scholarly journals Deep Learning-Based Image Reconstruction for CT Angiography of the Aorta

Diagnostics ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 2037
Author(s):  
Andra Heinrich ◽  
Felix Streckenbach ◽  
Ebba Beller ◽  
Justus Groß ◽  
Marc-André Weber ◽  
...  

To evaluate the impact of a novel, deep-learning-based image reconstruction (DLIR) algorithm on image quality in CT angiography of the aorta, we retrospectively analyzed 51 consecutive patients who underwent ECG-gated chest CT angiography and non-gated acquisition for the abdomen on a 256-dectector-row CT. Images were reconstructed with adaptive statistical iterative reconstruction (ASIR-V) and DLIR. Intravascular image noise, the signal-to-noise ratio (SNR) and the contrast-to-noise ratio (CNR) were quantified for the ascending aorta, the descending thoracic aorta, the abdominal aorta and the iliac arteries. Two readers scored subjective image quality on a five-point scale. Compared to ASIR-V, DLIR reduced the median image noise by 51-54% for the ascending aorta and the descending thoracic aorta. Correspondingly, median CNR roughly doubled for the ascending aorta and descending thoracic aorta. There was a 38% reduction in image noise for the abdominal aorta and the iliac arteries, with a corresponding improvement in CNR. Median subjective image quality improved from good to excellent at all anatomical levels. In CT angiography of the aorta, DLIR substantially improved objective and subjective image quality beyond what can be achieved by state-of-the-art iterative reconstruction. This can pave the way for further radiation or contrast dose reductions.

Author(s):  
Jihang Sun ◽  
Haoyan Li ◽  
Haiyun Li ◽  
Michelle Li ◽  
Yingzi Gao ◽  
...  

BACKGROUND: The inflammatory indexes of children with Takayasu arteritis (TAK) usually tend to be normal immediately after treatment, therefore, CT angiography (CTA) has become an important method to evaluate the status of TAK and sometime is even more sensitive than laboratory test results. OBJECTIVE: To evaluate image quality improvement in CTA of children diagnosed with TAK using a deep learning image reconstruction (DLIR) in comparison to other image reconstruction algorithms. METHODS: hirty-two TAK patients (9.14±4.51 years old) underwent neck, chest and abdominal CTA using 100 kVp were enrolled. Images were reconstructed at 0.625 mm slice thickness using Filtered Back-Projection (FBP), 50%adaptive statistical iterative reconstruction-V (ASIR-V), 100%ASIR-V and DLIR with high setting (DLIR-H). CT number and standard deviation (SD) of the descending aorta and back muscle were measured and contrast-to-noise ratio (CNR) for aorta was calculated. The vessel visualization, overall image noise and diagnostic confidence were evaluated using a 5-point scale (5, excellent; 3, acceptable) by 2 observers. RESULTS: There was no significant difference in CT number across images reconstructed using different algorithms. Image noise values (in HU) were 31.36±6.01, 24.96±4.69, 18.46±3.91 and 15.58±3.65, and CNR values for aorta were 11.93±2.12, 15.66±2.37, 22.54±3.34 and 24.02±4.55 using FBP, 50%ASIR-V, 100%ASIR-V and DLIR-H, respectively. The 100%ASIR-V and DLIR-H images had similar noise and CNR (all P >  0.05), and both had lower noise and higher CNR than FBP and 50%ASIR-V images (all P <  0.05). The subjective evaluation suggested that all images were diagnostic for large arteries, however, only 50%ASIR-V and DLIR-H met the diagnostic requirement for small arteries (3.03±0.18 and 3.53±0.51). CONCLUSION: DLIR-H improves CTA image quality and diagnostic confidence for TAK patients compared with 50%ASIR-V, and best balances image noise and spatial resolution compared with 100%ASIR-V.


2021 ◽  
Vol 94 (1117) ◽  
pp. 20200677
Author(s):  
Andrea Steuwe ◽  
Marie Weber ◽  
Oliver Thomas Bethge ◽  
Christin Rademacher ◽  
Matthias Boschheidgen ◽  
...  

