Dataset Information

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

ABSTRACT:

Purpose

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

Methods

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

Results

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

Conclusion

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

SUBMITTER: Alagic Z

PROVIDER: S-EPMC8917108 | biostudies-literature | 2022 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Alagic Zlatan Z Diaz Cardenas Jacqueline J Halldorsson Kolbeinn K Grozman Vitali V Wallgren Stig S Suzuki Chikako C Helmenkamp Johan J Koskinen Seppo K SK

Emergency radiology 20220105 2

<h4>Purpose</h4>To compare the image quality between a deep learning-based image reconstruction algorithm (DLIR) and an adaptive statistical iterative reconstruction algorithm (ASiR-V) in noncontrast trauma head CT.<h4>Methods</h4>Head CT scans from 94 consecutive trauma patients were included. Images were reconstructed with ASiR-V 50% and the DLIR strengths: low (DLIR-L), medium (DLIR-M), and high (DLIR-H). The image quality was assessed quantitatively and qualitatively and compared between the ...[more]

PMID: 34984574

Similar Datasets

Project description:ObjectivesTo 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 methodsOncologic 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.ResultsFifty 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%.ConclusionsDLIR 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 statementDeep 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.

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 compare a deep learning-based reconstruction (DLR) algorithm for pediatric abdominopelvic computed tomography (CT) with filtered back projection (FBP) and iterative reconstruction (IR) algorithms.Materials and methodsPost-contrast abdominopelvic CT scans obtained from 120 pediatric patients (mean age ± standard deviation, 8.7 ± 5.2 years; 60 males) between May 2020 and October 2020 were evaluated in this retrospective study. Images were reconstructed using FBP, a hybrid IR algorithm (ASiR-V) with blending factors of 50% and 100% (AV50 and AV100, respectively), and a DLR algorithm (TrueFidelity) with three strength levels (low, medium, and high). Noise power spectrum (NPS) and edge rise distance (ERD) were used to evaluate noise characteristics and spatial resolution, respectively. Image noise, edge definition, overall image quality, lesion detectability and conspicuity, and artifacts were qualitatively scored by two pediatric radiologists, and the scores of the two reviewers were averaged. A repeated-measures analysis of variance followed by the Bonferroni post-hoc test was used to compare NPS and ERD among the six reconstruction methods. The Friedman rank sum test followed by the Nemenyi-Wilcoxon-Wilcox all-pairs test was used to compare the results of the qualitative visual analysis among the six reconstruction methods.ResultsThe NPS noise magnitude of AV100 was significantly lower than that of the DLR, whereas the NPS peak of AV100 was significantly higher than that of the high- and medium-strength DLR (p < 0.001). The NPS average spatial frequencies were higher for DLR than for ASiR-V (p < 0.001). ERD was shorter with DLR than with ASiR-V and FBP (p < 0.001). Qualitative visual analysis revealed better overall image quality with high-strength DLR than with ASiR-V (p < 0.001).ConclusionFor pediatric abdominopelvic CT, the DLR algorithm may provide improved noise characteristics and better spatial resolution than the hybrid IR algorithm.

Project description:Background GE Healthcare’s new generation of deep-learning image reconstruction (DLIR), the Revolution Apex CT is the first CT image reconstruction engine based on a deep neural network to be approved by the US Food and Drug Administration (FDA). It can generate high-quality CT images that restore the true texture with a low radiation dose. The aim of the present study was to assess the image quality of coronary CT angiography (CCTA) at 70 kVp with the DLIR algorithm as compared to the adaptive statistical iterative reconstruction-Veo (ASiR-V) algorithm in patients of different weight. Methods The study group comprised 96 patients who underwent CCTA examination at 70 kVp and were subdivided by body mass index (BMI) into normal-weight patients [48] and overweight patients [48]. ASiR-V40%, ASiR-V80%, DLIR-low, DLIR-medium, and DLIR-high images were obtained. The objective image quality, radiation dose, and subjective score of the two groups of images with different reconstruction algorithms were compared and statistically analyzed. Results In the overweight group, the noise of the DLIR image was lower than that of the routinely used ASiR-40%, and the contrast-to-noise ratio (CNR) of DLIR (H: 19.15±4.31; M: 12.68±2.91; L: 10.59±2.32) was higher than that of the ASiR-40% reconstructed image (8.39±1.46), with statistically significant differences (all P values <0.05). The subjective image quality evaluation of DLIR was significantly higher than that of ASiR-V reconstructed images (all P values <0.05), with the DLIR-H being the best. In a comparison of the normal-weight and overweight groups, the objective score of the ASiR-V-reconstructed image increased with increasing strength, but the subjective image evaluation decreased, and both differences (i.e., objective and subjective) were statistically significant (P<0.05). In general, the objective score of the DLIR reconstruction image between the two groups increased with increased noise reduction, and the DLIR-L image was the best. The difference between the two groups was statistically significant (P<0.05), but there was no significant difference in subjective image evaluation between the two groups. The effective dose (ED) of the normal-weight group and the overweight group was 1.36±0.42 and 1.59±0.46 mSv, respectively, and was significantly higher in the overweight group (P<0.05). Conclusions As the strength of the ASiR-V reconstruction algorithm increased, the objective image quality increased accordingly, but the high-strength ASiR-V changed the noise texture of the image, resulting in a decrease in the subjective score, which affected disease diagnosis. Compared with the ASiR-V reconstruction algorithm, the DLIR reconstruction algorithm improved the image quality and diagnostic reliability for CCTA in patients with different weights, especially in heavier patients.

Dataset Information

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

Purpose

Methods

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets