIR, NR-DLR, and SR-DLR across three noise reduction strengths: mild, standard, and strong. The noise power spectrum (NPS) was obtained from the FBP, HIR, NR-DLR, and SR-DLR images at various FOVs, radiation doses, and noise reduction strengths. The noise magnitude ratio (NMR) and central frequency ratio (CFR) were calculated from the HIR, NR-DLR, and SR-DLR images relative to the FBP images using NPS. The high-contrast value was obtained from the amplitude values of the peaks and valleys of profile curve and the task-based transfer function were also analyzed.

RESULTS

SR-DLR consistently demonstrated superior noise reduction capabilities, with NMR of 0.29-0.36 at reduced dose and 0.35-0.45 at standard dose, outperforming HIR and showing comparable efficiency to NR-DLR. The high-contrast values for SR-DLR were highest at mild and standard levels for both low and standard doses (0.610 and 0.726 at mild and 0.725 and 0.603 at standard levels). At the standard dose, the spatial resolution of SR-DLR was significantly improved, regardless of the noise reduction strength and FOV.

CONCLUSION

SR-DLR images achieved more substantial noise reduction than HIR and similar noise reduction as NR-DLR reconstructions while also improving spatial resolution.

Intraindividual Comparison of Image Quality Between Low-Dose and Ultra-Low-Dose Abdominal CT With Deep Learning Reconstruction and Standard-Dose Abdominal CT Using Dual-Split Scan

OBJECTIVE

The aim of this study was to intraindividually compare the conspicuity of focal liver lesions (FLLs) between low- and ultra-low-dose computed tomography (CT) with deep learning reconstruction (DLR) and standard-dose CT with model-based iterative reconstruction (MBIR) from a single CT using dual-split scan in patients with suspected liver metastasis via a noninferiority design.

MATERIALS AND METHODS

This prospective study enrolled participants who met the eligibility criteria at 2 tertiary hospitals in South Korea from June 2022 to January 2023. The criteria included (a) being aged between 20 and 85 years and (b) having suspected or known liver metastases. Dual-source CT scans were conducted, with the standard radiation dose divided in a 2:1 ratio between tubes A and B (67% and 33%, respectively). The voltage settings of 100/120 kVp were selected based on the participant's body mass index (<30 vs ≥30 kg/m2). For image reconstruction, MBIR was utilized for standard-dose (100%) images, whereas DLR was employed for both low-dose (67%) and ultra-low-dose (33%) images. Three radiologists independently evaluated FLL conspicuity, the probability of metastasis, and subjective image quality using a 5-point Likert scale, in addition to quantitative signal-to-noise and contrast-to-noise ratios. The noninferiority margins were set at -0.5 for conspicuity and -0.1 for detection.

RESULTS

One hundred thirty-three participants (male = 58, mean body mass index = 23.0 ± 3.4 kg/m2) were included in the analysis. The low- and ultra-low- dose had a lower radiation dose than the standard-dose (median CT dose index volume: 3.75, 1.87 vs 5.62 mGy, respectively, in the arterial phase; 3.89, 1.95 vs 5.84 in the portal venous phase, P < 0.001 for all). Median FLL conspicuity was lower in the low- and ultra-low-dose scans compared with the standard-dose (3.0 [interquartile range, IQR: 2.0, 4.0], 3.0 [IQR: 1.0, 4.0] vs 3.0 [IQR: 2.0, 4.0] in the arterial phase; 4.0 [IQR: 1.0, 5.0], 3.0 [IQR: 1.0, 4.0] vs 4.0 [IQR: 2.0, 5.0] in the portal venous phases), yet within the noninferiority margin (P < 0.001 for all). FLL detection was also lower but remained within the margin (lesion detection rate: 0.772 [95% confidence interval, CI: 0.727, 0.812], 0.754 [0.708, 0.795], respectively) compared with the standard-dose (0.810 [95% CI: 0.770, 0.844]). Sensitivity for liver metastasis differed between the standard- (80.6% [95% CI: 76.0, 84.5]), low-, and ultra-low-doses (75.7% [95% CI: 70.2, 80.5], 73.7 [95% CI: 68.3, 78.5], respectively, P < 0.001 for both), whereas specificity was similar (P > 0.05).

CONCLUSIONS

Low- and ultra-low-dose CT with DLR showed noninferior FLL conspicuity and detection compared with standard-dose CT with MBIR. Caution is needed due to a potential decrease in sensitivity for metastasis (clinicaltrials.gov/ NCT05324046).

Characterization of hepatocellular carcinoma with CT with deep learning reconstruction compared with iterative reconstruction and 3-Tesla MRI

OBJECTIVES

This study compared the characteristics of lesions suspicious for hepatocellular carcinoma (HCC) and their LI-RADS classifications in adaptive statistical iterative reconstruction (ASIR) and deep learning reconstruction (DLR) to those of MR images, along with radiologist confidence.

MATERIALS AND METHODS

This prospective single-center trial included patients who underwent four-phase liver CT and multiphasic contrast-enhanced MRI within 7 days from February to August 2023. The lesion characteristics, LI-RADS classifications and confidence scores according to two radiologists on the ASIR, DLR and MRI techniques were compared. If the patient had at least one lesion, he was included in the HCC group, otherwise in the non-HCC group. MRI being the technique with the best sensitivity, concordance of lesions characteristics and LI-RADS classifications were calculated by weighted kappa between the ASIR and MRI and between the DLR and MRI. The confidence scores are expressed as the means and standard deviations.

RESULTS

Eighty-nine patients were enrolled, 52 in the HCC group (67 years ± 9 [mean ± SD], 46 men) and 37 in the non-HCC group (68 years ± 9, 33 men). The concordance coefficient between the LI-RADS classification by ASIR and MRI was 0.64 [0.52; 0.76], showing good agreement, that by DLR and MRI was 0.83 [0.73; 0.92], showing excellent agreement. The diagnostic confidence in ASIR was 3.31 ± 0.95 (mean ± SD) and 3.0 ± 1.11, that in the DLR was 3.9 ± 0.88 and 4.11 ± 0.75, that in the MRI was 4.46 ± 0.80 and 4.57 ± 0.80.

CONCLUSION

DLR provided excellent LI-RADS classification concordance with MRI, whereas ASIR provided good concordance. The radiologists' confidence was greater in the DLR than in the ASIR but remained highest in the MR group.

KEY POINTS

Question Does the use of deep learning reconstructions (DLR) improve LI-RADS classification of suspicious hepatocellular carcinoma lesions compared to adaptive statistical iterative reconstructions (ASIR)? Findings DLR demonstrated superior concordance of LI-RADS classification with MRI compared to ASIR. It also provided greater diagnostic confidence than ASIR. Clinical relevance The use of DLR enhances radiologists' ability to visualize and characterize lesions suspected of being HCC, as well as their LI-RADS classification. Moreover, it also boosts their confidence in interpreting these images.

Reduced-dose deep learning iterative reconstruction for abdominal computed tomography with low tube voltage and tube current

BACKGROUND

The low tube-voltage technique (e.g., 80 kV) can efficiently reduce the radiation dose and increase the contrast enhancement of vascular and parenchymal structures in abdominal CT. However, a high tube current is always required in this setting and limits the dose reduction potential. This study investigated the feasibility of a deep learning iterative reconstruction algorithm (Deep IR) in reducing the radiation dose while improving the image quality for abdominal computed tomography (CT) with low tube voltage and current.

METHODS

Sixty patients (male/female, 36/24; Age, 57.72 ± 10.19 years) undergoing the abdominal portal venous phase CT were randomly divided into groups A (100 kV, automatic exposure control [AEC] with reference tube-current of 213 mAs) and B (80 kV, AEC with reference of 130 mAs). Images were reconstructed via hybrid iterative reconstruction (HIR) and Deep IR (levels 1-5). The mean CT and standard deviation (SD) values of four regions of interest (ROI), i.e. liver, spleen, main portal vein and erector spinae at the porta hepatis level in each image serial were measured, and the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated. The image quality was subjectively scored by two radiologists using a 5-point criterion.

RESULTS

A significant reduction in the radiation dose of 69.94% (5.09 ± 0.91 mSv vs. 1.53 ± 0.37 mSv) was detected in Group B compared with Group A. After application of the Deep IR, there was no significant change in the CT value, but the SD gradually increased. Group B had higher CT values than group A, and the portal vein CT values significantly differed between the groups (P < 0.003). The SNR and CNR in Group B with Deep IR at levels 1-5 were greater than those in Group A and significantly differed when HIR and Deep IR were applied at levels 1-3 of HIR and Deep IR (P < 0.003). The subjective scores (distortion, clarity of the portal vein, visibility of small structures and overall image quality) with Deep IR at levels 4-5 in Group B were significantly higher than those in group A with HIR (P < 0.003).

CONCLUSION

Deep IR algorithm can meet the clinical requirements and reduce the radiation dose by 69.94% in portal venous phase abdominal CT with a low tube voltage of 80 kV and a low tube current. Deep IR at levels 4-5 can significantly improve the image quality of the abdominal parenchymal organs and the clarity of the portal vein.

Deep learning based ultra-low dose fan-beam computed tomography image enhancement algorithm: Feasibility study in image quality for radiotherapy

OBJECTIVE

We investigated the feasibility of deep learning-based ultra-low dose kV-fan-beam computed tomography (kV-FBCT) image enhancement algorithm for clinical application in abdominal and pelvic tumor radiotherapy.

METHODS

A total of 76 patients of abdominal and pelvic tumors were prospectively selected. The Catphan504 was acquired with the same conditions as the standard phantom test set. We used a CycleGAN-based model for image enhancement. Normal dose CT (NDCT), ultra-low dose CT (LDCT) and deep learning enhanced CT (DLR) were evaluated by subjective and objective analyses in terms of imaging quality, HU accuracy, and image signal-to-noise ratio (SNR).

RESULTS

The image noise of DLR was significantly reduced, and the contrast-to-noise ratio (CNR) was significantly improved compared to the LDCT. The most significant improvement was the acrylic which represented soft tissue in CNR from 1.89 to 3.37, improving by 76%, nearly approaching the NDCT, and in low-density resolution from 7.64 to 12.6, improving by 64%. The spatial frequencies of MTF10 and MTF50 in DLR were 4.28 and 2.35 cycles/mm in DLR, respectively, which are higher than LDCT 3.87 and 2.12 cycles/mm, and even slightly higher than NDCT 4.15 and 2.28 cycles/mm. The accuracy and stability of HU values of DLR were similar to NDCT. The image quality evaluation of the two doctors agreed well with DLR and NDCT. A two-by-two comparison between groups showed that the differences in image scores of LDCT compared with NDCT and DLR were all statistically significant (p < 0.05), and the subjective scores of DLR were close to NDCT.

CONCLUSION

The image quality of DLR was close to NDCT with reduced radiation dose, which can fully meet the needs of conventional image-guided adaptive radiotherapy (ART) and achieve the quality requirements of clinical radiotherapy. The proposed method provided a technical basis for LDCT-guided ART.

Existence, uniqueness, and efficiency of numerically unbiased attenuation pathlength estimators for photon counting detectors at low count rates

BACKGROUND

The first step in computed tomography (CT) reconstruction is to estimate attenuation pathlength. Usually, this is done with a logarithm transformation, which is the direct solution to the Beer-Lambert Law. At low signals, however, the logarithm estimator is biased. Bias arises both from the curvature of the logarithm and from the possibility of detecting zero counts, so a data substitution strategy may be employed to avoid the singularity of the logarithm. Recent progress has been made by Li et al. [IEEE Trans Med Img 42:6, 2023] to modify the logarithm estimator to eliminate curvature bias, but the optimal strategy for mitigating bias from the singularity remains unknown.

