1
|
Cai H, Jiang H, Xie D, Lai Z, Wu J, Chen M, Yang Z, Xu R, Zeng S, Ma H. Enhancing image quality in computed tomography angiography follow-ups after endovascular aneurysm repair: a comparative study of reconstruction techniques. BMC Med Imaging 2024; 24:162. [PMID: 38956470 PMCID: PMC11218285 DOI: 10.1186/s12880-024-01343-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2024] [Accepted: 06/20/2024] [Indexed: 07/04/2024] Open
Abstract
BACKGROUND The image quality of computed tomography angiography (CTA) images following endovascular aneurysm repair (EVAR) is not satisfactory, since artifacts resulting from metallic implants obstruct the clear depiction of stent and isolation lumens, and also adjacent soft tissues. However, current techniques to reduce these artifacts still need further advancements due to higher radiation doses, longer processing times and so on. Thus, the aim of this study is to assess the impact of utilizing Single-Energy Metal Artifact Reduction (SEMAR) alongside a novel deep learning image reconstruction technique, known as the Advanced Intelligent Clear-IQ Engine (AiCE), on image quality of CTA follow-ups conducted after EVAR. MATERIALS This retrospective study included 47 patients (mean age ± standard deviation: 68.6 ± 7.8 years; 37 males) who underwent CTA examinations following EVAR. Images were reconstructed using four different methods: hybrid iterative reconstruction (HIR), AiCE, the combination of HIR and SEMAR (HIR + SEMAR), and the combination of AiCE and SEMAR (AiCE + SEMAR). Two radiologists, blinded to the reconstruction techniques, independently evaluated the images. Quantitative assessments included measurements of image noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), the longest length of artifacts (AL), and artifact index (AI). These parameters were subsequently compared across different reconstruction methods. RESULTS The subjective results indicated that AiCE + SEMAR performed the best in terms of image quality. The mean image noise intensity was significantly lower in the AiCE + SEMAR group (25.35 ± 6.51 HU) than in the HIR (47.77 ± 8.76 HU), AiCE (42.93 ± 10.61 HU), and HIR + SEMAR (30.34 ± 4.87 HU) groups (p < 0.001). Additionally, AiCE + SEMAR exhibited the highest SNRs and CNRs, as well as the lowest AIs and ALs. Importantly, endoleaks and thrombi were most clearly visualized using AiCE + SEMAR. CONCLUSIONS In comparison to other reconstruction methods, the combination of AiCE + SEMAR demonstrates superior image quality, thereby enhancing the detection capabilities and diagnostic confidence of potential complications such as early minor endleaks and thrombi following EVAR. This improvement in image quality could lead to more accurate diagnoses and better patient outcomes.
Collapse
Affiliation(s)
- Huasong Cai
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Hairong Jiang
- Department of Radiology, Foresea Life Insurance Guangzhou General Hospital, No. 703, Xincheng Avenue, Zengcheng District, Guangzhou, Guangdong, 511300, China
| | - Dingxiang Xie
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Zhiman Lai
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Jiale Wu
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Mingjie Chen
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Zhiyun Yang
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China
| | - Rulin Xu
- Research Collaboration, Canon Medical Systems, No.10 Huaxia Road, Guangzhou, Guangdong, 510623, China
| | - Shanmei Zeng
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China.
| | - Hui Ma
- Department of Radiology, The First Affiliated Hospital, Sun Yat-sen University, No. 58, Zhongshan Er Road, Guangzhou, Guangdong Province, 510080, People's Republic of China.
| |
Collapse
|
2
|
Bos D, Demircioğlu A, Neuhoff J, Haubold J, Zensen S, Opitz MK, Drews MA, Li Y, Styczen H, Forsting M, Nassenstein K. Assessment of image quality and impact of deep learning-based software in non-contrast head CT scans. Sci Rep 2024; 14:11810. [PMID: 38782976 PMCID: PMC11116440 DOI: 10.1038/s41598-024-62394-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Accepted: 05/16/2024] [Indexed: 05/25/2024] Open
Abstract
In this retrospective study, we aimed to assess the objective and subjective image quality of different reconstruction techniques and a deep learning-based software on non-contrast head computed tomography (CT) images. In total, 152 adult head CT scans (77 female, 75 male; mean age 69.4 ± 18.3 years) obtained from three different CT scanners using different protocols between March and April 2021 were included. CT images were reconstructed using filtered-back projection (FBP), iterative reconstruction (IR), and post-processed using a deep learning-based algorithm (PS). Post-processing significantly reduced noise in FBP-reconstructed images (up to 15.4% reduction) depending on the protocol, leading to improvements in signal-to-noise ratio of up to 19.7%. However, when deep learning-based post-processing was applied to FBP images compared to IR alone, the differences were inconsistent and partly non-significant, which appeared to be protocol or site specific. Subjective assessments showed no significant overall improvement in image quality for all reconstructions and post-processing. Inter-rater reliability was low and preferences varied. Deep learning-based denoising software improved objective image quality compared to FBP in routine head CT. A significant difference compared to IR was observed for only one protocol. Subjective assessments did not indicate a significant clinical impact in terms of improved subjective image quality, likely due to the low noise levels in full-dose images.
