Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data

Greffier, Joël; Frandon, Julien; Si‐Mohamed, Salim; Dabli, Djamel; Hamard, Aymeric; Belaouni, Asmaa; Akessoul, Philippe; Besse, F.; Guiu, Boris; Beregi, Jean‐Paul

doi:10.1016/j.diii.2021.08.001

Cited by 47 publications

(36 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the f av was higher than iDose 4 level 4 for all levels except for the Smoother level. Lastly, the noise variations between this algorithm and the iterative algorithm usually used in clinical routine were different from those found in the literature, with the other two DLR algorithms 9,11–13,15,23,25 . Indeed, with TrueFidelity and AiCE, the noise was lower compared to ASIR‐V 50% and AIDR‐3D Enhanced, respectively, and this was more so as the strength level of each algorithm increased.…”

Section: Discussionmentioning

confidence: 59%

“…Lastly, the noise variations between this algorithm and the iterative algorithm usually used in clinical routine were different from those found in the literature, with the other two DLR algorithms. 9,[11][12][13]15,23,25 Indeed, with TrueFidelity and AiCE, the noise was lower compared to ASIR-V 50% and AIDR-3D Enhanced, respectively, and this was more so as the strength level of each algorithm increased. With TrueFidelity, the f av values were higher than ASIR-V 50% and the difference increased with the level.…”

Section: Discussionmentioning

confidence: 98%

“…No articles or reports have yet been published to describe the iQMetrix-CT software; however, this software has been used in various studies. 11,12,30…”

Section: Task-based Image Quality Assessment-acr Geometric Phantommentioning

confidence: 99%

“…To use the same process than for the TTF calculation, the NPS was computed in 250 consecutive axial slices (50 slices for each of the 5 acquisitions) by placing 4 square regions of interest (ROIs) of 128 × 128 pixels (Figure 1a) using the same methodology as previously reported. 11,12,30 In the iQMetrix-CT software, the raw data NPS1D curves are fitted using an 11th-order polynomial.…”

Section: Noise Power Spectrummentioning

confidence: 99%

“…Two senior chest radiologists (12 and 8 years of experience) were read in consensus the chest images of the anthropomorphic phantom. 10,12 For each set of images, the radiologists read all the axial chest images randomly and were blinded to the reconstruction type (algorithm and levels) and dose level. They were instructed to subjectively assess image noise, image smoothing, and contrast between the vessels and fat in the mediastinum for mediastinal images and for visual border detection between bronchus and lung parenchyma for parenchymal images using a commonly used four-or five-point scale.…”

Section: Subjective Image Quality Assessment On An Anthropomorphic Ph...mentioning

confidence: 99%

See 4 more Smart Citations

Impact of an artificial intelligence deep‐learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Recently, computed tomography (CT) manufacturers have developed deep‐learning‐based reconstruction algorithms to compensate for the limitations of iterative reconstruction (IR) algorithms, such as image smoothing and the spatial resolution's dependence on contrast and dose levels. Purpose To assess the impact of an artificial intelligence deep‐learning reconstruction (AI‐DLR) algorithm on image quality and dose reduction compared with a hybrid IR algorithm in chest CT for different clinical indications. Methods Acquisitions on the CT American College of Radiology (ACR) 464 and CT Torso CTU‐41 phantoms were performed at five dose levels (CTDIvol: 9.5/7.5/6/2.5/0.4 mGy) used for chest CT conditions. Raw data were reconstructed using filtered backprojection, two levels of IR (iDose4 levels 4 (i4) and 7 (i7)), and five levels of AI‐DLR (Precise Image; Smoother, Smooth, Standard, Sharp, Sharper). Noise power spectrum (NPS), task‐based transfer function, and detectability index (d′) were computed: d′‐modeled detection of a soft tissue mediastinal nodule (low‐contrast soft tissue chest nodule within the mediastinum [LCN]), ground‐glass opacity (GGO), or high‐contrast pulmonary (HCP) lesion. The subjective image quality of chest anthropomorphic phantom images was independently evaluated by two radiologists. They assessed image noise, image smoothing, contrast between vessels and fat in the mediastinum for mediastinal images, visual border detection between bronchus and lung parenchyma for parenchymal images, and overall image quality using a commonly used four‐ or five‐point scale. Results From Standard to Smoother levels, on average, the noise magnitude decreased (for all dose levels: −66.3% ± 0.5% for mediastinal images and −63.1% ± 0.1% for parenchymal images), the average NPS spatial frequency decreased (for all dose levels: −35.3% ± 2.2% for mediastinal images and −13.3% ± 2.2% for parenchymal images), and the detectability (d′) of the three lesions increased. The opposite pattern was found from Standard to Sharper levels. From Smoother to Sharper levels, the spatial resolution increased for the low‐contrast polyethylene insert and the opposite for the high‐contrast air insert. Compared to the i4 used in clinical practice, d′ values were higher using Smoother (mean for all dose levels: 338.7% ± 29.4%), Smooth (103.4% ± 11.2%), and Standard (34.1% ± 6.6%) levels for the LCN on mediastinal images and Smoother (169.5% ± 53.2% for GGO and 136.9% ± 1.6% for HCP) and Smooth (36.4% ± 22.1% and 24.1% ± 0.9%, respectively) levels for parenchymal images. Radiologists considered the images satisfactory for clinical use at these levels, but adaptation to the dose level of the protocol is required. Conclusion With AI‐DLR, the smoothest levels reduced the noise and improved the detectability of chest lesions but increased the image smoothing. The opposite was found with the sharpest levels. The choice of level depends on the dose level and type of image: mediastinal or parenchymal.

show abstract

Section: Discussionmentioning

confidence: 59%

Section: Discussionmentioning

confidence: 98%

“…No articles or reports have yet been published to describe the iQMetrix-CT software; however, this software has been used in various studies. 11,12,30…”

Section: Task-based Image Quality Assessment-acr Geometric Phantommentioning

confidence: 99%

Section: Noise Power Spectrummentioning

confidence: 99%

Section: Subjective Image Quality Assessment On An Anthropomorphic Ph...mentioning

confidence: 99%

See 3 more Smart Citations

Impact of an artificial intelligence deep‐learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

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

et al. 2023

View full text Add to dashboard Cite

Improved image quality and dose reduction in abdominal CT with deep-learning reconstruction algorithm: a phantom study

Greffier

Durand²,

Frandon³

et al. 2022

Eur Radiol

View full text Add to dashboard Cite

Comparison of two deep learning image reconstruction algorithms in chest CT images: A task-based image quality assessment on phantom data

Cited by 47 publications

References 28 publications

Impact of an artificial intelligence deep‐learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study

Impact of an artificial intelligence deep‐learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study

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

Improved image quality and dose reduction in abdominal CT with deep-learning reconstruction algorithm: a phantom study

Contact Info

Product

Resources

About