Dataset Information

Dose reduction potential of vendor-agnostic deep learning model in comparison with deep learning-based image reconstruction algorithm on CT: a phantom study.

ABSTRACT:

Objectives

To compare the dose reduction potential (DRP) of a vendor-agnostic deep learning model (DLM, ClariCT.AI) with that of a vendor-specific deep learning-based image reconstruction algorithm (DLR, TrueFidelity™).

Methods

Computed tomography (CT) images of a multi-sized image quality phantom (Mercury v4.0) were acquired under six radiation dose levels (0.48/0.97/1.93/3.87/7.74/15.47 mGy) and were reconstructed using filtered back projection (FBP) and three strength levels of the DLR (low/medium/high). The FBP images were denoised using the DLM. For all DLM and DLR images, the detectability index (d') (a task-based detection performance metric) was obtained, under various combinations of three target sizes (10/5/1 mm), five inlets (CT value difference with the background; -895/50/90/335/1000 HU), five phantom diameters (36/31/26/21/16 cm), and six radiation dose levels. Dose reduction potential (DRP) measures the dose reduction made by using DLM or DLR, while yielding d' equivalent to that of FBP at full dose.

Results

The DRPs of the DLM, DLR-low, DLR-medium, and DLR-high were 86% (81-88%), 60% (46-67%), 76% (60-81%), and 87% (78-92%), respectively. For 10-mm targets, the DRP of the DLM (87%) was higher than that of all DLR algorithms (58-86%). However, for smaller targets (5 mm/1 mm), the DRPs of the DLR-high (89/88%) were greater than those of the DLM (87/84%).

Conclusion

The dose reduction potential of the vendor-agnostic DLM was shown to be comparable to that of the vendor-specific DLR at high strength and superior to those of the DLRs at medium and low strengths.

Key points

• DRP of the vendor-agnostic model was comparable to that of high-strength vendor-specific model and superior to those of medium- and low-strength models. • Under various radiation dose levels, the deep learning model shows higher detectability indexes compared to FBP.

SUBMITTER: Choi H

PROVIDER: S-EPMC8364308 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Two novel methods of image reconstruction, xSPECT Quant (xQ) and xSPECT Bone (xB), that use an ordered subset conjugate gradient minimizer (OSCGM) for SPECT/CT reconstruction have been proposed. The present study compares the performance characteristics of xQ, xB, and conventional Flash3D (F3D) reconstruction using images derived from phantoms and patients. METHODS:A custom-designed body phantom for bone SPECT was scanned using a Symbia Intevo (Siemens Healthineers), and reconstructed xSPECT images were evaluated. The phantom experiments proceeded twice with different activity concentrations and sphere sizes. A phantom with 28-mm spheres containing a 99mTc-background and tumor-to-normal bone ratios (TBR) of 1, 2, 4, and 10 were generated, and convergence property against various TBR was evaluated across 96 iterations. A phantom with four spheres (13-, 17-, 22-, and 28-mm diameters), containing a 99mTc-background at TBR4, was also generated. The full width at half maximum of an imaged spinous process (10?mm), coefficients of variance (CV), contrast-to-noise ratio (CNR), and recovery coefficients (RC) were evaluated after reconstructing images of a spine using Flash 3D (F3D), xQ, and xB. We retrospectively analyzed images from 20 patients with suspected bone metastases (male, n = 13) which were acquired using [99mTc]Tc-(H)MDP SPECT/CT, then CV and standardized uptake values (SUV) at the 4th vertebral body (L4) were compared after xQ and xB reconstruction in a clinical setup. RESULTS:Mean activity concentrations with various TBR converged according to increasing numbers of iterations. The spatial resolution of xB was considerably superior to xQ and F3D, and it approached almost the actual size regardless of the iteration numbers during reconstruction. The CV and RC were better for xQ and xB than for F3D. The CNR peaked at 24 iterations for xQ and 48 iterations for F3D and xB, respectively. The RC between xQ and xB significantly differed at lower numbers of iterations but were almost equivalent at higher numbers of iterations. The reconstructed xQ and xB images of the clinical patients showed a significant difference in the SUVmax and SUVpeak. CONCLUSIONS:The reconstructed xQ and xB images were more accurate than those reconstructed conventionally using F3D. The xB for bone SPECT imaging offered essentially unchanged spatial resolution even when the numbers of iterations did not converge. The xB reconstruction further enhanced SPECT image quality using CT data. Our findings provide important information for understanding the performance characteristics of the novel xQ and xB algorithms.

