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

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

PURPOSE

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

MATERIALS AND METHODS

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

RESULTS

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

CONCLUSIONS

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

Transferring U-Net between low-dose CT denoising tasks: a validation study with varied spatial resolutions

Background

Recently, deep learning techniques have been widely used in low-dose computed tomography (LDCT) imaging applications for quickly generating high quality computed tomography (CT) images at lower radiation dose levels. The purpose of this study is to validate the reproducibility of the denoising performance of a given network that has been trained in advance across varied LDCT image datasets that are acquired from different imaging systems with different spatial resolutions.

Methods

Specifically, LDCT images with comparable noise levels but having different spatial resolutions were prepared to train the U-Net. The number of CT images used for the network training, validation and test was 2,400, 300 and 300, respectively. Afterwards, self- and cross-validations among six selected spatial resolutions (62.5, 125, 250, 375, 500, 625 µm) were studied and compared side by side. The residual variance, peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE) and structural similarity (SSIM) were measured and compared. In addition, network retraining on a small number of image set was performed to fine tune the performance of transfer learning among LDCT tasks with varied spatial resolutions.

Results

Results demonstrated that the U-Net trained upon LDCT images having a certain spatial resolution can effectively reduce the noise of the other LDCT images having different spatial resolutions. Regardless, results showed that image artifacts would be generated during the above cross validations. For instance, noticeable residual artifacts were presented at the margin and central areas of the object as the resolution inconsistency increased. The retraining results showed that the artifacts caused by the resolution mismatch can be greatly reduced by utilizing about only 20% of the original training data size. This quantitative improvement led to a reduction in the NRMSE from 0.1898 to 0.1263 and an increase in the SSIM from 0.7558 to 0.8036.

Conclusions

In conclusion, artifacts would be generated when transferring the U-Net to a LDCT denoising task with different spatial resolution. To maintain the denoising performance, it is recommended to retrain the U-Net with a small amount of datasets having the same target spatial resolution.

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

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

Improved Diagnosis of Adjacent Organ Invasion of Extrahepatic Cholangiocarcinoma by Adding Arterial and Delayed Phases

PURPOSE

To clarify the role of dynamic computed tomography (CT) in diagnosing extrahepatic cholangiocarcinoma (eCCA) involving adjacent organs.

MATERIAL AND METHODS

We retrospectively analyzed patients diagnosed with eCCA in Iwate Medical University Hospital (Morioka, Japan) during January 2011-December 2021 who underwent dynamic contrast-enhanced CT before biliary intervention, surgery, or chemotherapy. For surgical cases, two radiologists independently reviewed CT images in the portal, dual (adding arterial phase), and triple (adding delayed phase) phases. The mean attenuations of the abdominal aorta, portal vein (PV), hepatic parenchyma, pancreatic parenchyma, and eCCA were measured. The biliary segment-wise longitudinal tumour extent, arterial and PV invasion, organ invasion (liver, pancreas, and duodenum), and regional lymph node metastasis were assessed on a five-point scale. Image performances were compared using the sensitivity, specificity, and area under the curve (AUC).

RESULTS

We included 120 patients (mean age, 71.7 ± 8.9; 84 males). The PV and liver differed most from the bile duct tumour in the portal phase. The abdominal aorta and pancreas differed most from eCCA in the arterial phase. For 80 patients evaluated on the five-point scale, adding phases increased the AUC for pancreatic, duodenal, and arterial invasion for each observer (observer 1, 0.79-0.93, p<0.01, 0.71-0.86, p = 0.04, 0.74-0.99, p = 0.02; observer 2, 0.88-0.96, p = 0.01, 0.73-0.94, p<0.01, 0.80-0.99 p = 0.04; respectively). The AUC for biliary segment-wise longitudinal tumor extent, hepatic, and PV invasion remained unchanged with additional phases.

CONCLUSIONS

Portal-phase information is sufficient to evaluate the segmental extent of bile duct and liver/PV invasion. Arterial- and delayed-phase information can help evaluate pancreatic, duodenal, and arterial invasion.

