Performance of clinically available deep learning image reconstruction in computed tomography: a phantom study

Kawashima, Hiroki; Ichikawa, Katsuhiro; Takata, Takushi; Mitsui, Wataru; Ueta, Hiroshi; Yoneda, Norihide; Kobayashi, Satoshi

doi:10.1117/1.jmi.7.6.063503

Cited by 11 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to the basic noise characteristics measured in the uniform region, the f ave values of TF were almost comparable to those of FBP. Several reports have shown that the TF images had overall favorable noise characteristics, so that image noise was reduced without impacting the noise texture 6,9–11 . Our results were consistent with these previous reports.…”

Section: Discussionsupporting

confidence: 92%

Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background: Two deep learning image reconstruction (DLIR) techniques from two different computed tomography (CT) vendors have recently been introduced into clinical practice.Purpose: To characterize the noise properties of two DLIR techniques with different training methods, using a phantom containing a simple uniform and a complex non-uniform region. Methods: A water-bath phantom with a diameter of 300 mm was used as a base phantom. A textured phantom with a diameter of 128 mm, which was made of two materials, one equivalent to water and the other being 12 mg/ml diluted iodine, irregularly mixed to create a complex texture (non-uniform region), was placed in the base phantom. Thirty repeated phantom scans were performed using two CT scanners (Revolution CT with Apex Edition, GE Healthcare; Aquilion One PRISM Edition, Canon Medical Systems) at two dose levels (CT dose index: 5 and 15 mGy). Images were reconstructed with each CT system's filtered back projection (FBP) and DLIR [TrueFidelity (TF), GE Healthcare; Advanced intelligent Clear-IQ Engine Body Sharp (AC), Canon Medical Systems] for three process strengths. For basic characteristics of noise, the standard deviation (SD) and noise power spectrum (NPS) were measured for the uniform (water) region.A noise magnitude map was generated by calculating the inter-image SD at each pixel position across the 30 images. Then, a noise reduction map (NRM), which visualizes the relative differences in noise magnitude between FBP and DLIR, was calculated. The NRM values ranged from 0.0 to 1.0. A low NRM value represents a less aggressive noise reduction. The histograms of the NRM value were analyzed for the uniform and non-uniform regions. Results:The reduction in noise magnitude compared with FBP tended to be greater with AC (45%-85%) than with TF (32%-65%). The average NPS frequencies of TF and AC were almost comparable to those of FBP, except for the low-dose condition and the high noise reduction strength for AC. The NRM values of TF and AC were higher in the uniform region than in the non-uniform region. In the non-uniform region, TF's average NRM values (0.21-0.48) tended to be lower than AC's (0.39-0.78). The histograms for TF showed a small overlap between the uniform and the non-uniform regions; in contrast, those for AC showed a greater overlap. This difference seems to indicate that TF processes the uniform and non-uniform regions more differently than AC does. Conclusion:This study has revealed a distinct difference in characteristics between the two DLIR techniques:TF tends to offer less aggressive noise reduction in non-uniform regions and preserve the original signals, whereas AC tends

show abstract

Section: Discussionsupporting

confidence: 92%

Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first studies carried out on phantoms and patients with these two DLR algorithms have already demonstrated their contribution for improving image quality and their strong potential for dose reduction 4–26 . Compared to IR algorithms, they reduce image noise whilst improving the contrast‐to‐noise ratio, which improves lesion detectability and diagnostic confidence 5,6,19,20 .…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2022

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

“…AiCE uses high‐quality MBIR patient datasets and TrueFidelity high‐quality filtered back‐projection phantom and patient datasets. Many studies on phantoms and patients have demonstrated the image quality capabilities and dose reduction opportunities of the first versions of these two algorithms 3,10,12,15–17,19–23,25–32 …”

Section: Introductionmentioning

confidence: 99%

Comparison of two versions of a deep learning image reconstruction algorithm on CT image quality and dose reduction: A phantom study

et al. 2021

View full text Add to dashboard Cite

Purpose To compare the impact on CT image quality and dose reduction of two versions of a Deep Learning Image Reconstruction algorithm. Material and methods Acquisitions on the CT ACR 464 phantom were performed at five dose levels (CTDIvol: 10/7.5/5/2.5/1 mGy) using chest or abdomen pelvis protocol parameters. Raw data were reconstructed using the filtered‐back projection (FBP), the enhanced level of AIDR 3D (AIDR 3De), and the three levels of AiCE (Mild, Standard, and Strong) for the two versions (AiCE V8 vs AiCE V10). The noise power spectrum (NPS) and task‐based transfer function (TTF) for bone (high‐contrast insert) and acrylic (low‐contrast insert) inserts were computed. To quantify the changes of noise magnitude and texture, the square root of the area under the NPS curve and the average spatial frequency (fav) of the NPS curve were measured. The detectability index (d’) was computed to model the detectability of either a large mass in the liver or lung, or a small calcification or high contrast tissue boundaries. Results The noise magnitude was lower with both AiCE versions than with AIDR 3De. The noise magnitude was lower with AiCE V10 than with AiCE V8 (‐4 ± 6% for Mild, ‐13 ± 3% for Standard, and ‐48 ± 0% for Strong levels). fav and TTF50% values for both inserts shifted towards higher frequencies with AiCE than with AIDR 3De. Compared to AiCE V08, fav shifted towards higher frequencies with AiCE V10 (45 ± 4%, 36 ± 3%, and 5 ± 4% for all levels, respectively). The TTF50% values shifted towards higher frequencies with AiCE V10 as compared with AiCE V8 for both inserts, except for the Strong level for the acrylic insert. Whatever the dose and AiCE levels, d’ values were higher with AiCE V10 than with AiCE V8 for the small object/calcification and for the large object/lesion. Conclusion As compared to AIDR 3De, lower noise magnitude and higher spatial resolution and detectability index were found with both versions of AiCE. As compared to AiCE V8, AiCE V10 reduced noise and improved spatial resolution and detectability without changing the noise texture in a simple geometric phantom, except for the Strong level. AiCE V10 seems to have a greater potential for dose reduction than AiCE V8.

show abstract

Performance of clinically available deep learning image reconstruction in computed tomography: a phantom study

Cited by 11 publications

References 31 publications

Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection

Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection

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

Comparison of two versions of a deep learning image reconstruction algorithm on CT image quality and dose reduction: A phantom study

Contact Info

Product

Resources

About