Project description:ObjectiveTo assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction.Materials and methodsWe retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction).ResultsObjective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons.ConclusionApplication of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

Project description:ObjectiveTo assess the dose reduction potential of a calcium-aware reconstruction technique, which aims at tube voltage-independent computed tomography (CT) numbers for calcium.Methods and materialsA cardiothoracic phantom, mimicking three different patient sizes, was scanned with two calcium inserts (named D100 and CCI), containing calcifications varying in size and density. Tube voltage was varied both manually (range 70-150 and Sn100 kVp) and automatically. Tube current was automatically adapted to maintain reference image quality defined at 120 kVp. Data was reconstructed with the standard reconstruction technique (kernel Qr36) and the calcium-aware reconstruction technique (kernel Sa36). We assessed the radiation dose reduction potential (volumetric CT dose index values (CTDIvol)), noise (standard deviation (SD)), mean CT number (HU) of each calcification, and Agatston scores for varying kVp. Results were compared with the reference acquired at 120 kVp and reconstructed with Qr36.ResultsAutomatic selection of the optimal tube voltage resulted in a CTDIvol reduction of 22%, 15%, and 12% compared with the reference for the small, medium, and large phantom, respectively. CT numbers differed up to 64% for the standard reconstruction and 11% for the calcium-aware reconstruction. Similarly, Agatston scores deviated up to 40% and 8% for the standard and calcium-aware reconstruction technique, respectively.ConclusionCT numbers remained consistent with comparable calcium scores when the calcium-aware image reconstruction technique was applied with varying tube voltage. Less consistency was observed in small calcifications with low density. Automatic reduction of tube voltage resulted in a dose reduction of up to 22%.Key points• The calcium-aware image reconstruction technique allows for consistent CT numbers when varying the tube voltage. • Automatic reduction of tube voltage results in a reduced radiation exposure of up to 22%. • This study stresses the known limitations of the current Agatston score technique.

Project description:While the recent advancements of computed tomography (CT) technology have contributed in reducing radiation dose and image noise, an objective evaluation of image quality in patient scans has not yet been established. In this study, we present a patient-specific CT image quality evaluation method that includes fully automated measurements of noise level, structure sharpness, and alteration of structure. This study used the CT images of 120 patients from four different CT scanners reconstructed with three types of algorithm: filtered back projection (FBP), vendor-specific iterative reconstruction (IR), and a vendor-agnostic deep learning model (DLM, ClariCT.AI, ClariPi Inc.). The structure coherence feature (SCF) was used to divide an image into the homogeneous (RH) and structure edge (RS) regions, which in turn were used to localize the regions of interests (ROIs) for subsequent analysis of image quality indices. The noise level was calculated by averaging the standard deviations from five randomly selected ROIs on RH, and the mean SCFs on RS was used to estimate the structure sharpness. The structure alteration was defined by the standard deviation ratio between RS and RH on the subtraction image between FBP and IR or DLM, in which lower structure alterations indicate successful noise reduction without degradation of structure details. The estimated structure sharpness showed a high correlation of 0.793 with manually measured edge slopes. Compared to FBP, IR and DLM showed 34.38% and 51.30% noise reduction, 2.87% and 0.59% lower structure sharpness, and 2.20% and -12.03% structure alteration, respectively, on an average. DLM showed statistically superior performance to IR in all three image quality metrics. This study is expected to contribute to enhance the CT protocol optimization process by allowing a high throughput and quantitative image quality evaluation during the introduction or adjustment of lower-dose CT protocol into routine practice.

Project description:ObjectiveFew studies have explored the clinical feasibility of using deep-learning reconstruction to reduce the radiation dose of CT. We aimed to compare the image quality and lung nodule detectability between chest CT using a quarter of the low dose (QLD) reconstructed with vendor-agnostic deep-learning image reconstruction (DLIR) and conventional low-dose (LD) CT reconstructed with iterative reconstruction (IR).Materials and methodsWe retrospectively collected 100 patients (median age, 61 years [IQR, 53-70 years]) who received LDCT using a dual-source scanner, where total radiation was split into a 1:3 ratio. QLD CT was generated using a quarter dose and reconstructed with DLIR (QLD-DLIR), while LDCT images were generated using a full dose and reconstructed with IR (LD-IR). Three thoracic radiologists reviewed subjective noise, spatial resolution, and overall image quality, and image noise was measured in five areas. The radiologists were also asked to detect all Lung-RADS category 3 or 4 nodules, and their performance was evaluated using area under the jackknife free-response receiver operating characteristic curve (AUFROC).ResultsThe median effective dose was 0.16 (IQR, 0.14-0.18) mSv for QLD CT and 0.65 (IQR, 0.57-0.71) mSv for LDCT. The radiologists' evaluations showed no significant differences in subjective noise (QLD-DLIR vs. LD-IR, lung-window setting; 3.23 ± 0.19 vs. 3.27 ± 0.22; P = .11), spatial resolution (3.14 ± 0.28 vs. 3.16 ± 0.27; P = .12), and overall image quality (3.14 ± 0.21 vs. 3.17 ± 0.17; P = .15). QLD-DLIR demonstrated lower measured noise than LD-IR in most areas (P < .001 for all). No significant difference was found between QLD-DLIR and LD-IR for the sensitivity (76.4% vs. 72.2%; P = .35) or the AUFROCs (0.77 vs. 0.78; P = .68) in detecting Lung-RADS category 3 or 4 nodules. Under a noninferiority limit of -0.1, QLD-DLIR showed noninferior detection performance (95% CI for AUFROC difference, -0.04 to 0.06).ConclusionQLD-DLIR images showed comparable image quality and noninferior nodule detectability relative to LD-IR images.