1
|
Zhu H, Kong D, Qian J, Shi X, Fan J. The impact of deep learning image reconstruction of spectral CTU virtual non contrast images for patients with renal stones. Eur J Radiol Open 2024; 13:100599. [PMID: 39280122 PMCID: PMC11402413 DOI: 10.1016/j.ejro.2024.100599] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2024] [Revised: 08/13/2024] [Accepted: 08/27/2024] [Indexed: 09/18/2024] Open
Abstract
Purpose To compare image quality and detection accuracy of renal stones between deep learning image reconstruction (DLIR) and Adaptive Statistical Iterative Reconstruction-Veo (ASIR-V) reconstructed virtual non-contrast (VNC) images and true non-contrast (TNC) images in spectral CT Urography (CTU). Methods A retrospective analysis was conducted on images of 70 patients who underwent abdominal-pelvic CTU in TNC phase using non-contrast scan and contrast-enhanced corticomedullary phase (CP) and excretory phase (EP) using spectral scan. The TNC scan was reconstructed using ASIR-V70 % (TNC-AR70), contrast-enhanced scans were reconstructed using AR70, DLIR medium-level (DM), and high-level (DH) to obtain CP-VNC-AR70/DM/DH and EP-VNC-AR70/DM/DH image groups, respectively. CT value, image quality and kidney stones quantification accuracy were measured and compared among groups. The subjective evaluation was independently assessed by two senior radiologists using the 5-point Likert scale for image quality and lesion visibility. Results DH images were superior to AR70 and DM images in objective image quality evaluation. There was no statistical difference in the liver and spleen (both P > 0.05), or within 6HU in renal and fat in CT value between VNC and TNC images. EP-VNC-DH had the lowest image noise, highest SNR, and CNR, and VNC-AR70 images had better noise and SNR performance than TNC-AR70 images (all p < 0.05). EP-VNC-DH had the highest subjective image quality, and CP-VNC-DH performed the best in lesion visibility. In stone CT value and volume measurements, there was no statistical difference between VNC and TNC (P > 0.05). Conclusion The DLIR-reconstructed VNC images in CTU provide better image quality than the ASIR-V reconstructed TNC images and similar quantification accuracy for kidney stones for potential dose savings.The study highlights that deep learning image reconstruction (DLIR)-reconstructed virtual non-contrast (VNC) images in spectral CT Urography (CTU) offer improved image quality compared to traditional true non-contrast (TNC) images, while maintaining similar accuracy in kidney stone detection, suggesting potential dose savings in clinical practice.
Collapse
Affiliation(s)
- Hong Zhu
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 200025, China
| | - Deyan Kong
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 200025, China
| | - Jiale Qian
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 200025, China
| | - Xiaomeng Shi
- CT Imaging Research Center, GE Healthcare China, Shanghai 201203, China
| | - Jing Fan
- Department of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, 200025, China
| |
Collapse
|
2
|
Wen D, Pu Q, Peng P, Yue X, Ming Y, Yang H, Yang J, Zhang X, Liu H, Yang L, Sun J. Comparison of virtual and true non-contrast images from dual-layer spectral detector computed tomography (CT) in patients with colorectal cancer. Quant Imaging Med Surg 2024; 14:6260-6272. [PMID: 39281124 PMCID: PMC11400675 DOI: 10.21037/qims-24-535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2024] [Accepted: 08/05/2024] [Indexed: 09/18/2024]
Abstract
Background Colorectal cancer (CRC) is commonly assessed by computed tomography (CT), but the associated radiation exposure is a major concern. This study aimed to quantitatively and qualitatively compare the image quality of virtual non-contrast (VNC) images reconstructed from arterial and portal venous phases with that of true non-contrast (TNC) images in patients with CRC to assess the potential of TNC images to replace VNC images, thereby reducing the radiation dose. Methods A total of 69 patients with postoperative pathologically confirmed CRC at the West China Hospital of Sichuan University between May 2022 and April 2023 were enrolled in this cross-sectional study. The CT protocol included the acquisition of TNC images, arterial and portal venous phase images; the VNC images were reconstructed from the two postcontrast phase images. Several parameters, including the CT attenuation value, absolute attenuation error, imaging noise [standard deviation (SD)], signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR), were measured in multiple abdominal structures for both the TNC and VNC images. Two blinded readers assessed the subjective image quality using a five-point scale. Interobserver agreement was evaluated using interclass correlation coefficients (ICCs). The paired t-test and Wilcoxon signed-rank test were used to compare the objective and subjective results between the TNC and VNC images. Individual measurements of radiation doses for the TNC scan and contrast scan protocols were recorded. Results A total of 2,070 regions of interest (ROIs) of the 69 patients were analyzed. Overall, the VNC images exhibited significantly lower attenuation values and SD values than the TNC images in all tissues, except for the abdominal aorta, portal vein, and spleen. The mean absolute attenuation errors between the VNC and TNC images were all less than 10 Hounsfield units (HU). The percentages of absolute attenuation errors less than 5 and 10 HU in the VNC images from the arterial phase (VNCa) were 78.99% and 97.97%, respectively, while those from the portal venous phase (VNCp) were 81.59% and 96.96%, respectively. The absolute attenuation errors between the TNC and VNCa images were smaller than those between the TNC and VNCp images for tumors [VNCaerror: 2.77, interquartile range (IQR) 1.77-4.22; VNCperror: 3.27, IQR 2.68-4.30; P=0.002]. The SNR values and CNR values in the VNC images were significantly higher than those in the TNC images for all tissues, except for the portal vein and spleen. The image quality was rated as excellent (represented by a score of 5) in the majority of the TNC and VNC images; however, the VNC images scored lower than the TNC images. Eliminating the TNC phase resulted in a reduction of approximately 37.99% in the effective dose (ED). Conclusions The VNC images provided accurate CT attenuation, good image quality, and lower radiation doses than the TNC images in CRC, and the VNCa images showed minimal differences in the CT attenuation of the tumors.
