Image quality in liver CT: low-dose deep learning vs standard-dose model-based iterative reconstructions

2021 ◽  
Author(s):  
Sungeun Park ◽  
Jeong Hee Yoon ◽  
Ijin Joo ◽  
Mi Hye Yu ◽  
Jae Hyun Kim ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Low Dose ◽  
Standard Dose ◽  
Liver Ct ◽  
Model Based ◽  
Dose Model

Low-dose whole-body CT using deep learning image reconstruction: image quality and lesion detection

2021 ◽  
Vol 94 (1121) ◽  
pp. 20201329
Author(s):  
Yoshifumi Noda ◽  
Tetsuro Kaga ◽  
Nobuyuki Kawai ◽  
Toshiharu Miyoshi ◽  
Hiroshi Kawada ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Low Dose ◽  
Standard Dose ◽  
Lesion Detection ◽  
Whole Body ◽  
Hybrid Iterative Reconstruction ◽  
Whole Body Ct ◽  
Attenuation Values

Objectives: To evaluate image quality and lesion detection capabilities of low-dose (LD) portal venous phase whole-body computed tomography (CT) using deep learning image reconstruction (DLIR). Methods: The study cohort of 59 consecutive patients (mean age, 67.2 years) who underwent whole-body LD CT and a prior standard-dose (SD) CT reconstructed with hybrid iterative reconstruction (SD-IR) within one year for surveillance of malignancy were assessed. The LD CT images were reconstructed with hybrid iterative reconstruction of 40% (LD-IR) and DLIR (LD-DLIR). The radiologists independently evaluated image quality (5-point scale) and lesion detection. Attenuation values in Hounsfield units (HU) of the liver, pancreas, spleen, abdominal aorta, and portal vein; the background noise and signal-to-noise ratio (SNR) of the liver, pancreas, and spleen were calculated. Qualitative and quantitative parameters were compared between the SD-IR, LD-IR, and LD-DLIR images. The CT dose-index volumes (CTDIvol) and dose-length product (DLP) were compared between SD and LD scans. Results: The image quality and lesion detection rate of the LD-DLIR was comparable to the SD-IR. The image quality was significantly better in SD-IR than in LD-IR (p < 0.017). The attenuation values of all anatomical structures were comparable between the SD-IR and LD-DLIR (p = 0.28–0.96). However, background noise was significantly lower in the LD-DLIR (p < 0.001) and resulted in improved SNRs (p < 0.001) compared to the SD-IR and LD-IR images. The mean CTDIvol and DLP were significantly lower in the LD (2.9 mGy and 216.2 mGy•cm) than in the SD (13.5 mGy and 1011.6 mGy•cm) (p < 0.0001). Conclusion: LD CT images reconstructed with DLIR enable radiation dose reduction of >75% while maintaining image quality and lesion detection rate and superior SNR in comparison to SD-IR. Advances in knowledge: Deep learning image reconstruction algorithm enables around 80% reduction in radiation dose while maintaining the image quality and lesion detection compared to standard-dose whole-body CT.

Evaluation of an iterative model-based reconstruction of pediatric abdominal CT with regard to image quality and radiation dose

2017 ◽  
Vol 59 (6) ◽  
pp. 740-747
Author(s):  
Marie-Louise Aurumskjöld ◽  
Marcus Söderberg ◽  
Fredrik Stålhammar ◽  
Kristina Vult von Steyern ◽  
Anders Tingberg ◽  
...  
Keyword(s):  
Image Quality ◽  
Radiation Dose ◽  
Iterative Reconstruction ◽  
Low Dose ◽  
Pediatric Patients ◽  
Standard Dose ◽  
Reconstruction Method ◽  
Abdominal Ct ◽  
Model Based ◽  
Iterative Model

Background In pediatric patients, computed tomography (CT) is important in the medical chain of diagnosing and monitoring various diseases. Because children are more radiosensitive than adults, they require minimal radiation exposure. One way to achieve this goal is to implement new technical solutions, like iterative reconstruction. Purpose To evaluate the potential of a new, iterative, model-based method for reconstructing (IMR) pediatric abdominal CT at a low radiation dose and determine whether it maintains or improves image quality, compared to the current reconstruction method. Material and Methods Forty pediatric patients underwent abdominal CT. Twenty patients were examined with the standard dose settings and 20 patients were examined with a 32% lower radiation dose. Images from the standard examination were reconstructed with a hybrid iterative reconstruction method (iDose4), and images from the low-dose examinations were reconstructed with both iDose4 and IMR. Image quality was evaluated subjectively by three observers, according to modified EU image quality criteria, and evaluated objectively based on the noise observed in liver images. Results Visual grading characteristics analyses showed no difference in image quality between the standard dose examination reconstructed with iDose4 and the low dose examination reconstructed with IMR. IMR showed lower image noise in the liver compared to iDose4 images. Inter- and intra-observer variance was low: the intraclass coefficient was 0.66 (95% confidence interval = 0.60–0.71) for the three observers. Conclusion IMR provided image quality equivalent or superior to the standard iDose4 method for evaluating pediatric abdominal CT, even with a 32% dose reduction.