PURPOSE

The purpose of this study was to use numerical techniques to construct unbiased attenuation pathlength estimators that are alternatives to the logarithm estimator, and to study the uniqueness and optimality of possible solutions, assuming a photon counting detector.

METHODS

Formally, an attenuation pathlength estimator is a mapping from integer detector counts to real pathlength values. We constrain our focus to only the small signal inputs that are problematic for the logarithm estimator, which we define as inputs of <100 counts, and we consider estimators that use only a single input and that are not informed by adjacent measurements (e.g., adaptive smoothing). The set of all possible pathlength estimators can then be represented as points in a 100-dimensional vector space. Within this vector space, we use optimization to select the estimator that (1) minimizes mean squared error and (2) is unbiased. We define "unbiased" as satisfying the numerical condition that the maximum bias be less than 0.001 across a continuum of 1000 object thicknesses that span the desired operating range. Because the objective function is convex and the constraints are affine, optimization is tractable and guaranteed to converge to the global minimum. We further examine the nullspace of the constraint matrix to understand the uniqueness of possible solutions, and we compare the results to the Cramér-Rao bound of the variance.

RESULTS

We first show that an unbiased attenuation pathlength estimator does not exist if very low mean detector signals (equivalently, very thick objects) are permitted. It is necessary to select a minimum mean detector signal for which unbiased behavior is desired. If we select two counts, the optimal estimator is similar to Li's estimator. If we select one count, the optimal estimator becomes non-monotonic. The oscillations cause the unbiased estimator to be noise amplifying. The nullspace of the constraint matrix is high-dimensional, so that unbiased solutions are not unique. The Cramér-Rao bound of the variance matches well with the expectedI - 0.5 ${{I}^{ - 0.5}}$ scaling law and cannot be attained.

CONCLUSION

If arbitrarily thick objects are permitted, an unbiased attenuation pathlength estimator does not exist. If the maximum thickness is restricted, an unbiased estimator exists but is not unique. An optimal estimator can be selected that minimizes variance, but a bias-variance tradeoff exists where a larger domain of unbiased behavior requires increased variance.

State-of-the-Art Deep Learning CT Reconstruction Algorithms in Abdominal Imaging

The implementation of deep neural networks has spurred the creation of deep learning reconstruction (DLR) CT algorithms. DLR CT techniques encompass a spectrum of deep learning-based methodologies that operate during the different steps of the image creation, prior to or after the traditional image formation process (eg, filtered backprojection [FBP] or iterative reconstruction [IR]), or alternatively by fully replacing FBP or IR techniques. DLR algorithms effectively facilitate the reduction of image noise associated with low photon counts from reduced radiation dose protocols. DLR methods have emerged as an effective solution to ameliorate limitations observed with prior CT image reconstruction algorithms, including FBP and IR algorithms, which are not able to preserve image texture and diagnostic performance at low radiation dose levels. An additional advantage of DLR algorithms is their high reconstruction speed, hence targeting the ideal triad of features for a CT image reconstruction (ie, the ability to consistently provide diagnostic-quality images and achieve radiation dose imaging levels as low as reasonably possible, with high reconstruction speed). An accumulated body of evidence supports the clinical use of DLR algorithms in abdominal imaging across multiple CT imaging tasks. The authors explore the technical aspects of DLR CT algorithms and examine various approaches to image synthesis in DLR creation. The clinical applications of DLR algorithms are highlighted across various abdominal CT imaging domains, with emphasis on the supporting evidence for diverse clinical tasks. An overview of the current limitations of and outlook for DLR algorithms for CT is provided. ©RSNA, 2024.

[Deep Learning Reconstruction Algorithm Combined With Smart Metal Artifact Reduction Technique Improves Image Quality of Upper Abdominal CT in Critically Ill Patients]

Objective

To evaluate the effect of deep learning reconstruction algorithm combined with smart metal artifact reduction (DLMAR) on the quality of abdominal CT images in critically ill patients who are unable to raise their arms and require electrocardiographic (ECG) monitoring.

Methods

A total of 102 patients were retrospectively enrolled. All subjects were critically ill patients who were unable to raise their arms and required ECG monitoring. Images were reconstructed using 6 algorithms, including filtered back projection (FBP), iterative reconstruction (IR), deep learning (DL), FBP combined with smart metal artifact reduction (FBPMAR), adaptive statistical iterative reconstruction-V combined with smart metal artifact reduction (IRMAR), and DLMAR. A quantitative analysis of CT values, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) was conducted in regions without metal artifacts and regions with metal artifacts in the liver, as well as the tissues, including those from the liver, spleen, pancreas, and aorta, between the two arms. Qualitative analysis of electrode metal artifacts, the visualization of the structures between the two arms, and image noise was performed with a 5-point scoring system (1=worst and 5=best).

Results

In the regions of the liver with metal artifacts, there was a significant difference between the CT values of the DLMAR group ([98.5±9.8] Hounsfield units [HU]) and those of the FBP group ([73.7±5.6] HU), the IR group ([75.3±7.5] HU), and the DL group ([66.3±11.4] HU) (P<0.01). There was no significant difference between the CT values of the DLMAR group and those of the FBPMAR group ([99.8±4.8] HU) and the IRMAR group ([99.6±3.4] HU) (P>0.05). The noise of the DLMAR group was found to be significantly lower than that of the other groups (P<0.01). Furthermore, the SNR and CNR of the DLMAR group were also found to be higher than those of the other groups (P<0.01). In the tissue region between the two arms, the differences in CT values among the six groups were not statistically significant (P>0.05). The noise of the DLMAR group was lower than those of the other groups (P<0.01), and the SNR and CNR of the DLMAR group were higher than those of the other groups (P<0.01). In terms of the removal of metal artifacts, the scores of the FBPMAR, IRMAR, and DLMAR groups (4.27±0.32, 4.44±0.34, and 4.61±0.28, respectively) were higher than those of the FBP, IR, and DL groups (1.36±0.54, 1.32±0.45, and 1.24±0.46, respectively) (P<0.01). The DLMAR group also had a higher score of 4.62±0.37 in the visualization of structures between the two arms and 4.53±0.39 in the noise reduction of images, both of which were higher than those of the other groups (P<0.01).

Conclusion

DLMAR reduces artifacts, decreases noise, and improves the quality of abdominal CT imaging in critically ill patients who are unable to raise their arms and require ECG monitoring.

Conceptual review of outcome metrics and measures used in clinical evaluation of artificial intelligence in radiology

Artificial intelligence (AI) has numerous applications in radiology. Clinical research studies to evaluate the AI models are also diverse. Consequently, diverse outcome metrics and measures are employed in the clinical evaluation of AI, presenting a challenge for clinical radiologists. This review aims to provide conceptually intuitive explanations of the outcome metrics and measures that are most frequently used in clinical research, specifically tailored for clinicians. While we briefly discuss performance metrics for AI models in binary classification, detection, or segmentation tasks, our primary focus is on less frequently addressed topics in published literature. These include metrics and measures for evaluating multiclass classification; those for evaluating generative AI models, such as models used in image generation or modification and large language models; and outcome measures beyond performance metrics, including patient-centered outcome measures. Our explanations aim to guide clinicians in the appropriate use of these metrics and measures.

Low tube voltage and deep-learning reconstruction for reducing radiation and contrast medium doses in thin-slice abdominal CT: a prospective clinical trial

OBJECTIVES

To investigate the feasibility of low-radiation dose and low iodinated contrast medium (ICM) dose protocol combining low-tube voltage and deep-learning reconstruction (DLR) algorithm in thin-slice abdominal CT.

METHODS

This prospective study included 148 patients who underwent contrast-enhanced abdominal CT with either 120-kVp (600 mgL/kg, n = 74) or 80-kVp protocol (360 mgL/kg, n = 74). The 120-kVp images were reconstructed using hybrid iterative reconstruction (HIR) (120-kVp-HIR), while 80-kVp images were reconstructed using HIR (80-kVp-HIR) and DLR (80-kVp-DLR) with 0.5 mm thickness. Size-specific dose estimate (SSDE) and iodine dose were compared between protocols. Image noise, CT attenuation, and contrast-to-noise ratio (CNR) were quantified. Noise power spectrum (NPS) and edge rise slope (ERS) were used to evaluate noise texture and edge sharpness, respectively. The subjective image quality was rated on a 4-point scale.

RESULTS

SSDE and iodine doses of 80-kVp were 40.4% (8.1 ± 0.9 vs. 13.6 ± 2.7 mGy) and 36.3% (21.2 ± 3.9 vs. 33.3 ± 4.3 gL) lower, respectively, than those of 120-kVp (both, p < 0.001). CT attenuation of vessels and solid organs was higher in 80-kVp than in 120-kVp images (all, p < 0.001). Image noise of 80-kVp-HIR and 80-kVp-DLR was higher and lower, respectively than that of 120-kVp-HIR (both p < 0.001). The highest CNR and subjective scores were attained in 80-kVp-DLR (all, p < 0.001). There were no significant differences in average NPS frequency and ERS between 120-kVp-HIR and 80-kVp-DLR (p ≥ 0.38).

CONCLUSION

Compared with the 120-kVp-HIR protocol, the combined use of 80-kVp and DLR techniques yielded superior subjective and objective image quality with reduced radiation and ICM doses at thin-section abdominal CT.

CLINICAL RELEVANCE STATEMENT

Scanning at low-tube voltage (80-kVp) combined with the deep-learning reconstruction algorithm may enhance diagnostic efficiency and patient safety by improving image quality and reducing radiation and contrast doses of thin-slice abdominal CT.

KEY POINTS

Reducing radiation and iodine doses is desirable; however, contrast and noise degradation can be detrimental. The 80-kVp scan with the deep-learning reconstruction technique provided better images with lower radiation and contrast doses. This technique may be efficient for improving diagnostic confidence and patient safety in thin-slice abdominal CT.

Exploring the Low-Dose Limit for Focal Hepatic Lesion Detection with a Deep Learning-Based CT Reconstruction Algorithm: A Simulation Study on Patient Images

This study aims to investigate the maximum achievable dose reduction for applying a new deep learning-based reconstruction algorithm, namely the artificial intelligence iterative reconstruction (AIIR), in computed tomography (CT) for hepatic lesion detection. A total of 40 patients with 98 clinically confirmed hepatic lesions were retrospectively included. The mean volume CT dose index was 13.66 ± 1.73 mGy in routine-dose portal venous CT examinations, where the images were originally obtained with hybrid iterative reconstruction (HIR). Low-dose simulations were performed in projection domain for 40%-, 20%-, and 10%-dose levels, followed by reconstruction using both HIR and AIIR. Two radiologists were asked to detect hepatic lesion on each set of low-dose image in separate sessions. Qualitative metrics including lesion conspicuity, diagnostic confidence, and overall image quality were evaluated using a 5-point scale. The contrast-to-noise ratio (CNR) for lesion was also calculated for quantitative assessment. The lesion CNR on AIIR at reduced doses were significantly higher than that on routine-dose HIR (all p < 0.05). Lower qualitative image quality was observed as the radiation dose reduced, while there were no significant differences between 40%-dose AIIR and routine-dose HIR images. The lesion detection rate was 100%, 98% (96/98), and 73.5% (72/98) on 40%-, 20%-, and 10%-dose AIIR, respectively, whereas it was 98% (96/98), 73.5% (72/98), and 40% (39/98) on the corresponding low-dose HIR, respectively. AIIR outperformed HIR in simulated low-dose CT examinations of the liver. The use of AIIR allows up to 60% dose reduction for lesion detection while maintaining comparable image quality to routine-dose HIR.