Objectives: Modern reconstruction and post-processing software aims at reducing image noise in CT images, potentially allowing for a reduction of the employed radiation exposure. This study aimed at assessing the influence of a novel deep-learning based software on the subjective and objective image quality compared to two traditional methods [filtered back-projection (FBP), iterative reconstruction (IR)]. Methods: In this institutional review board-approved retrospective study, abdominal low-dose CT images of 27 patients (mean age 38 ± 12 years, volumetric CT dose index 2.9 ± 1.8 mGy) were reconstructed with IR, FBP and, furthermore, post-processed using a novel software. For the three reconstructions, qualitative and quantitative image quality was evaluated by means of CT numbers, noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) in six different ROIs. Additionally, the reconstructions were compared using SNR, peak SNR, root mean square error and mean absolute error to assess structural differences. Results: On average, CT numbers varied within 1 Hounsfield unit (HU) for the three assessed methods in the assessed ROIs. In soft tissue, image noise was up to 42% lower compared to FBP and up to 27% lower to IR when applying the novel software. Consequently, SNR and CNR were highest with the novel software. For both IR and the novel software, subjective image quality was equal but higher than the image quality of FBP-images. Conclusion: The assessed software reduces image noise while maintaining image information, even in comparison to IR, allowing for a potential dose reduction of approximately 20% in abdominal CT imaging. Advances in knowledge: The assessed software reduces image noise by up to 27% compared to IR and 48% compared to FBP while maintaining the image information. The reduced image noise allows for a potential dose reduction of approximately 20% in abdominal imaging.


2021 ◽  
Vol 94 (1123) ◽  
pp. 20201357
Author(s):  
Akio Tamura ◽  
Eisuke Mukaida ◽  
Yoshitaka Ota ◽  
Masayoshi Kamata ◽  
Shun Abe ◽  
...  

Objective: This study aimed to conduct objective and subjective comparisons of image quality among abdominal computed tomography (CT) reconstructions with deep learning reconstruction (DLR) algorithms, model-based iterative reconstruction (MBIR), and filtered back projection (FBP). Methods: Datasets from consecutive patients who underwent low-dose liver CT were retrospectively identified. Images were reconstructed using DLR, MBIR, and FBP. Mean image noise and contrast-to-noise ratio (CNR) were calculated, and noise, artifacts, sharpness, and overall image quality were subjectively assessed. Dunnett’s test was used for statistical comparisons. Results: Ninety patients (67 ± 12.7 years; 63 males; mean body mass index [BMI], 25.5 kg/m2) were included. The mean noise in the abdominal aorta and hepatic parenchyma of DLR was lower than that in FBP and MBIR (p < .001). For FBP and MBIR, image noise was significantly higher for obese patients than for those with normal BMI. The CNR for the abdominal aorta and hepatic parenchyma was higher for DLR than for FBP and MBIR (p < .001). MBIR images were subjectively rated as superior to FBP images in terms of noise, artifacts, sharpness, and overall quality (p < .001). DLR images were rated as superior to MBIR images in terms of noise (p < .001) and overall quality (p = .03). Conclusions: Based on objective and subjective comparisons, the image quality of DLR was found to be superior to that of MBIR and FBP on low-dose abdominal CT. DLR was the only method for which image noise was not higher for obese patients than for those with a normal BMI. Advances in knowledge: This study provides previously unavailable information on the properties of DLR systems and their clinical utility.