scholarly journals Image quality and radiologists’ subjective acceptance using model-based iterative and deep learning reconstructions as adjuncts to ultrahigh-resolution CT in low-dose contrast-enhanced abdominopelvic CT: phantom and clinical pilot studies

2021 ◽  
Author(s):  
Makiko Nishikawa ◽  
Haruhiko Machida ◽  
Yuta Shimizu ◽  
Toshiya Kariyasu ◽  
Hiroyuki Morisaka ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Low Dose ◽  
Tube Voltage ◽  
Ultrahigh Resolution ◽  
Matrix Size ◽  
Noise Index ◽  
Model Based ◽  
Contrast Enhanced ◽  
Abdominopelvic Ct

Abstract Purpose In contrast-enhanced abdominopelvic CT (CE-APCT) for oncologic follow-up, ultrahigh-resolution CT (UHRCT) may improve depiction of fine lesions and low-dose scans are desirable for minimizing the potential adverse effects by ionizing radiation. We compared image quality and radiologists’ acceptance of model-based iterative (MBIR) and deep learning (DLR) reconstructions of low-dose CE-APCT by UHRCT. Methods Using our high-resolution (matrix size: 1024) and low-dose (tube voltage 100 kV; noise index: 20–40 HU) protocol, we scanned phantoms to compare the modulation transfer function and noise power spectrum between MBIR and DLR and assessed findings in 36 consecutive patients who underwent CE-APCT (noise index: 35 HU; mean CTDIvol: 4.2 ± 1.6 mGy) by UHRCT. We used paired t-test to compare objective noise and contrast-to-noise ratio (CNR) and Wilcoxon signed-rank test to compare radiologists’ subjective acceptance regarding noise, image texture and appearance, and diagnostic confidence between MBIR and DLR using our routine protocol (matrix size: 512; tube voltage: 120 kV; noise index: 15 HU) for reference. Results Phantom studies demonstrated higher spatial resolution and lower low-frequency noise by DLR than MBIR at equal doses. Clinical studies indicated significantly worse objective noise, CNR, and subjective noise by DLR than MBIR, but other subjective characteristics were better (P < 0.001 for all). Compared with the routine protocol, subjective noise was similar or better by DLR, and other subjective characteristics were similar or worse by MBIR. Conclusion Image quality, except regarding noise characteristics, and acceptance by radiologists were better by DLR than MBIR in low-dose CE-APCT by UHRCT. Graphical abstract

A feasibility study of realizing low-dose abdominal CT using deep learning image reconstruction algorithm

2021 ◽  
pp. 1-12
Author(s):  
Lu-Lu Li ◽  
Huang Wang ◽  
Jian Song ◽  
Jin Shang ◽  
Xiao-Ying Zhao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Reconstruction ◽  
Image Quality ◽  
Radiation Dose ◽  
Low Dose ◽  
Standard Dose ◽  
Image Noise ◽  
Arterial Phase ◽  
Abdominal Ct ◽  
Reconstruction Methods

OBJECTIVES: To explore the feasibility of achieving diagnostic images in low-dose abdominal CT using a Deep Learning Image Reconstruction (DLIR) algorithm. METHODS: Prospectively enrolled 47 patients requiring contrast-enhanced abdominal CT scans. The late-arterial phase scan was added and acquired using lower-dose mode (tube current range, 175–545 mA; 80 kVp for patients with BMI ≤24 kg/m2 and 100 kVp for patients with BMI >  24 kg/m2) and reconstructed with DLIR at medium setting (DLIR-M) and high setting (DLIR-H), ASIR-V at 0% (FBP), 40% and 80% strength. Both the quantitative measurement and qualitative analysis of the five types of reconstruction methods were compared. In addition, radiation dose and image quality between the early-arterial phase ASIR-V images using standard-dose and the late-arterial phase DLIR images using low-dose were compared. RESULTS: For the late-arterial phase, all five reconstructions had similar CT value (P >  0.05). DLIR-H, DLIR-M and ASIR-V80% images significantly reduced the image noise and improved the image contrast noise ratio, compared with the standard ASIR-V40% images (P <  0.05). ASIR-V80% images had undesirable image characteristics with obvious “waxy” artifacts, while DLIR-H images maintained high spatial resolution and had the highest subjective image quality. Compared with the early-arterial scans, the late-arterial phase scans significantly reduced the radiation dose (P <  0.05), while the DLIR-H images exhibited lower image noise and good display of the specific image details of lesions. CONCLUSIONS: DLIR algorithm improves image quality under low-dose scan condition and may be used to reduce the radiation dose without adversely affecting the image quality.

scholarly journals Deep learning–based reconstruction may improve non-contrast cerebral CT imaging compared to other current reconstruction algorithms