Deep learning image reconstruction for low-kiloelectron volt virtual monoenergetic images in abdominal dual-energy CT: medium strength provides higher lesion conspicuity

BACKGROUND

The best settings of deep learning image reconstruction (DLIR) algorithm for abdominal low-kiloelectron volt (keV) virtual monoenergetic imaging (VMI) have not been determined.

PURPOSE

To determine the optimal settings of the DLIR algorithm for abdominal low-keV VMI.

MATERIAL AND METHODS

The portal-venous phase computed tomography (CT) scans of 109 participants with 152 lesions were reconstructed into four image series: VMI at 50 keV using adaptive statistical iterative reconstruction (Asir-V) at 50% blending (AV-50); and VMI at 40 keV using AV-50 and DLIR at medium (DLIR-M) and high strength (DLIR-H). The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of nine anatomical sites were calculated. Noise power spectrum (NPS) using homogenous region of liver, and edge rise slope (ERS) at five edges were measured. Five radiologists rated image quality and diagnostic acceptability, and evaluated the lesion conspicuity.

RESULTS

The SNR and CNR values, and noise and noise peak in NPS measurements, were significantly lower in DLIR images than AV-50 images in all anatomical sites (all P < 0.001). The ERS values were significantly higher in 40-keV images than 50-keV images at all edges (all P < 0.001). The differences of the peak and average spatial frequency among the four reconstruction algorithms were significant but relatively small. The 40-keV images were rated higher with DLIR-M than DLIR-H for diagnostic acceptance (P < 0.001) and lesion conspicuity (P = 0.010).

CONCLUSION

DLIR provides lower noise, higher sharpness, and more natural texture to allow 40 keV to be a new standard for routine VMI reconstruction for the abdomen and DLIR-M gains higher diagnostic acceptance and lesion conspicuity rating than DLIR-H.

A paradigm shift in oncology imaging: a prospective cross-sectional study to assess low-dose deep learning image reconstruction versus standard-dose iterative reconstruction for comprehensive lesion detection in dual-energy computed tomography

Background

Low-kiloelectron volt (keV) virtual monochromatic images (VMIs) from low-dose (LD) dual-energy computed tomography (DECT) can enhance lesion contrast but suffer from high image noise. Recently, a deep learning image reconstruction (DLIR) algorithm has been developed and shown significant potential in suppressing image noise and improving image quality. To date, the capacity of LD low-keV thoracic-abdominal-pelvic DECT with DLIR to detect various types of tumor lesions have not been assessed. Hence, this study aimed to evaluate the image quality and lesion detection capabilities of LD VMIs using DLIR with thoracic-abdominal-pelvic DECT versus standard-dose (SD) iterative reconstruction (IR) in oncology patients.

Methods

This prospective intraindividual study included 56 oncology patients who received a SD (13.86 mGy) and a consecutive LD (7.15 mGy) thoracic-abdominal-pelvic DECT from April 2022 to July 2023 at The First Affiliated hospital of Zhengzhou University. SD VMIs were reconstructed using IR at 50 keV (SD-IR50 keV), while LD VMIs were processed using DLIR at 50 keV (LD-DL50 keV) and 40 keV (LD-DL40 keV), respectively. Quantitative image parameters [computed tomography (CT) values, image noise, and contrast-to-noise ratios (CNRs)], qualitative metrics (image noise, vessel conspicuity, image contrast, artificial sensation, and overall image quality), and lesion CNRs and conspicuity were compared. The lesion detection rates in the SD-IR50 keV, LD-DL50 keV, and LD-DL40 keV VMIs were assessed according to lesion location (lung, liver, and lymph), type, and size. Repeated measures analysis of variance and the Friedman test were applied for comparing quantitative and qualitative measures, respectively. The Cochran Q test was used for comparing lesion detection rates.

Results

Compared to SD-IR50 keV VMIs, LD-DL50 keV VMIs showed similar CT values and image noise (P>0.05), similar (P>0.05) or higher(P<0.05) CNRs, similar (P>0.05) or superior (P<0.05) perceptual image quality, and similar (P>0.05) or higher (P<0.001) lesion CNR and conspicuity. LD-DL40 keV VMIs exhibited higher CT values (by 40.4-47.1%) and CNRs (by 21.8-39.8%) (P<0.001), equivalent image noise, similar (P>0.05) or superior (P<0.05) perceptual image quality except for artificial sensation, and similar (P>0.05) or higher (P<0.001) lesion CNRs (by 16.5-46.3%) and conspicuity. The VMIs of LD-DL50 keV and LD-DL40 keV were consistent with those of SD-IR50 keV in terms of lesion detection capability in pulmonary nodules [SD-IR50 keV vs. LD-DL50 keV vs. LD-DL40 keV: 88/88 (100.0%) vs. 88/88 (100.0%) vs. 88/88 (100.0%); P>0.99], for lymph nodes [125/126 (99.2%) vs. 123/126 (97.6%) vs. 124/126 (98.4%); P>0.05], and high-contrast liver lesions [12/12 (100.0%) vs. 12/12 (100.0%) vs. 12/12 (100.0%); P>0.05], but not for small liver lesions (≤0.5 cm) [63/65 (96.9%) vs. 43/65 (66.2%) vs. 51/65 (78.5%); P<0.05] or low-contrast liver lesions [198/200 (99.0%) vs. 174/200 (87.0%) vs. 183/200 (91.5%); P<0.05].

Conclusions

VMIs at 40 keV with DLIR enables a 50% decrease in the radiation dose while largely maintaining diagnostic capabilities for multidetection of pulmonary nodules, lymph nodes, and liver lesions in oncology patients.

Image quality and radiation doses in abdominal CT: A multicenter study

PURPOSE

To benchmark image quality and corresponding radiation doses for acute abdominal CT examination across different laboratories and CT manufacturers.

METHOD

An anthropomorphic phantom was scanned once with local abdominal CT protocols at 40 CT scanners, from four vendors, in thirty-three sites. Quantitative image quality was evaluated by CNR and SNR in the liver and kidney parenchyma. Qualitative image quality was assessed by visual grading analysis performed by three experienced radiologists using a five-point Likert scale to score thirteen image quality criteria. The CTDIvol was recorded for each scan. Pearson's correlation coefficient was calculated for the continuous variables, and the intraclass correlation coefficient was used to investigate interrater reliability between the radiologists.

RESULTS

CTDIvol ranged from 3.5 to 12 mGy (median 5.3 mGy, third quartile 6.7 mGy). SNR in liver parenchyma ranged from 4.4 to 14.4 (median 8.5), and CNR ranged from 2.7 to 11.2 (median 6.1). A weak correlation was found between CTDIvol and CNR (r = 0.270, p = 0.092). Variations in CNR across scanners at the same dose level CTDIvol were observed. No significant difference in CTDIvol or CNR was found based on scanner installation year. The oldest scanners had a 15 % higher median CTDIvol and a 12 % lower median CNR. The ICC showed acceptable agreement for all dose groups: low (ICC=0.889), medium (ICC=0.767), high (ICC=0.847), and in low (ICC=0.803) and medium (ICC=0.811) CNR groups.

CONCLUSION

There was large variation in radiation dose and image quality across the different CT scanners. Interestingly, the weak correlation between CTDIvol and CNR indicates that higher doses do not consistently improve CNR, indicating a need for systematic assessment and optimization of image quality and radiation doses for the abdominal CT examination.

Optimizing computed tomography image reconstruction for focal hepatic lesions: Deep learning image reconstruction vs iterative reconstruction

Background

Deep learning image reconstruction (DLIR) is a novel computed tomography (CT) reconstruction technique that minimizes image noise, enhances image quality, and enables radiation dose reduction. This study aims to compare the diagnostic performance of DLIR and iterative reconstruction (IR) in the evaluation of focal hepatic lesions.

Methods

We conducted a retrospective study of 216 focal hepatic lesions in 109 adult participants who underwent abdominal CT scanning at our institution. We used DLIR (low, medium, and high strength) and IR (0 %, 10 %, 20 %, and 30 %) techniques for image reconstruction. Four experienced abdominal radiologists independently evaluated focal hepatic lesions based on five qualitative aspects (lesion detectability, lesion border, diagnostic confidence level, image artifact, and overall image quality). Quantitatively, we measured and compared the level of image noise for each technique at the liver and aorta.

Results

There were significant differences (p < 0.001) among the seven reconstruction techniques in terms of lesion borders, image artifacts, and overall image quality. Low-strength DLIR (DLIR-L) exhibited the best overall image quality. Although high-strength DLIR (DLIR-H) had the least image noise and fewest artifacts, it also had the lowest scores for lesion borders and overall image quality. Image noise showed a weak to moderate positive correlation with participants' body mass index and waist circumference.

Conclusions

The optimal-strength DLIR significantly improved overall image quality for evaluating focal hepatic lesions compared to the IR technique. DLIR-L achieved the best overall image quality while maintaining acceptable levels of image noise and quality of lesion borders.

Artificial intelligence in liver cancer - new tools for research and patient management

Liver cancer has high incidence and mortality globally. Artificial intelligence (AI) has advanced rapidly, influencing cancer care. AI systems are already approved for clinical use in some tumour types (for example, colorectal cancer screening). Crucially, research demonstrates that AI can analyse histopathology, radiology and natural language in liver cancer, and can replace manual tasks and access hidden information in routinely available clinical data. However, for liver cancer, few of these applications have translated into large-scale clinical trials or clinically approved products. Here, we advocate for the incorporation of AI in all stages of liver cancer management. We present a taxonomy of AI approaches in liver cancer, highlighting areas with academic and commercial potential, and outline a policy for AI-based liver cancer management, including interdisciplinary training of researchers, clinicians and patients. The potential of AI in liver cancer is immense, but effort is required to ensure that AI can fulfil expectations.

Deep Learning-Based Reconstruction Improves the Image Quality of Low-Dose CT Colonography

RATIONALE AND OBJECTIVES

To evaluate the image quality of low-dose CT colonography (CTC) using deep learning-based reconstruction (DLR) compared to iterative reconstruction (IR).

MATERIALS AND METHODS

Adults included in the study were divided into four groups according to body mass index (BMI). Routine-dose (RD: 120 kVp) CTC images were reconstructed with IR (RD-IR); low-dose (LD: 100kVp) images were reconstructed with IR (LD-IR) and DLR (LD-DLR). The subjective image quality was rated on a 5-point scale by two radiologists independently. The parameters for objective image quality included noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The Friedman test was used to compare the image quality among RD-IR, LD-IR and LD-DLR. The KruskalWallis test was used to compare the results among different BMI groups.