2016 ◽  
Vol 20 (4) ◽  
pp. 76
Author(s):  
A. P. Shket ◽  
T. V. Glybovskaya ◽  
V. G. Krutov ◽  
O. G. Nizhnikova ◽  
Y. P. Ostrovskii

<p><strong>Aim.</strong> The study looks at the results of clinical testing of the first Belarusian aortic stent graft system developed and manufactured by a team of specialists from RSPC "Cardiology", Minsk, Belarus, and Belarusian Technical University.<br /><strong>Methods.</strong> The original system of aortic stent graft includes a delivery system and an aortic stent graft itself. It is used in surgical treatment of complicated and common aneurysms of the thoracic aorta, as well as in cases of concomitant thoracic aneurysms and heart pathology to be treated under cardiopulmonary bypass. Clinical testing of the stent graft was carried out according to the requirements of Ministry of Health of the Republic of Belarus on the basis of three different cardiac hospitals of the country. <br /><strong>Results.</strong> All the three hospitals treated one patient each. The first patient underwent implantation of the stent graft into the descending thoracic aorta, with the thoracic aorta aneurysm isolated and the aortic valve replaced with bioprosthesis. The second patient underwent ascending aorta and aortic valve replacement with a conduit and implantation of aortic stent graft into the descending thoracic aorta. In the third patient the domestic aortic stent graft was implanted into the descending thoracic aorta with isolation of the thoracic aneurysm; aortic valve and ascending aorta were replaced with ‘MedEng' conduit and the aortic arch was also replaced, with the brachiocephalic arteries re-implanted in place. All the patients were followed-up for both early and long-term outcomes for more than 1 year and were examined by using CT angiography in the early postoperative period and after 1 year. Uncomplicated postoperative course was observed in all the patients. There were no complications in the long-term follow-up as well. CT angiography data confirmed good positioning of the stent graft and good isolation of the aneurysm lumen. Preoperative and postoperative СТ data of one patient are presented in the article.<br /><strong>Conclusion.</strong> The Belarusian system of aortic stent graft successfully passed clinical testing and may be certified and used in clinical practice at a later time on the territory of Belarus.</p><p>Received 21 June 2016. Accepted 11 November 2016.</p><p><strong>Funding:</strong> The research was financed by Ministry of Health Care of Republic of Belarus.<br /><strong>Conflict of interest:</strong> The authors declare no conflict of interest.<br /><strong>Author contributions</strong><br />Conceptualization and study design: Shket A.P.<br />Material acquisition and analysis: Shket A.P., Nizhnikova O.G. <br />Statistical data processing: Glybovskaya T.V.<br />Article writing: Shket A.P., Krutov V.G.<br />Review &amp; editing: Ostrovskii Y.P.</p>


2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Martina Correa Londono ◽  
Nino Trussardi ◽  
Verena C. Obmann ◽  
Davide Piccini ◽  
Michael Ith ◽  
...  

Abstract Background The native balanced steady state with free precession (bSSFP) magnetic resonance angiography (MRA) technique has been shown to provide high diagnostic image quality for thoracic aortic disease. This study compares a 3D radial respiratory self-navigated native MRA (native-SN-MRA) based on a bSSFP sequence with conventional Cartesian, 3D, contrast-enhanced MRA (CE-MRA) with navigator-gated respiration control for image quality of the entire thoracic aorta. Methods Thirty-one aortic native-SN-MRA were compared retrospectively (63.9 ± 10.3 years) to 61 CE-MRA (63.1 ± 11.7 years) serving as a reference standard. Image quality was evaluated at the aortic root/ascending aorta, aortic arch and descending aorta. Scan time was recorded. In 10 patients with both MRA sequences, aortic pathologies were evaluated and normal and pathologic aortic diameters were measured. The influence of artifacts on image quality was analyzed. Results Compared to the overall image quality of CE-MRA, the overall image quality of native-SN-MRA was superior for all segments analyzed (aortic root/ascending, p < 0.001; arch, p < 0.001, and descending, p = 0.005). Regarding artifacts, the image quality of native-SN-MRA remained superior at the aortic root/ascending aorta and aortic arch before and after correction for confounders of surgical material (i.e., susceptibility-related artifacts) (p = 0.008 both) suggesting a benefit in terms of motion artifacts. Native-SN-MRA showed a trend towards superior intraindividual image quality, but without statistical significance. Intraindividually, the sensitivity and specificity for the detection of aortic disease were 100% for native-SN-MRA. Aortic diameters did not show a significant difference (p = 0.899). The scan time of the native-SN-MRA was significantly reduced, with a mean of 05:56 ± 01:32 min vs. 08:51 ± 02:57 min in the CE-MRA (p < 0.001). Conclusions Superior image quality of the entire thoracic aorta, also regarding artifacts, can be achieved with native-SN-MRA, especially in motion prone segments, in addition to a shorter acquisition time.