2021 ◽  
Author(s):  
Luuk J. Oostveen ◽  
Frederick J. A. Meijer ◽  
Frank de Lange ◽  
Ewoud J. Smit ◽  
Sjoert A. Pegge ◽  
...  
Keyword(s):  
Deep Learning ◽  
White Matter ◽  
Image Quality ◽  
Iterative Reconstruction ◽  
Quality Characteristics ◽  
Model Based ◽  
Hybrid Iterative Reconstruction ◽  
Contrast Ct ◽  
Lower Noise ◽  
Reconstruction Time

Abstract Objectives To evaluate image quality and reconstruction times of a commercial deep learning reconstruction algorithm (DLR) compared to hybrid-iterative reconstruction (Hybrid-IR) and model-based iterative reconstruction (MBIR) algorithms for cerebral non-contrast CT (NCCT). Methods Cerebral NCCT acquisitions of 50 consecutive patients were reconstructed using DLR, Hybrid-IR and MBIR with a clinical CT system. Image quality, in terms of six subjective characteristics (noise, sharpness, grey-white matter differentiation, artefacts, natural appearance and overall image quality), was scored by five observers. As objective metrics of image quality, the noise magnitude and signal-difference-to-noise ratio (SDNR) of the grey and white matter were calculated. Mean values for the image quality characteristics scored by the observers were estimated using a general linear model to account for multiple readers. The estimated means for the reconstruction methods were pairwise compared. Calculated measures were compared using paired t tests. Results For all image quality characteristics, DLR images were scored significantly higher than MBIR images. Compared to Hybrid-IR, perceived noise and grey-white matter differentiation were better with DLR, while no difference was detected for other image quality characteristics. Noise magnitude was lower for DLR compared to Hybrid-IR and MBIR (5.6, 6.4 and 6.2, respectively) and SDNR higher (2.4, 1.9 and 2.0, respectively). Reconstruction times were 27 s, 44 s and 176 s for Hybrid-IR, DLR and MBIR respectively. Conclusions With a slight increase in reconstruction time, DLR results in lower noise and improved tissue differentiation compared to Hybrid-IR. Image quality of MBIR is significantly lower compared to DLR with much longer reconstruction times. Key Points • Deep learning reconstruction of cerebral non-contrast CT results in lower noise and improved tissue differentiation compared to hybrid-iterative reconstruction. • Deep learning reconstruction of cerebral non-contrast CT results in better image quality in all aspects evaluated compared to model-based iterative reconstruction. • Deep learning reconstruction only needs a slight increase in reconstruction time compared to hybrid-iterative reconstruction, while model-based iterative reconstruction requires considerably longer processing time.

scholarly journals Implementation of ultra-low-dose lung protocols in CT-guided lung biopsies: feasibility and safety in the clinical setting

2017 ◽  
Vol 45 (6) ◽  
pp. 2101-2109 ◽  
Author(s):  
Barbara K Frisch ◽  
Karin Slebocki ◽  
Kamal Mammadov ◽  
Michael Puesken ◽  
Ingrid Becker ◽  
...  
Keyword(s):  
Image Quality ◽  
Radiation Dose ◽  
Low Dose ◽  
Standard Dose ◽  
Complication Rates ◽  
Dose Length Product ◽  
Ct Guided ◽  
Total Radiation Dose ◽  
Lung Biopsies ◽  
Histological Results

Objective To evaluate the use of ultra-low-dose computed tomography (ULDCT) for CT-guided lung biopsy versus standard-dose CT (SDCT). Methods CT-guided lung biopsies from 115 patients (50 ULDCT, 65 SDCT) were analyzed retrospectively. SDCT settings were 120 kVp with automatic mAs modulation. ULDCT settings were 80 kVp with fixed exposure (20 mAs). Two radiologists evaluated image quality (i.e., needle artifacts, lesion contouring, vessel recognition, visibility of interlobar fissures). Complications and histological results were also evaluated. Results ULDCT was considered feasible for all lung interventions, showing the same diagnostic accuracy as SDCT. Its mean total radiation dose (dose–length product) was significantly reduced to 34 mGy-cm (SDCT 426 mGy-cm). Image quality and complication rates ( P = 0.469) were consistent. Conclusions ULDCT for CT-guided lung biopsies appears safe and accurate, with a significantly reduced radiation dose. We therefore recommend routine clinical use of ULDCT for the benefit of patients and interventionalists.

Combination of Deep Learning–Based Denoising and Iterative Reconstruction for Ultra-Low-Dose CT of the Chest: Image Quality and Lung-RADS Evaluation

2020 ◽  
Vol 215 (6) ◽  
pp. 1321-1328
Author(s):  
Akinori Hata ◽  
Masahiro Yanagawa ◽  
Yuriko Yoshida ◽  
Tomo Miyata ◽  
Mitsuko Tsubamoto ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Quality ◽  
Iterative Reconstruction ◽  
Low Dose ◽  
Low Dose Ct
Sign in / Sign up

Export Citation Format

Share Document