RESULTS

A total of 270 volunteers (mean age: 47.94 years ± 11.57; 115 men) were included. The effective dose of low-dose CTC was decreased by approximately 83.18% (5.18mSv ± 0.86 vs. 0.86mSv ± 0.05, P < 0.001). The subjective image quality score of LD-DLR was superior to that of LD-IR (3.61 ± 0.56 vs. 2.70 ± 0.51, P < 0.001) and on par with the RD- IR's (3.61 ± 0.56 vs. 3.74 ± 0.52, P = 0.486). LD-DLR exhibited the lowest noise, and the maximum SNR and CNR compared to RD-IR and LD-IR (all P < 0.001). No statistical difference was found in the noise of LD-DLR images between different BMI groups (all P > 0.05).

CONCLUSION

Compared to IR, DLR provided low-dose CTC with superior image quality at an average radiation dose of 0.86mSv, which may be promising in future colorectal cancer screening.

Image quality evaluation in deep-learning-based CT noise reduction using virtual imaging trial methods: Contrast-dependent spatial resolution

BACKGROUND

Deep-learning-based image reconstruction and noise reduction methods (DLIR) have been increasingly deployed in clinical CT. Accurate image quality assessment of these methods is challenging as the performance measured using physical phantoms may not represent the true performance of DLIR in patients since DLIR is trained mostly on patient images.

PURPOSE

In this work, we aim to develop a patient-data-based virtual imaging trial framework and, as a first application, use it to measure the spatial resolution properties of a DLIR method.

METHODS

The patient-data-based virtual imaging trial framework consists of five steps: (1) insertion of lesions into projection domain data using the acquisition geometry of the patient exam to simulate different lesion characteristics; (2) insertion of noise into projection domain data using a realistic photon statistical model of the CT system to simulate different dose levels; (3) creation of DLIR-processed images from projection or image data; (4) creation of ensembles of DLIR-processed patient images from a large number of noise and lesion realizations; and (5) evaluation of image quality using ensemble DLIR images. This framework was applied to measure the spatial resolution of a ResNet based deep convolutional neural network (DCNN) trained on patient images. Lesions in a cylindrical shape and different contrast levels (-500, -100, -50, -20, -10 HU) were inserted to the lower right lobe of the liver in a patient case. Multiple dose levels were simulated (50%, 25%, 12.5%). Each lesion and dose condition had 600 noise realizations. Multiple reconstruction and denoising methods were used on all the noise realizations, including the original filtered-backprojection (FBP), iterative reconstruction (IR), and the DCNN method with three different strength setting (DCNN-weak, DCNN-medium, and DCNN-strong). Mean lesion signal was calculated by performing ensemble averaging of all the noise realizations for each lesion and dose condition and then subtracting the lesion-present images from the lesion absent images. Modulation transfer functions (MTFs) both in-plane and along the z-axis were calculated based on the mean lesion signals. The standard deviations of MTFs at each condition were estimated with bootstrapping: randomly sampling (with replacement) all the DLIR/FBP/IR images from the ensemble data (600 samples) at each condition. The impact of varying lesion contrast, dose levels, and denoising strengths were evaluated. Statistical analysis with paired t-test was used to compare the z-axis and in-plane spatial resolution of five algorithms for five different contrasts and three dose levels.

RESULTS

The in-plane and z-axis spatial resolution degradation of DCNN becomes more severe as the contrast or radiation dose decreased, or DCNN denoising strength increased. In comparison with FBP, a 59.5% and 4.1% reduction of in-plane and z-axis MTF (in terms of spatial frequencies at 50% MTF), respectively, was observed at low contrast (-10 HU) for DCNN with the highest denoising strength at 25% routine dose level. When the dose level reduces from 50% to 12.5% of routine dose, the in-plane and z-axis MTFs reduces from 92.1% to 76.3%, and from 98.9% to 95.5%, respectively, at contrast of -100 HU, using FBP as the reference. For most conditions of contrasts and dose levels, significant differences were found among the five algorithms, with the following relationship in both in-plane and cross-plane spatial resolution: FBP > DCNN-Weak > IR > DCNN-Medium > DCNN-Strong. The spatial resolution difference among algorithms decreases at higher contrast or dose levels.

CONCLUSIONS

A patient-data-based virtual imaging trial framework was developed and applied to measuring the spatial resolution properties of a DCNN noise reduction method at different contrast and dose levels using real patient data. As with other non-linear image reconstruction and post-processing techniques, the evaluated DCNN method degraded the in-plane and z-axis spatial resolution at lower contrast levels, lower radiation dose, and higher denoising strength.

Low-contrast lesion detection in neck CT: a multireader study comparing deep learning, iterative, and filtered back projection reconstructions using realistic phantoms

BACKGROUND

Computed tomography (CT) reconstruction algorithms can improve image quality, especially deep learning reconstruction (DLR). We compared DLR, iterative reconstruction (IR), and filtered back projection (FBP) for lesion detection in neck CT.

METHODS

Nine patient-mimicking neck phantoms were examined with a 320-slice scanner at six doses: 0.5, 1, 1.6, 2.1, 3.1, and 5.2 mGy. Each of eight phantoms contained one circular lesion (diameter 1 cm; contrast -30 HU to the background) in the parapharyngeal space; one phantom had no lesions. Reconstruction was made using FBP, IR, and DLR. Thirteen readers were tasked with identifying and localizing lesions in 32 images with a lesion and 20 without lesions for each dose and reconstruction algorithm. Receiver operating characteristic (ROC) and localization ROC (LROC) analysis were performed.

RESULTS

DLR improved lesion detection with ROC area under the curve (AUC) 0.724 ± 0.023 (mean ± standard error of the mean) using DLR versus 0.696 ± 0.021 using IR (p = 0.037) and 0.671 ± 0.023 using FBP (p < 0.001). Likewise, DLR improved lesion localization, with LROC AUC 0.407 ± 0.039 versus 0.338 ± 0.041 using IR (p = 0.002) and 0.313 ± 0.044 using FBP (p < 0.001). Dose reduction to 0.5 mGy compromised lesion detection in FBP-reconstructed images compared to doses ≥ 2.1 mGy (p ≤ 0.024), while no effect was observed with DLR or IR (p ≥ 0.058).

CONCLUSION

DLR improved the detectability of lesions in neck CT imaging. Dose reduction to 0.5 mGy maintained lesion detectability when denoising reconstruction was used.

RELEVANCE STATEMENT

Deep learning enhances lesion detection in neck CT imaging compared to iterative reconstruction and filtered back projection, offering improved diagnostic performance and potential for x-ray dose reduction.

KEY POINTS

Low-contrast lesion detectability was assessed in anatomically realistic neck CT phantoms. Deep learning reconstruction (DLR) outperformed filtered back projection and iterative reconstruction. Dose has little impact on lesion detectability against anatomical background structures.

Deep learning CT reconstruction improves liver metastases detection

OBJECTIVES

Detection of liver metastases is crucial for guiding oncological management. Computed tomography through iterative reconstructions is widely used in this indication but has certain limitations. Deep learning image reconstructions (DLIR) use deep neural networks to achieve a significant noise reduction compared to iterative reconstructions. While reports have demonstrated improvements in image quality, their impact on liver metastases detection remains unclear. Our main objective was to determine whether DLIR affects the number of detected liver metastasis. Our secondary objective was to compare metastases conspicuity between the two reconstruction methods.

METHODS

CT images of 121 patients with liver metastases were reconstructed using a 50% adaptive statistical iterative reconstruction (50%-ASiR-V), and three levels of DLIR (DLIR-low, DLIR-medium, and DLIR-high). For each reconstruction, two double-blinded radiologists counted up to a maximum of ten metastases. Visibility and contour definitions were also assessed. Comparisons between methods for continuous parameters were performed using mixed models.

RESULTS

A higher number of metastases was detected by one reader with DLIR-high: 7 (2-10) (median (Q₁-Q₃); total 733) versus 5 (2-10), respectively for DLIR-medium, DLIR-low, and ASiR-V (p < 0.001). Ten patents were detected with more metastases with DLIR-high simultaneously by both readers and a third reader for confirmation. Metastases visibility and contour definition were better with DLIR than ASiR-V.

CONCLUSION

DLIR-high enhanced the detection and visibility of liver metastases compared to ASiR-V, and also increased the number of liver metastases detected.

CRITICAL RELEVANCE STATEMENT

Deep learning-based reconstruction at high strength allowed an increase in liver metastases detection compared to hybrid iterative reconstruction and can be used in clinical oncology imaging to help overcome the limitations of CT.

KEY POINTS

Detection of liver metastases is crucial but limited with standard CT reconstructions. More liver metastases were detected with deep-learning CT reconstruction compared to iterative reconstruction. Deep learning reconstructions are suitable for hepatic metastases staging and follow-up.

3D printed phantom with 12 000 submillimeter lesions to improve efficiency in CT detectability assessment

BACKGROUND

The detectability performance of a CT scanner is difficult to precisely quantify when nonlinearities are present in reconstruction. An efficient detectability assessment method that is sensitive to small effects of dose and scanner settings is desirable. We previously proposed a method using a search challenge instrument: a phantom is embedded with hundreds of lesions at random locations, and a model observer is used to detect lesions. Preliminary tests in simulation and a prototype showed promising results.

PURPOSE

In this work, we fabricated a full-size search challenge phantom with design updates, including changes to lesion size, contrast, and number, and studied our implementation by comparing the lesion detectability from a nonprewhitening (NPW) model observer between different reconstructions at different exposure levels, and by estimating the instrument sensitivity to detect changes in dose.

METHODS

Designed to fit into QRM anthropomorphic phantoms, our search challenge phantom is a cylindrical insert 10 cm wide and 4 cm thick, embedded with 12 000 lesions (nominal width of 0.6 mm, height of 0.8 mm, and contrast of -350 HU), and was fabricated using PixelPrint, a 3D printing technique. The insert was scanned alone at a high dose to assess printing accuracy. To evaluate lesion detectability, the insert was placed in a QRM thorax phantom and scanned from 50 to 625 mAs with increments of 25 mAs, once per exposure level, and the average of all exposure levels was used as high-dose reference. Scans were reconstructed with three different settings: filtered-backprojection (FBP) with Br40 and Br59, and Sinogram Affirmed Iterative Reconstruction (SAFIRE) with strength level 5 and Br59 kernel. An NPW model observer was used to search for lesions, and detection performance of different settings were compared using area under the exponential transform of free response ROC curve (AUC). Using propagation of uncertainty, the sensitivity to changes in dose was estimated by the percent change in exposure due to one standard deviation of AUC, measured from 5 repeat scans at 100, 200, 300, and 400 mAs.

RESULTS

The printed insert lesions had an average position error of 0.20 mm compared to printing reference. As the exposure level increases from 50 mAs to 625 mAs, the lesion detectability AUCs increase from 0.38 to 0.92, 0.42 to 0.98, and 0.41 to 0.97 for FBP Br40, FBP Br59, and SAFIRE Br59, respectively, with a lower rate of increase at higher exposure level. FBP Br59 performed best with AUC 0.01 higher than SAFIRE Br59 on average and 0.07 higher than FBP Br40 (all P < 0.001). The standard deviation of AUC was less than 0.006, and the sensitivity to detect changes in mAs was within 2% for FBP Br59.

CONCLUSIONS

Our 3D-printed search challenge phantom with 12 000 submillimeter lesions, together with an NPW model observer, provide an efficient CT detectability assessment method that is sensitive to subtle effects in reconstruction and is sensitive to small changes in dose.