Implementation of AI image reconstruction in CT-how is it validated and what dose reductions can be achieved

CT reconstruction has undergone a substantial change over the last decade with the introduction of iterative reconstruction (IR) and now with deep learning reconstruction (DLR). In this review, DLR will be compared to IR and filtered back-projection (FBP) reconstructions. Comparisons will be made using image quality metrics such as noise power spectrum, contrast-dependent task-based transfer function, and non-prewhitening filter detectability index (dNPW'). Discussion on how DLR has impacted CT image quality, low-contrast detectability, and diagnostic confidence will be provided. DLR has shown the ability to improve in areas that IR is lacking, namely: noise magnitude reduction does not alter noise texture to the degree that IR did, and the noise texture found in DLR is more aligned with noise texture of an FBP reconstruction. Additionally, the dose reduction potential for DLR is shown to be greater than IR. For IR, the consensus was dose reduction should be limited to no more than 15-30% to preserve low-contrast detectability. For DLR, initial phantom and patient observer studies have shown acceptable dose reduction between 44 and 83% for both low- and high-contrast object detectability tasks. Ultimately, DLR is able to be used for CT reconstruction in place of IR, making it an easy "turnkey" upgrade for CT reconstruction. DLR for CT is actively being improved as more vendor options are being developed and current DLR options are being enhanced with second generation algorithms being released. DLR is still in its developmental early stages, but is shown to be a promising future for CT reconstruction.

Deep Learning-Based Versus Iterative Image Reconstruction for Unenhanced Brain CT: A Quantitative Comparison of Image Quality

This exploratory retrospective study aims to quantitatively compare the image quality of unenhanced brain computed tomography (CT) reconstructed with an iterative (AIDR-3D) and a deep learning-based (AiCE) reconstruction algorithm. After a preliminary phantom study, AIDR-3D and AiCE reconstructions (0.5 mm thickness) of 100 consecutive brain CTs acquired in the emergency setting on the same 320-detector row CT scanner were retrospectively analyzed, calculating image noise reduction attributable to the AiCE algorithm, artifact indexes in the posterior cranial fossa, and contrast-to-noise ratios (CNRs) at the cortical and thalamic levels. In the phantom study, the spatial resolution of the two datasets proved to be comparable; conversely, AIDR-3D reconstructions showed a broader noise pattern. In the human study, median image noise was lower with AiCE compared to AIDR-3D (4.7 vs. 5.3, p < 0.001, median 19.6% noise reduction), whereas AIDR-3D yielded a lower artifact index than AiCE (7.5 vs. 8.4, p < 0.001). AiCE also showed higher median CNRs at the cortical (2.5 vs. 1.8, p < 0.001) and thalamic levels (2.8 vs. 1.7, p < 0.001). These results highlight how image quality improvements granted by deep learning-based (AiCE) and iterative (AIDR-3D) image reconstruction algorithms vary according to different brain areas.

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.

Computed Tomography 2.0: New Detector Technology, AI, and Other Developments

ABSTRACT

Computed tomography (CT) dramatically improved the capabilities of diagnostic and interventional radiology. Starting in the early 1970s, this imaging modality is still evolving, although tremendous improvements in scan speed, volume coverage, spatial and soft tissue resolution, as well as dose reduction have been achieved. Tube current modulation, automated exposure control, anatomy-based tube voltage (kV) selection, advanced x-ray beam filtration, and iterative image reconstruction techniques improved image quality and decreased radiation exposure. Cardiac imaging triggered the demand for high temporal resolution, volume acquisition, and high pitch modes with electrocardiogram synchronization. Plaque imaging in cardiac CT as well as lung and bone imaging demand for high spatial resolution. Today, we see a transition of photon-counting detectors from experimental and research prototype setups into commercially available systems integrated in patient care. Moreover, with respect to CT technology and CT image formation, artificial intelligence is increasingly used in patient positioning, protocol adjustment, and image reconstruction, but also in image preprocessing or postprocessing. The aim of this article is to give an overview of the technical specifications of up-to-date available whole-body and dedicated CT systems, as well as hardware and software innovations for CT systems in the near future.