Collapse
Affiliation(s)
- Denise Bos
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany.
| | - Aydin Demircioğlu
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Julia Neuhoff
- Faculty of Medicine, University Duisburg-Essen, Hufelandstraße 55, 45122, Essen, Germany
| | - Johannes Haubold
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Sebastian Zensen
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Marcel K Opitz
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Marcel A Drews
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Yan Li
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Hanna Styczen
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Michael Forsting
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| | - Kai Nassenstein
- Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University Duisburg-Essen, Hufelandstraße 55, 45147, Essen, Germany
| |
Collapse
|
3
|
Zhang W, Zhao Y, Tian Y, Liang X, Piao C. Early Diagnosis of High-Risk Chronic Obstructive Pulmonary Disease Based on Quantitative High-Resolution Computed Tomography Measurements. Int J Chron Obstruct Pulmon Dis 2023; 18:3099-3114. [PMID: 38162987 PMCID: PMC10757779 DOI: 10.2147/copd.s436803] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Accepted: 12/15/2023] [Indexed: 01/03/2024] Open
Abstract
Purpose Quantitative computed tomography (QCT) techniques, focusing on airway anatomy and emphysema, may help to detect early structural changes of COPD disease. This retrospective study aims to identify high-risk COPD participants by using QCT measurements. Patients and Methods We enrolled 140 participants from the Second Affiliated Hospital of Shenyang Medical College who completed inspiratory high-resolution CT scans, pulmonary function tests (PFTs), and clinical characteristics recorded. They were diagnosed Non-COPD by PFT value of FEV1/FVC >70% and divided into two groups according percentage predicted FEV1 (FEV1%), low-risk COPD group: FEV1% ≥ 95%, high-risk group: 80% < FEV1% < 95%. The QCT measurements were analyzed by the Student's t-test (or Mann-Whitney U-test) method. Then, feature candidates were identified using the LASSO method. Meanwhile, the correlation between QCT measurements and PFTs was assessed by the Spearman rank correlation test. Furthermore, support vector machine (SVM) was performed to identify high-risk COPD participants. The performance of the models was evaluated in terms of accuracy (ACC), sensitivity (SEN), specificity (SPE), F1-score, and area under the ROC curve (AUC), with p <0.05 considered statistically significant. Results The SVM based on QCT measurements achieved good performance in identifying high-risk COPD patients with 85.71% of ACC, 88.34% of SEN, 84.00% of SPE, 83.33% of F1-score, and 0.93 of AUC. Further, QCT measurements integration of clinical data improved the performance with an ACC of 90.48%. The emphysema index (%LAA-950) of left lower lung was negatively correlated with PFTs (P < 0.001). The airway anatomy indexes of lumen diameter (LD) were correlated with PFTs. Conclusion QCT measurements combined with clinical information could provide an effective tool for an early diagnosis of high-risk COPD. The QCT indexes can be used to assess the pulmonary function status of high-risk COPD.