Low-dose liver CT: image quality and diagnostic accuracy of deep learning image reconstruction algorithm

OBJECTIVES

To perform a comprehensive within-subject image quality analysis of abdominal CT examinations reconstructed with DLIR and to evaluate diagnostic accuracy compared to the routinely applied adaptive statistical iterative reconstruction (ASiR-V) algorithm.

MATERIALS AND METHODS

Oncologic patients were prospectively enrolled and underwent contrast-enhanced CT. Images were reconstructed with DLIR with three intensity levels of reconstruction (high, medium, and low) and ASiR-V at strength levels from 10 to 100% with a 10% interval. Three radiologists characterized the lesions and two readers assessed diagnostic accuracy and calculated signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), figure of merit (FOM), and subjective image quality, the latter with a 5-point Likert scale.

RESULTS

Fifty patients (mean age: 70 ± 10 years, 23 men) were enrolled and 130 liver lesions (105 benign lesions, 25 metastases) were identified. DLIR_H achieved the highest SNR and CNR, comparable to ASiR-V 100% (p ≥ .051). DLIR_M returned the highest subjective image quality (score: 5; IQR: 4-5; p ≤ .001) and significant median increase (29%) in FOM (p < .001). Differences in detection were identified only for lesions ≤ 0.5 cm: 32/33 lesions were detected with DLIR_M and 26 lesions were detected with ASiR-V 50% (p = .031). Lesion accuracy of was 93.8% (95% CI: 88.1, 97.3; 122 of 130 lesions) for DLIR and 87.7% (95% CI: 80.8, 92.8; 114 of 130 lesions) for ASiR-V 50%.

CONCLUSIONS

DLIR yields superior image quality and provides higher diagnostic accuracy compared to ASiR-V in the assessment of hypovascular liver lesions, in particular for lesions ≤ 0.5 cm.

CLINICAL RELEVANCE STATEMENT

Deep learning image reconstruction algorithm demonstrates higher diagnostic accuracy compared to iterative reconstruction in the identification of hypovascular liver lesions, especially for lesions ≤ 0.5 cm.

KEY POINTS

• Iterative reconstruction algorithm impacts image texture, with negative effects on diagnostic capabilities. • Medium-strength deep learning image reconstruction algorithm outperforms iterative reconstruction in the diagnostic accuracy of ≤ 0.5 cm hypovascular liver lesions (93.9% vs 78.8%), also granting higher objective and subjective image quality. • Deep learning image reconstruction algorithm can be safely implemented in routine abdominal CT protocols in place of iterative reconstruction.

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.

Organ dose prediction for patients undergoing radiotherapy CBCT chest examinations using artificial intelligence

PURPOSE

To propose an artificial intelligence (AI)-based method for personalized and real-time dosimetry for chest CBCT acquisitions.

METHODS

CT images from 113 patients who underwent radiotherapy treatment were collected for simulating thorax examinations using cone-beam computed tomography (CBCT) with the Monte Carlo technique. These simulations yielded organ dose data, used to train and validate specific AI algorithms. The efficacy of these AI algorithms was evaluated by comparing dose predictions with the actual doses derived from Monte Carlo simulations, which are the ground truth, utilizing Bland-Altman plots for this comparative analysis.

RESULTS

The absolute mean discrepancies between the predicted doses and the ground truth are (0.9 ± 1.3)% for bones, (1.2 ± 1.2)% for the esophagus, (0.5 ± 1.3)% for the breast, (2.5 ± 1.4)% for the heart, (2.4 ± 2.1)% for lungs, (0.8 ± 0.6)% for the skin, and (1.7 ± 0.7)% for integral. Meanwhile, the maximum discrepancies between the predicted doses and the ground truth are (14.4 ± 1.3)% for bones, (12.9 ± 1.2)% for the esophagus, (9.4 ± 1.3)% for the breast, (14.6 ± 1.4)% for the heart, (21.2 ± 2.1)% for lungs, (10.0 ± 0.6)% for the skin, and (10.5 ± 0.7)% for integral.

CONCLUSIONS

AI models that can make real-time predictions of the organ doses for patients undergoing CBCT thorax examinations as part of radiotherapy pre-treatment positioning were developed. The results of this study clearly show that the doses predicted by analyzed AI models are in close agreement with those calculated using Monte Carlo simulations.

CT and MRI of abdominal cancers: current trends and perspectives in the era of radiomics and artificial intelligence

Abdominal cancers continue to pose daily challenges to clinicians, radiologists and researchers. These challenges are faced at each stage of abdominal cancer management, including early detection, accurate characterization, precise assessment of tumor spread, preoperative planning when surgery is anticipated, prediction of tumor aggressiveness, response to therapy, and detection of recurrence. Technical advances in medical imaging, often in combination with imaging biomarkers, show great promise in addressing such challenges. Information extracted from imaging datasets owing to the application of radiomics can be used to further improve the diagnostic capabilities of imaging. However, the analysis of the huge amount of data provided by these advances is a difficult task in daily practice. Artificial intelligence has the potential to help radiologists in all these challenges. Notably, the applications of AI in the field of abdominal cancers are expanding and now include diverse approaches for cancer detection, diagnosis and classification, genomics and detection of genetic alterations, analysis of tumor microenvironment, identification of predictive biomarkers and follow-up. However, AI currently has some limitations that need further refinement for implementation in the clinical setting. This review article sums up recent advances in imaging of abdominal cancers in the field of image/data acquisition, tumor detection, tumor characterization, prognosis, and treatment response evaluation.

Image Quality and Diagnostic Performance of Low-Dose Liver CT with Deep Learning Reconstruction versus Standard-Dose CT

Purpose To compare the image quality and diagnostic capability in detecting malignant liver tumors of low-dose CT (LDCT, 33% dose) with deep learning-based denoising (DLD) and standard-dose CT (SDCT, 100% dose) with model-based iterative reconstruction (MBIR). Materials and Methods In this prospective, multicenter, noninferiority study, individuals referred for liver CT scans were enrolled from three tertiary referral hospitals between February 2021 and August 2022. All liver CT scans were conducted using a dual-source scanner with the dose split into tubes A (67% dose) and B (33% dose). Blended images from tubes A and B were created using MBIR to produce SDCT images, whereas LDCT images used data from tube B and were reconstructed with DLD. The noise in liver images was measured and compared between imaging techniques. The diagnostic performance of each technique in detecting malignant liver tumors was evaluated by three independent radiologists using jackknife alternative free-response receiver operating characteristic analysis. Noninferiority of LDCT compared with SDCT was declared when the lower limit of the 95% CI for the difference in figure of merit (FOM) was greater than -0.10. Results A total of 296 participants (196 men, 100 women; mean age, 60.5 years ± 13.3 [SD]) were included. The mean noise level in the liver was significantly lower for LDCT (10.1) compared with SDCT (10.7) (P < .001). Diagnostic performance was assessed in 246 participants (108 malignant tumors in 90 participants). The reader-averaged FOM was 0.880 for SDCT and 0.875 for LDCT (P = .35). The difference fell within the noninferiority margin (difference, -0.005 [95% CI: -0.024, 0.012]). Conclusion Compared with SDCT with MBIR, LDCT using 33% of the standard radiation dose had reduced image noise and comparable diagnostic performance in detecting malignant liver tumors. Keywords: CT, Abdomen/GI, Liver, Comparative Studies, Diagnosis, Reconstruction Algorithms Clinical trial registration no. NCT05804799 © RSNA, 2024 Supplemental material is available for this article.

Deep learning reconstruction vs standard reconstruction for abdominal CT: the influence of BMI

OBJECTIVE

This study aimed to evaluate the image quality and lesion conspicuity of the deep learning image reconstruction (DLIR) algorithm compared with standard image reconstruction algorithms on abdominal enhanced computed tomography (CT) scanning with a wide range of body mass indexes (BMIs).

METHODS

A total of 112 participants who underwent contrast-enhanced abdominal CT scans were divided into three groups according to BMIs: the 80-kVp group (BMI ≤ 23.9 kg/m2), 100-kVp group (BMI 24-28.9 kg/m2), and 120-kVp group (BMI ≥ 29 kg/m2). All images were reconstructed using filtered back projection (FBP), adaptive statistical iterative reconstruction-V of 50% level (IR), and DLIR at low, medium, and high levels (DL, DM, and DH, respectively). Subjective noise, artifact, overall image quality, and low- and high-contrast hepatic lesion conspicuity were all graded on a 5-point scale. The CT attenuation value (in HU), image noise, and contrast-to-noise ratio (CNR) were quantified and compared.

RESULTS

DM and DH improved the qualitative and quantitative parameters compared with FBP and IR for all three BMI groups. DH had the lowest image noise and highest CNR value, while DM had the highest subjective overall image quality and low- and high-contrast lesion conspicuity scores for the three BMI groups. Based on the FBP, the improvement in image quality and lesion conspicuity of DM and DH images was greater in the 80-kVp group than in the 100-kVp and 120-kVp groups.

CONCLUSION

For all BMIs, DLIR improves both image quality and hepatic lesion conspicuity, of which DM would be the best choice to balance both.

CLINICAL RELEVANCE STATEMENT

The study suggests that utilizing DLIR, particularly at the medium level, can significantly enhance image quality and lesion visibility on abdominal CT scans across a wide range of BMIs.

KEY POINTS

• DLIR improved the image quality and lesion conspicuity across a wide range of BMIs. • DLIR at medium level had the highest subjective parameters and lesion conspicuity scores among all reconstruction levels. • On the basis of the FBP, the 80-kVp group had improved image quality and lesion conspicuity more than the 100-kVp and 120-kVp groups.

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.

Deep learning reconstruction CT for liver metastases: low-dose dual-energy vs standard-dose single-energy

OBJECTIVES

To assess image quality and liver metastasis detection of reduced-dose dual-energy CT (DECT) with deep learning image reconstruction (DLIR) compared to standard-dose single-energy CT (SECT) with DLIR or iterative reconstruction (IR).

METHODS

In this prospective study, two groups of 40 participants each underwent abdominal contrast-enhanced scans with full-dose SECT (120-kVp images, DLIR and IR algorithms) or reduced-dose DECT (40- to 60-keV virtual monochromatic images [VMIs], DLIR algorithm), with 122 and 106 metastases, respectively. Groups were matched by age, sex ratio, body mass index, and cross-sectional area. Noise power spectrum of liver images and task-based transfer function of metastases were calculated to assess the noise texture and low-contrast resolution. The image noise, signal-to-noise ratios (SNR) of liver and portal vein, liver-to-lesion contrast-to-noise ratio (LLR), lesion conspicuity, lesion detection rate, and the subjective image quality metrics were compared between groups on 1.25-mm reconstructed images.

RESULTS

Compared to 120-kVp images with IR, 40- and 50-keV VMIs with DLIR showed similar noise texture and LLR, similar or higher image noise and low-contrast resolution, improved SNR and lesion conspicuity, and similar or better perceptual image quality. When compared to 120-kVp images with DLIR, 50-keV VMIs with DLIR had similar low-contrast resolution, SNR, LLR, lesion conspicuity, and perceptual image quality but lower frequency noise texture and higher image noise. For the detection of hepatic metastases, reduced-dose DECT by 34% maintained observer lesion detection rates.

CONCLUSION

DECT assisted with DLIR enables a 34% dose reduction for detecting hepatic metastases while maintaining comparable perceptual image quality to full-dose SECT.

CLINICAL RELEVANCE STATEMENT

Reduced-dose dual-energy CT with deep learning image reconstruction is as accurate as standard-dose single-energy CT for the detection of liver metastases and saves more than 30% of the radiation dose.