2020 ◽  
Vol 13 (1) ◽  
pp. e231957
Author(s):  
Rita Reis Correia ◽  
Fábia Cruz ◽  
Sandra Martin ◽  
Maria Eugenia André

A 72-year-old man was admitted with complaints of sudden-onset oppressive precordial pain radiating to the back for 1 hour. He had hypotension, peripheral cyanosis and cold extremities. An initial assessment was done and acute coronary syndrome was excluded. After the patient was admitted, he developed fever and increased levels of inflammatory markers. Data obtained from CT angiography and transoesophageal echocardiogram revealed diffuse parietal thickening of the arch and the descending thoracic aorta, as well as dilatation of the aortic root and the proximal ascending aorta. In addition, the test for Borrelia burgdorferi was positive, and the patient was diagnosed with Lyme vasculitis of the thoracic aorta. He was treated with doxycycline for 3 weeks. Two months later, the patient exhibited a Stanford type A aortic dissection (clinically stable), which was treated by prosthesis replacement. The patient has remained asymptomatic for 1 year after the episode, performing his routine daily activities.


2020 ◽  
Vol 9 (9) ◽  
pp. 2731
Author(s):  
Mikko Jormalainen ◽  
Peter Raivio ◽  
Fausto Biancari ◽  
Caius Mustonen ◽  
Hannu-Pekka Honkanen ◽  
...  

The aim of this study was to evaluate all-cause mortality and aortic reoperations after surgery for Stanford type A aortic dissection (TAAD). We evaluated the late outcome of patients who underwent surgery for acute TAAD from January 2005 to December 2017 at the Helsinki University Hospital, Finland. We studied 309 patients (DeBakey type I TAAD: 89.3%) who underwent repair of TAAD. Aortic root repair was performed in 94 patients (30.4%), hemiarch repair in 264 patients (85.4%) and partial/total aortic arch repair in 32 patients (10.4%). Hospital mortality was 13.6%. At 10 years, all-cause mortality was 34.9%, and the cumulative incidence of aortic reoperation or late aortic-related death was 15.6%, of any aortic reoperation 14.6%, reoperation on the aortic root 6.6%, on the aortic arch, descending thoracic and/or abdominal aorta 8.7%, on the descending thoracic and/or abdominal aorta 6.4%, and on the abdominal aorta 3.8%. At 10 years, cumulative incidence of reoperation on the distal aorta was higher in patients with a diameter of the descending thoracic aorta ≥35 mm at primary surgery (cumulative incidence in the overall series: 13.2% vs. 4.0%, SHR 3.993, 95%CI 1.316–12.120; DeBakey type I aortic dissection: 13.6% vs. 4.5%, SHR 3.610, 95%CI 1.193–10.913; patients with dissected descending thoracic aorta: 15.8% vs. 5.9%, SHR 3.211, 95%CI 1.067–9.664). In conclusion, surgical repair of TAAD limited to the aortic segments involved by the intimal tear was associated with favorable survival and a low rate of aortic reoperations. However, patients with enlarged descending thoracic aorta at primary surgery had higher risk of late reoperation. Half of the distal aortic reinterventions were performed on the abdominal aorta.


2010 ◽  
Vol 194 (1) ◽  
pp. W111-W114 ◽  
Author(s):  
Philipp Blanke ◽  
Tobias Baumann ◽  
Stefan Bulla ◽  
Oliver Schaefer ◽  
Elmar Kotter ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document