Collapse
Affiliation(s)
- Wenxiu Zhang
- Institute of Research and Clinical Innovations, Neusoft Medical Systems Co, Ltd, Shanghai, People’s Republic of China
| | - Yu Zhao
- Radiology Department, Second Affiliated Hospital of Shenyang Medical College, Shenyang, Liaoning, People’s Republic of China
| | - Yuchi Tian
- Institute of Research and Clinical Innovations, Neusoft Medical Systems Co, Ltd, Shanghai, People’s Republic of China
| | - Xiaoyun Liang
- Institute of Research and Clinical Innovations, Neusoft Medical Systems Co, Ltd, Shanghai, People’s Republic of China
| | - Chenghao Piao
- Radiology Department, Second Affiliated Hospital of Shenyang Medical College, Shenyang, Liaoning, People’s Republic of China
| |
Collapse
|
4
|
Cozzi A, Cè M, De Padova G, Libri D, Caldarelli N, Zucconi F, Oliva G, Cellina M. Deep Learning-Based Versus Iterative Image Reconstruction for Unenhanced Brain CT: A Quantitative Comparison of Image Quality. Tomography 2023; 9:1629-1637. [PMID: 37736983 PMCID: PMC10514884 DOI: 10.3390/tomography9050130] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Revised: 08/23/2023] [Accepted: 08/30/2023] [Indexed: 09/23/2023] Open
Abstract
This exploratory retrospective study aims to quantitatively compare the image quality of unenhanced brain computed tomography (CT) reconstructed with an iterative (AIDR-3D) and a deep learning-based (AiCE) reconstruction algorithm. After a preliminary phantom study, AIDR-3D and AiCE reconstructions (0.5 mm thickness) of 100 consecutive brain CTs acquired in the emergency setting on the same 320-detector row CT scanner were retrospectively analyzed, calculating image noise reduction attributable to the AiCE algorithm, artifact indexes in the posterior cranial fossa, and contrast-to-noise ratios (CNRs) at the cortical and thalamic levels. In the phantom study, the spatial resolution of the two datasets proved to be comparable; conversely, AIDR-3D reconstructions showed a broader noise pattern. In the human study, median image noise was lower with AiCE compared to AIDR-3D (4.7 vs. 5.3, p < 0.001, median 19.6% noise reduction), whereas AIDR-3D yielded a lower artifact index than AiCE (7.5 vs. 8.4, p < 0.001). AiCE also showed higher median CNRs at the cortical (2.5 vs. 1.8, p < 0.001) and thalamic levels (2.8 vs. 1.7, p < 0.001). These results highlight how image quality improvements granted by deep learning-based (AiCE) and iterative (AIDR-3D) image reconstruction algorithms vary according to different brain areas.
Collapse
Affiliation(s)
- Andrea Cozzi
- Service of Radiology, Imaging Institute of Southern Switzerland (IIMSI), Ente Ospedaliero Cantonale (EOC), Via Tesserete 46, 6900 Lugano, Switzerland;
| | - Maurizio Cè
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milano, Italy (G.D.P.); (D.L.); (N.C.)
| | - Giuseppe De Padova
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milano, Italy (G.D.P.); (D.L.); (N.C.)
| | - Dario Libri
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milano, Italy (G.D.P.); (D.L.); (N.C.)
| | - Nazarena Caldarelli
- Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milano, Italy (G.D.P.); (D.L.); (N.C.)
| | - Fabio Zucconi
- Department of Radioprotection, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Milano, Piazza Principessa Clotilde 3, 20121 Milano, Italy;
| | - Giancarlo Oliva
- Radiology Department, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Milano, Piazza Principessa Clotilde 3, 20121 Milano, Italy;
| | - Michaela Cellina
- Radiology Department, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Milano, Piazza Principessa Clotilde 3, 20121 Milano, Italy;
| |
Collapse
|
5
|
A Review of Deep Learning CT Reconstruction: Concepts, Limitations, and Promise in Clinical Practice. CURRENT RADIOLOGY REPORTS 2022. [DOI: 10.1007/s40134-022-00399-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/16/2022]
Abstract
Abstract
Purpose of Review
Deep Learning reconstruction (DLR) is the current state-of-the-art method for CT image formation. Comparisons to existing filter back-projection, iterative, and model-based reconstructions are now available in the literature. This review summarizes the prior reconstruction methods, introduces DLR, and then reviews recent findings from DLR from a physics and clinical perspective.
Recent Findings
DLR has been shown to allow for noise magnitude reductions relative to filtered back-projection without suffering from “plastic” or “blotchy” noise texture that was found objectionable with most iterative and model-based solutions. Clinically, early reader studies have reported increases in subjective quality scores and studies have successfully implemented DLR-enabled dose reductions.
Summary
The future of CT image reconstruction is bright; deep learning methods have only started to tackle problems in this space via addressing noise reduction. Artifact mitigation and spectral applications likely be future candidates for DLR applications.
Collapse
|