KEY POINTS

• The 40- and 50-keV virtual monochromatic images (VMIs) with deep learning image reconstruction (DLIR) improved lesion conspicuity compared with 120-kVp images with iterative reconstruction while providing similar or better perceptual image quality. • The 50-keV VMIs with DLIR provided comparable perceptual image quality and lesion conspicuity to 120-kVp images with DLIR. • The reduction of radiation by 34% by DLIR in low-keV VMIs is clinically sufficient for detecting low-contrast hepatic metastases.

Preclinical validation of a novel deep learning-based metal artifact correction algorithm for orthopedic CT imaging

PURPOSE

To validate a novel deep learning-based metal artifact correction (MAC) algorithm for CT, namely, AI-MAC, in preclinical setting with comparison to conventional MAC and virtual monochromatic imaging (VMI) technique.

MATERIALS AND METHODS

An experimental phantom was designed by consecutively inserting two sets of pedicle screws (size Φ 6.5 × 30-mm and Φ 7.5 × 40-mm) into a vertebral specimen to simulate the clinical scenario of metal implantation. The resulting MAC, VMI, and AI-MAC images were compared with respect to the metal-free reference image by subjective scoring, as well as by CT attenuation, image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and correction accuracy via adaptive segmentation of the paraspinal muscle and vertebral body.

RESULTS

The AI-MAC and VMI images showed significantly higher subjective scores than the MAC image (all p < 0.05). The SNRs and CNRs on the AI-MAC image were comparable to the reference (all p > 0.05), whereas those on the VMI were significantly lower (all p < 0.05). The paraspinal muscle segmented on the AI-MAC image was 4.6% and 5.1% more complete to the VMI and MAC images for the Φ 6.5 × 30-mm screws, and 5.0% and 5.1% for the Φ 7.5 × 40-mm screws, respectively. The vertebral body segmented on the VMI was closest to the reference, with only 3.2% and 7.4% overestimation for Φ 6.5 × 30-mm and Φ 7.5 × 40-mm screws, respectively.

CONCLUSIONS

Using metal-free reference as the ground truth for comparison, the AI-MAC outperforms VMI in characterizing soft tissue, while VMI is useful in skeletal depiction.

Deep learning imaging reconstruction of reduced-dose 40 keV virtual monoenergetic imaging for early detection of colorectal cancer liver metastases

OBJECTIVE

To explore whether reduced-dose (RD) gemstone spectral imaging (GSI) and deep learning image reconstruction (DLIR) of 40 keV virtual monoenergetic image (VMI) enhanced the early detection and diagnosis of colorectal cancer liver metastases (CRLM).

METHODS

Thirty-five participants with pathologically confirmed colorectal cancer were prospectively enrolled from March to August 2022 after routine care abdominal computed tomography (CT). GSI mode was used for contrast-enhanced CT, and two portal venous phase CT images were obtained [standard-dose (SD) CT dose index (CTDIvol) = 15.51 mGy, RD CTDIvol = 7.95 mGy]. The 40 keV-VMI were reconstructed via filtered back projection (FBP) and iterative reconstruction (ASIR-V 60 %, AV60) of both SD and RD images. RD medium-strength deep learning image reconstruction (DLIR-M) and RD high-strength deep learning image reconstruction (DLIR-H) were used to reconstruct the 40 keV-VMI. The contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) of the liver and the lesions were objectively evaluated. The overall image quality, lesion conspicuity, and diagnostic confidence were subjectively evaluated, to compare the differences in evaluation results among the different images.

RESULTS

All 35 participants (mean age: 59.51 ± 11.01 years; 14 females) underwent SD and RD GSI portal venous-phase CT scans. The dose-length product of the RD GSI scan was reduced by 49-53 % lower than that of the SD GSI scan (420.22 ± 31.95) vs (817.58 ± 60.56). A total of 219 lesions were identified, including 55 benign lesions and 164 metastases, with an average size of 7.37 ± 4.14 mm. SD-FBP detected 207 lesions, SD-AV60 detected 201 lesions, and DLIR-M and DLIR-H detected 199 and 190 lesions, respectively. For lesions ≤ 5 mm, there was no statistical difference between SD-FBP vs DLIR-M (χ2McNemar = 1.00, P = 0.32) and SD-AV60 vs DLIR-M (χ2McNemar = 0.33, P = 0.56) in the detection rate. The CNR, SNR, and noise of DLIR-M and DLIR-H 40 keV-VMI images were better than those of SD-FBP images (P < 0.01) but did not differ significantly from those of SD-AV60 images (P > 0.05). When the lesions ≤ 5 mm, there were statistical differences in the overall diagnostic sensitivity of lesions compared with SD-FBP, SD-AV60, DLIR-M and DLIR-H (P＜0.01). There were no statistical differences in the sensitivity of lesions diagnosis between SD-FBP, SD-AV60 and DLIR-M (both P＞0.05). However, the DLIR-M subjective image quality and lesion diagnostic confidence were higher for SD-FBP (both P < 0.01).

CONCLUSION

Reduced dose DLIR-M of 40 keV-VMI can be used for routine follow-up care of colorectal cancer patients, to optimize evaluations and ensure CT image quality. Meanwhile, the detection rate and diagnostic sensitivity and specificity of small lesions, early liver metastases is not obviously reduced.

Accuracy of liver metastasis detection and characterization: Dual-energy CT versus single-energy CT with deep learning reconstruction

PURPOSE

To assess whether image quality differences between SECT (single-energy CT) and DECT (dual-energy CT 70 keV) with equivalent radiation doses result in altered detection and characterization accuracy of liver metastases when using deep learning image reconstruction (DLIR), and whether DECT spectral curve usage improves accuracy of indeterminate lesion characterization.

METHODS

In this prospective Health Insurance Portability and Accountability Act-compliant study (March through August 2022), adult men and non-pregnant adult women with biopsy-proven colorectal cancer and liver metastases underwent SECT (120 kVp) and a DECT (70 keV) portovenous abdominal CT scan using DLIR in the same breath-hold (Revolution CT ES; GE Healthcare). Participants were excluded if consent could not be obtained, if there were nonequivalent radiation doses between the two scans, or if the examination was cancelled/rescheduled. Three radiologists independently performed lesion detection and characterization during two separate sessions (SECT DLIRmedium and DECT DLIRhigh) as well as reported lesion confidence and overall image quality. Hounsfield units were measured. Spectral HU curves were provided for any lesions rated as indeterminate. McNemar's test was used to test the marginal homogeneity in terms of diagnostic sensitivity, accuracy and lesion detection. A generalized estimating equation method was used for categorical outcomes.

RESULTS

30 participants (mean age, 58 years ± 11, 21 men) were evaluated. Mean CTDIvol was 34 mGy for both scans. 141 lesions (124 metastases, 17 benign) with a mean size of 0.8 cm ± 0.3 cm were identified. High scores for image quality (scores of 4 or 5) were not significantly different between DECT (N = 71 out of 90 total scores from the three readers) and SECT (N = 62) (OR, 2.01; 95% CI:0.89, 4.57; P = 0.093). Equivalent image noise to SECT DLIRmed (HU SD 10 ± 2) was obtained with DECT DLIRhigh (HU SD 10 ± 3) (P = 1). There was no significant difference in lesion detection between DECT and SECT (140/141 lesions) (99.3%; 95% CI:96.1%, 100%).The mean lesion confidence scores by each reader were 4.2 ± 1.3, 3.9 ± 1.0, and 4.8 ± 0.8 for SECT and 4.1 ± 1.4, 4.0 ± 1.0, and 4.7 ± 0.8 for DECT (odds ratio [OR], 0.83; 95% CI: 0.62, 1.11; P = 0.21). Small lesion (≤5mm) characterization accuracy on SECT and DECT was 89.1% (95% CI:76.4%, 96.4%; 41/46) and 84.8% (71.1%, 93.7%; 39/46), respectively (P = 0.41). Use of spectral HU lesion curves resulted in 34 correct changes in characterizations and no mischaracterizations.

CONCLUSION

DECT required a higher strength of DLIR to obtain equivalent noise compared to SECT DLIR. At equivalent radiation doses and image noise, there was no significant difference in subjective image quality or observer lesion performance between DECT (70 keV) and SECT. However, DECT spectral HU curves of indeterminate lesions improved characterization.

Recent advances in artificial intelligence for cardiac CT: Enhancing diagnosis and prognosis prediction

Recent advances in artificial intelligence (AI) for cardiac computed tomography (CT) have shown great potential in enhancing diagnosis and prognosis prediction in patients with cardiovascular disease. Deep learning, a type of machine learning, has revolutionized radiology by enabling automatic feature extraction and learning from large datasets, particularly in image-based applications. Thus, AI-driven techniques have enabled a faster analysis of cardiac CT examinations than when they are analyzed by humans, while maintaining reproducibility. However, further research and validation are required to fully assess the diagnostic performance, radiation dose-reduction capabilities, and clinical correctness of these AI-driven techniques in cardiac CT. This review article presents recent advances of AI in the field of cardiac CT, including deep-learning-based image reconstruction, coronary artery motion correction, automatic calcium scoring, automatic epicardial fat measurement, coronary artery stenosis diagnosis, fractional flow reserve prediction, and prognosis prediction, analyzes current limitations of these techniques and discusses future challenges.

Deep learning-based iodine contrast-augmenting algorithm for low-contrast-dose liver CT to assess hypovascular hepatic metastasis

PURPOSE

To investigate the image quality and diagnostic performance of low-contrast-dose liver CT using a deep learning-based iodine contrast-augmenting algorithm (DLICA) for hypovascular hepatic metastases.

METHODS

This retrospective study included 128 patients who underwent contrast-enhanced dual-energy CT for hepatic metastasis surveillance between July 2019 and June 2022 using a 30% reduced iodine contrast dose in the portal phase. Three image types were reconstructed: 50-keV virtual monoenergetic images (50-keV VMI); linearly blended images simulating 120-kVp images (120-kVp); and post-processed 120-kVp images using DLICA (DLICA 120-kVp). Three reviewers evaluated lesion conspicuity, image contrast, and subjective image noise. We also measured image noise, contrast-to-noise ratios (CNRs), and signal-to-noise ratios (SNRs). The diagnostic performance for hepatic metastases was evaluated using a jackknife alternative free-response receiver operating characteristic method with the consensus of two independent radiologists as the reference standard.

RESULTS

DLICA 120-kVp demonstrated significantly higher CNR of lesions to liver (5.7 ± 3.1 vs. 3.8 ± 2.1 vs. 3.8 ± 2.1) and higher SNR compared with 50-keV VMI and 120-kVp (p < 0.001 for all). DLICA 120-kVp had significantly lower image noise than 50-kVp VMI for all regions (p < 0.001 for all). DLICA 120-kVp also exhibited superior lesion conspicuity (4.0 [3.3-4.3] vs. 3.7 [3.0-4.0] vs. 3.7 [3.0-4.0]), higher image contrast, and lower subjective image noise compared with 50-keV VMI and 120-kVp (p < 0.001 for all). Although there was no significant difference in the figure of merit for lesion diagnosis among the three methods (p = 0.11), DLICA 120-kVp had a significantly higher figure of merit for lesions with a diameter < 20 mm than 50-keV VMI (0.677 vs. 0.648, p = 0.007). On a per-lesion basis, DLICA 120-kVp also demonstrated higher sensitivity than the 50-keV VMI (81.2% vs. 72.9%, p < 0.001). The specificities per lesion were not significantly different among the three algorithms (p = 0.15).

CONCLUSION

DLICA at 120-kVp provided superior lesion conspicuity and image quality and similar diagnostic performance for hypovascular hepatic metastases compared with 50-keV VMI.

Value of deep-learning image reconstruction at submillisievert CT for evaluation of the female pelvis

AIM

To assess the value of deep-learning reconstruction (DLR) at submillisievert computed tomography (CT) for the evaluation of the female pelvis, with standard dose (SD) hybrid iterative reconstruction (IR) images as reference.

MATERIALS AND METHODS

The present study enrolled 50 female patients consecutively who underwent contrast-enhanced abdominopelvic CT for clinically indicated reasons. Submillisievert pelvic images were acquired using a noise index of 15 for low-dose (LD) scans, which were reconstructed with DLR (body and body sharp), hybrid-IR, and model-based IR (MBIR). Additionally, SD scans were reconstructed with a noise index of 7.5 using hybrid-IR. Radiation dose, quantitative image quality, overall image quality, image appearance using a five-point Likert scale (1-5: worst to best), and lesion evaluation in both SD and LD images were analysed and compared.

RESULTS

The submillisievert pelvic CT examinations showed a 61.09 ± 4.13% reduction in the CT dose index volume compared to SD examinations. Among the LD images, DLR (body sharp) had the highest quantitative quality, followed by DLR (body), MBIR, and hybrid-IR. LD DLR (body) had overall image quality comparable to the reference (p=0.084) and favourable image appearance (p=0.209). In total, 40 pelvic lesions were detected in both SD and LD images. LD DLR (body and body sharp) exhibited similar diagnostic confidence (p=0.317 and 0.096) compared with SD hybrid-IR.

CONCLUSION

DLR algorithms, providing comparable image quality and diagnostic confidence, are feasible in submillisievert abdominopelvic CT. The DLR (body) algorithm with favourable image appearance is recommended in clinical settings.

Deep Learning-Based Motion Correction in Projection Domain for Coronary Computed Tomography Angiography: A Clinical Evaluation

OBJECTIVE

This study aimed to evaluate the clinical performance of a deep learning-based motion correction algorithm (MCA) in projection domain for coronary computed tomography angiography (CCTA).

METHODS

A total of 192 patients who underwent CCTA examinations were included and divided into 2 groups based on the average heart rate (HR): group 1, 82 patients with HR of <75 beats per minute; group 2, 110 patients with HR of ≥75 beats per minute. The CCTA images were reconstructed with and without MCA. The subjective image quality was graded in terms of vessel visualization, sharpness, diagnostic confidence, and overall image quality using a 5-point scale, where cases with all scores of ≥3 were deemed interpretable. Objective image quality was measured through signal-to-noise ratio and contrast-to-noise ratio in regions relative to the vessels. The image quality scores for 2 reconstructions and effective dose between 2 groups were compared.

RESULTS

The mean effective dose was similar between 2 groups. Neither group showed significant difference on objective image quality for 2 reconstructions. Images reconstructed with and without MCA were both found interpretable for group 1, whereas the subjective image quality was significantly improved by the MCA for all 4 metrics in group 2, with the interpretability increased from 80.91% to 99.09%. Compared with group 1, group 2 showed similar interpretability and diagnostic confidence, despite inferior overall image quality.

CONCLUSIONS

In CCTA examinations, the deep learning-based MCA is capable of improving the image quality and diagnostic confidence for patients with increased HR to a similar level as for those with low HR.

Low pitch significantly reduces helical artifacts in abdominal CT

PURPOSE

High helical pitch scanning minimizes scan times in CT imaging, and thus also minimizes motion artifact and mis-synchronization with contrast bolus. However, high pitch produces helical artifacts that may adversely affect diagnostic image quality. This study aims to determine the severity and incidence of helical artifacts in abdominal CT imaging and their relation to the helical pitch scan parameter.

METHODS

To obtain a dataset with varying pitch values, we used CT exam data both internal and external to our center. A cohort of 59 consecutive adult patients receiving an abdomen CT examination at our center with an accompanying prior examination from an external center was selected for retrospective review. Two expert observers performed a blinded rating of helical artifact in each examination using a five-point Likert scale. The incidence of artifacts with respect to the helical pitch was assessed. A generalized linear mixed-effects regression (GLMER) model, with study arm (Internal or External to our center) and helical pitch as the fixed-effect predictor variables, was fit to the artifact ratings, and significance of the predictor variables was tested.

RESULTS

For a pitch of <0.75, the proportion of exams with mild or worse helical artifacts (Likert scores of 1-3) was <1%. The proportion increased to 16% for exams with pitch between 0.75 and 1.2, and further increased to 78% for exams with a pitch greater than 1.2. Pitch was significantly associated with helical artifact in the GLMER model (p = 2.8 × 10-9), while study arm was not a significant factor (p = 0.76).

CONCLUSION

The incidence and severity of helical artifact increased with helical pitch. This difference persisted even after accounting for the potential confounding factor of the center where the study was performed.

Coronary artery calcium quantification: comparison between filtered-back projection, hybrid iterative reconstruction, and deep learning reconstruction techniques

BACKGROUND

The reference protocol for the quantification of coronary artery calcium (CAC) should be updated to meet the standards of modern imaging techniques.

PURPOSE

To assess the influence of filtered-back projection (FBP), hybrid iterative reconstruction (IR), and three levels of deep learning reconstruction (DLR) on CAC quantification on both in vitro and in vivo studies.

MATERIAL AND METHODS

In vitro study was performed with a multipurpose anthropomorphic chest phantom and small pieces of bones. The real volume of each piece was measured using the water displacement method. In the in vivo study, 100 patients (84 men; mean age = 71.2 ± 8.7 years) underwent CAC scoring with a tube voltage of 120 kVp and image thickness of 3 mm. The image reconstruction was done with FBP, hybrid IR, and three levels of DLR including mild (DLRmild), standard (DLRstd), and strong (DLRstr).

RESULTS

In the in vitro study, the calcium volume was equivalent (P = 0.949) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. In the in vivo study, the image noise was significantly lower in images that used DLRstr-based reconstruction, when compared images other reconstructions (P < 0.001). There were no significant differences in the calcium volume (P = 0.987) and Agatston score (P = 0.991) among FBP, hybrid IR, DLRmild, DLRstd, and DLRstr. The highest overall agreement of Agatston scores was found in the DLR groups (98%) and hybrid IR (95%) when compared to standard FBP reconstruction.

CONCLUSION

The DLRstr presented the lowest bias of agreement in the Agatston scores and is recommended for the accurate quantification of CAC.

Deep-learning CT reconstruction in clinical scans of the abdomen: a systematic review and meta-analysis

OBJECTIVE

To perform a systematic literature review and meta-analysis of the two most common commercially available deep-learning algorithms for CT.

METHODS

We used PubMed, Scopus, Embase, and Web of Science to conduct systematic searches for studies assessing the most common commercially available deep-learning CT reconstruction algorithms: True Fidelity (TF) and Advanced intelligent Clear-IQ Engine (AiCE) in the abdomen of human participants since only these two algorithms currently have adequate published data for robust systematic analysis.

RESULTS

Forty-four articles fulfilled inclusion criteria. 32 studies evaluated TF and 12 studies assessed AiCE. DLR algorithms produced images with significantly less noise (22-57.3% less than IR) but preserved a desirable noise texture with increased contrast-to-noise ratios and improved lesion detectability on conventional CT. These improvements with DLR were similarly noted in dual-energy CT which was only assessed for a single vendor. Reported radiation reduction potential was 35.1-78.5%. Nine studies assessed observer performance with the two dedicated liver lesion studies being performed on the same vendor reconstruction (TF). These two studies indicate preserved low contrast liver lesion detection (> 5 mm) at CTDIvol 6.8 mGy (BMI 23.5 kg/m2) to 12.2 mGy (BMI 29 kg/m2). If smaller lesion detection and improved lesion characterization is needed, a CTDIvol of 13.6-34.9 mGy is needed in a normal weight to obese population. Mild signal loss and blurring have been reported at high DLR reconstruction strengths.

CONCLUSION

Deep learning reconstructions significantly improve image quality in CT of the abdomen. Assessment of other dose levels and clinical indications is needed. Careful choice of radiation dose levels is necessary, particularly for small liver lesion assessment.

Improving lesion conspicuity in abdominal dual-energy CT with deep learning image reconstruction: a prospective study with five readers

OBJECTIVES

To evaluate image quality, diagnostic acceptability, and lesion conspicuity in abdominal dual-energy CT (DECT) using deep learning image reconstruction (DLIR) compared to those using adaptive statistical iterative reconstruction-V (Asir-V) at 50% blending (AV-50), and to identify potential factors impacting lesion conspicuity.

METHODS

The portal-venous phase scans in abdominal DECT of 47 participants with 84 lesions were prospectively included. The raw data were reconstructed to virtual monoenergetic image (VMI) at 50 keV using filtered back-projection (FBP), AV-50, and DLIR at low (DLIR-L), medium (DLIR-M), and high strength (DLIR-H). A noise power spectrum (NPS) was generated. CT number and standard deviation values of eight anatomical sites were measured. Signal-to-noise (SNR), and contrast-to-noise ratio (CNR) values were calculated. Five radiologists assessed image quality in terms of image contrast, image noise, image sharpness, artificial sensation, and diagnostic acceptability, and evaluated the lesion conspicuity.

RESULTS

DLIR further reduced image noise (p < 0.001) compared to AV-50 while better preserved the average NPS frequency (p < 0.001). DLIR maintained CT number values (p > 0.99) and improved SNR and CNR values compared to AV-50 (p < 0.001). DLIR-H and DLIR-M showed higher ratings in all image quality analyses than AV-50 (p < 0.001). DLIR-H provided significantly better lesion conspicuity than AV-50 and DLIR-M regardless of lesion size, relative CT attenuation to surrounding tissue, or clinical purpose (p < 0.05).

CONCLUSIONS

DLIR-H could be safely recommended for routine low-keV VMI reconstruction in daily contrast-enhanced abdominal DECT to improve image quality, diagnostic acceptability, and lesion conspicuity.

KEY POINTS

• DLIR is superior to AV-50 in noise reduction, with less shifts of the average spatial frequency of NPS towards low frequency, and larger improvements of NPS noise, noise peak, SNR, and CNR values. • DLIR-M and DLIR-H generate better image quality in terms of image contrast, noise, sharpness, artificial sensation, and diagnostic acceptability than AV-50, while DLIR-H provides better lesion conspicuity than AV-50 and DLIR-M. • DLIR-H could be safely recommended as a new standard for routine low-keV VMI reconstruction in contrast-enhanced abdominal DECT to provide better lesion conspicuity and better image quality than the standard AV-50.

Deep-learning image reconstruction for 80-kVp pancreatic CT protocol: Comparison of image quality and pancreatic ductal adenocarcinoma visibility with hybrid-iterative reconstruction

PURPOSE

To evaluate the image quality and visibility of pancreatic ductal adenocarcinoma (PDAC) in 80-kVp pancreatic CT protocol and compare them between hybrid-iterative reconstruction (IR) and deep-learning image reconstruction (DLIR) algorithms.

METHOD

A total of 56 patients who underwent 80-kVp pancreatic protocol CT for pancreatic disease evaluation from January 2022 to July 2022 were included in this retrospective study. Among them, 20 PDACs were observed. The CT raw data were reconstructed using 40% adaptive statistical IR-Veo (hybrid-IR group) and DLIR at medium- and high-strength levels (DLIR-M and DLIR-H groups, respectively). The CT attenuation of the abdominal aorta, pancreas, and PDAC (if present) at the pancreatic phase and those of the portal vein and liver at the portal venous phase; background noise; signal-to-noise ratio (SNR) of these anatomical structures; and tumor-to-pancreas contrast-to-noise ratio (CNR) were calculated. The confidence scores for the image noise, overall image quality, and visibility of PDAC were qualitatively assigned using a five-point scale. Quantitative and qualitative parameters were compared among the three groups using Friedman test.

RESULTS

The CT attenuation of all anatomical structures were comparable among the three groups (P = .26-.86), except that of the pancreas (P = .001). Background noise was lower (P <.001) and SNRs (P <.001) and tumor-to-pancreas CNR (P <.001) were higher in the DLIR-H group than those in the other two groups. The image noise, overall image quality, and visibility of PDAC were better in the DLIR-H group than in the other two groups (P <.001-.003).

CONCLUSION

In 80-kVp pancreatic CT protocol, DLIR at a high-strength level improved image quality and visibility of PDAC.

Self-trained deep convolutional neural network for noise reduction in CT

Purpose

Supervised deep convolutional neural network (CNN)-based methods have been actively used in clinical CT to reduce image noise. The networks of these methods are typically trained using paired high- and low-quality data from a massive number of patients and/or phantom images. This training process is tedious, and the network trained under a given condition may not be generalizable to patient images acquired and reconstructed under different conditions. We propose a self-trained deep CNN (ST_CNN) method for noise reduction in CT that does not rely on pre-existing training datasets.

Approach

The ST_CNN training was accomplished using extensive data augmentation in the projection domain, and the inference was applied to the data itself. Specifically, multiple independent noise insertions were applied to the original patient projection data to generate multiple realizations of low-quality projection data. Then, rotation augmentation was adopted for both the original and low-quality projection data by applying the rotation angle directly on the projection data so that images were rotated at arbitrary angles without introducing additional bias. A large number of paired low- and high-quality images from the same patient were reconstructed and paired for training the ST_CNN model.

Results

No significant difference was found between the ST_CNN and conventional CNN models in terms of the peak signal-to-noise ratio and structural similarity index measure. The ST_CNN model outperformed the conventional CNN model in terms of noise texture and homogeneity in liver parenchyma as well as better subjective visualization of liver lesions. The ST_CNN may sacrifice the sharpness of vessels slightly compared to the conventional CNN model but without affecting the visibility of peripheral vessels or diagnosis of vascular pathology.

Conclusions

The proposed ST_CNN method trained from the data itself may achieve similar image quality in comparison with conventional deep CNN denoising methods pre-trained on external datasets.

Clinical applications of artificial intelligence in liver imaging

This review outlines the current status and challenges of the clinical applications of artificial intelligence in liver imaging using computed tomography or magnetic resonance imaging based on a topic analysis of PubMed search results using latent Dirichlet allocation. LDA revealed that "segmentation," "hepatocellular carcinoma and radiomics," "metastasis," "fibrosis," and "reconstruction" were current main topic keywords. Automatic liver segmentation technology using deep learning is beginning to assume new clinical significance as part of whole-body composition analysis. It has also been applied to the screening of large populations and the acquisition of training data for machine learning models and has resulted in the development of imaging biomarkers that have a significant impact on important clinical issues, such as the estimation of liver fibrosis, recurrence, and prognosis of malignant tumors. Deep learning reconstruction is expanding as a new technological clinical application of artificial intelligence and has shown results in reducing contrast and radiation doses. However, there is much missing evidence, such as external validation of machine learning models and the evaluation of the diagnostic performance of specific diseases using deep learning reconstruction, suggesting that the clinical application of these technologies is still in development.

Artificial Intelligence in CT and MR Imaging for Oncological Applications

Cancer care increasingly relies on imaging for patient management. The two most common cross-sectional imaging modalities in oncology are computed tomography (CT) and magnetic resonance imaging (MRI), which provide high-resolution anatomic and physiological imaging. Herewith is a summary of recent applications of rapidly advancing artificial intelligence (AI) in CT and MRI oncological imaging that addresses the benefits and challenges of the resultant opportunities with examples. Major challenges remain, such as how best to integrate AI developments into clinical radiology practice, the vigorous assessment of quantitative CT and MR imaging data accuracy, and reliability for clinical utility and research integrity in oncology. Such challenges necessitate an evaluation of the robustness of imaging biomarkers to be included in AI developments, a culture of data sharing, and the cooperation of knowledgeable academics with vendor scientists and companies operating in radiology and oncology fields. Herein, we will illustrate a few challenges and solutions of these efforts using novel methods for synthesizing different contrast modality images, auto-segmentation, and image reconstruction with examples from lung CT as well as abdome, pelvis, and head and neck MRI. The imaging community must embrace the need for quantitative CT and MRI metrics beyond lesion size measurement. AI methods for the extraction and longitudinal tracking of imaging metrics from registered lesions and understanding the tumor environment will be invaluable for interpreting disease status and treatment efficacy. This is an exciting time to work together to move the imaging field forward with narrow AI-specific tasks. New AI developments using CT and MRI datasets will be used to improve the personalized management of cancer patients.

Impact of deep learning image reconstruction algorithms on CT radiomic features in patients with liver tumors

Objective

To evaluate the impact of deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-Veo (ASIR-V) on abdominal CT radiomic features acquired in portal venous phase in liver tumor patients.

Methods

Sixty patients with liver tumors who underwent contrast-enhanced abdominal CT were retrospectively enrolled. Six groups including filtered back projection (FBP), ASIR-V (30%, 70%) and DLIR at low (DLIR-L), medium (DLIR-M and high (DLIR-H), were reconstructed using portal venous phase data. CT-based radiomic features (first-order, texture and wavelet features) were extracted from 2D and 3D liver tumors, peritumor and liver parenchyma. All features were analyzed for comparison. P &lt; 0.05 indicated statistically different. The consistency of 3D lesion feature extraction was assessed by calculating intraclass correlation coefficient (ICC).

Results

Different reconstruction algorithms influenced most radiomic features. The percentages of first-order, texture and wavelet features without statistical difference among 2D and 3D lesions, peritumor and liver parenchyma for all six groups were 27.78% (5/18), 5.33% (4/75) and 5.56% (1/18), respectively (all p &gt; 0.05), and they decreased while the level of reconstruction strengthened for both ASIR-V and DLIR. Compared with FBP, the features of ASIR-V30% and 70% without statistical difference decreased from 71.31% to 23.95%, and DLIR-L, DLIR-M, and DLIR-H decreased from 31.65% to 27.11% and 23.73%. Among texture features, unaffected features of peritumor were larger than those of lesions and liver parenchyma, and unaffected 3D lesions features were larger than those of 2D lesions. The consistency of 3D lesion first-order features was excellent, with intra- and inter-observer ICCs ranging from 0.891 to 0.999 and 0.880 to 0.998.

Conclusions

Both ASIR-V and DLIR algorithms with different strengths influenced the radiomic features of abdominal CT images in portal venous phase, and the influences aggravated as reconstruction strength increased.

Deep Learning Image Reconstruction for CT: Technical Principles and Clinical Prospects

Filtered back projection (FBP) has been the standard CT image reconstruction method for 4 decades. A simple, fast, and reliable technique, FBP has delivered high-quality images in several clinical applications. However, with faster and more advanced CT scanners, FBP has become increasingly obsolete. Higher image noise and more artifacts are especially noticeable in lower-dose CT imaging using FBP. This performance gap was partly addressed by model-based iterative reconstruction (MBIR). Yet, its "plastic" image appearance and long reconstruction times have limited widespread application. Hybrid iterative reconstruction partially addressed these limitations by blending FBP with MBIR and is currently the state-of-the-art reconstruction technique. In the past 5 years, deep learning reconstruction (DLR) techniques have become increasingly popular. DLR uses artificial intelligence to reconstruct high-quality images from lower-dose CT faster than MBIR. However, the performance of DLR algorithms relies on the quality of data used for model training. Higher-quality training data will become available with photon-counting CT scanners. At the same time, spectral data would greatly benefit from the computational abilities of DLR. This review presents an overview of the principles, technical approaches, and clinical applications of DLR, including metal artifact reduction algorithms. In addition, emerging applications and prospects are discussed.

Iterative Reconstruction: State-of-the-Art and Future Perspectives

ABSTRACT

Image reconstruction processing in computed tomography (CT) has evolved tremendously since its creation, succeeding at optimizing radiation dose while maintaining adequate image quality. Computed tomography vendors have developed and implemented various technical advances, such as automatic noise reduction filters, automatic exposure control, and refined imaging reconstruction algorithms.Focusing on imaging reconstruction, filtered back-projection has represented the standard reconstruction algorithm for over 3 decades, obtaining adequate image quality at standard radiation dose exposures. To overcome filtered back-projection reconstruction flaws in low-dose CT data sets, advanced iterative reconstruction algorithms consisting of either backward projection or both backward and forward projections have been developed, with the goal to enable low-dose CT acquisitions with high image quality. Iterative reconstruction techniques play a key role in routine workflow implementation (eg, screening protocols, vascular and pediatric applications), in quantitative CT imaging applications, and in dose exposure limitation in oncologic patients.Therefore, this review aims to provide an overview of the technical principles and the main clinical application of iterative reconstruction algorithms, focusing on the strengths and weaknesses, in addition to integrating future perspectives in the new era of artificial intelligence.

Improved image quality with deep learning reconstruction - a study on a semi-anthropomorphic upper-abdomen phantom

Purpose

To assess image quality of a deep learning reconstruction (DLR) algorithm across dose levels using a semi-anthropomorphic upper-abdominal phantom, and compare with filtered back projection (FBP) and hybrid iterative reconstruction (IR).

Material and methods

CT scans obtained at five dose levels (CTDIvol 5, 10, 15, 20 and 25 mGy) were reconstructed with FBP, hybrid IR (IR50, IR70 and IR90) and DLR of low (DLL), medium (DLM) and high strength (DLH) in 0.625 mm and 2.5 mm slices. CT number, homogeneity, noise, contrast, contrast-to-noise ratio (CNR), noise texture deviation (NTD; a measure of IR-specific artifacts), noise power spectrum (NPS) and task-based transfer function (TTF) were compared between reconstruction algorithms.

Results

CT numbers were highly consistent across reconstruction algorithms. Image noise was significantly reduced with higher levels of DLR. Noise texture (NPS and NTD) was with DLR maintained at comparable levels to FBP, contrary to increasing levels of hybrid IR. Images reconstructed with DLR of low and high strength in 0.625 mm slices showed similar noise characteristics to 2.5 mm slice FBP and IR50, respectively. Dose-reduction potential based on image noise with IR50 as reference was estimated to 35% for DLM and 74% for DLH.

Conclusions

The novel DLR algorithm demonstrates robust noise reduction with maintained noise texture characteristics despite higher algorithm strength, and may have overcome important limitations of IR. There may be potential for dose reduction and additional benefit from thin-slice reconstruction.