Collapse
Affiliation(s)
- Deying Wen
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Qian Pu
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Pengfei Peng
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Xun Yue
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
- Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, China
| | - Yue Ming
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Huiyi Yang
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| | - Jianyang Yang
- Division of Gastrointestinal Surgery, Department of General Surgery, West China Hospital, Sichuan University, Chengdu, China
| | - Xiaodi Zhang
- Clinical Science, Philips Healthcare, Chengdu, China
| | - Haiwei Liu
- Advanced Clinical Application, Philips Healthcare, Beijing, China
| | - Lie Yang
- Division of Gastrointestinal Surgery, Department of General Surgery, West China Hospital, Sichuan University, Chengdu, China
| | - Jiayu Sun
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, China
| |
Collapse
|
3
|
Nowak E, Białecki M, Białecka A, Kazimierczak N, Kloska A. Assessing the diagnostic accuracy of artificial intelligence in post-endovascular aneurysm repair endoleak detection using dual-energy computed tomography angiography. Pol J Radiol 2024; 89:e420-e427. [PMID: 39257927 PMCID: PMC11384217 DOI: 10.5114/pjr/192115] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2024] [Accepted: 08/06/2024] [Indexed: 09/12/2024] Open
Abstract
Purpose The aim of this study was to evaluate the diagnostic accuracy of an artificial intelligence (AI) tool in detecting endoleaks in patients undergoing endovascular aneurysm repair (EVAR) using dual-energy computed tomography angiography (CTA). Material and methods The study involved 95 patients who underwent EVAR and subsequent CTA follow-up. Dualenergy scans were performed, and images were reconstructed as linearly blended (LB) and 40 keV virtual monoenergetic (VMI) images. The AI tool PRAEVAorta®2 was used to assess arterial phase images for endoleaks. Two experienced readers independently evaluated the same images, and their consensus served as the reference standard. Key metrics, including accuracy, precision, recall, F1 score, and area under the receiver operating characteristic (ROC) curve (AUC), were calculated. Results The final analysis included 94 patients. The AI tool demonstrated an accuracy of 78.7%, precision of 67.6%, recall of 10 71.9%, F1 score of 69.7%, and an AUC of 0.77 using LB images. However, the tool failed to process 40 keV VMI images correctly, limiting further analysis of these datasets. Conclusions The AI tool showed moderate diagnostic accuracy in detecting endoleaks using LB images but failed to achieve the reliability needed for clinical use due to the significant number of misdiagnoses.
Collapse
Affiliation(s)
- Ewa Nowak
- Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Toruń, Bydgoszcz, Poland
| | - Marcin Białecki
- Department of Radiology and Diagnostic Imaging, Collegium Medicum, Nicolaus Copernicus University in Toruń, Bydgoszcz, Poland
- Department of Radiology and Diagnostic Imaging, University Hospital no. 1 in Bydgoszcz, Poland
| | - Agnieszka Białecka
- Department of Dermatology and Venereology, Collegium Medicum, Nicolaus Copernicus University in Torun, Bydgoszcz, Poland
| | | | - Anna Kloska
- Faculty of Medicine, Bydgoszcz University of Science and Technology, Bydgoszcz, Poland
| |
Collapse
|
4
|
Stański M, Michałowska I, Lemanowicz A, Karmelita-Katulska K, Ratajczak P, Sławińska A, Serafin Z. Dual-Energy and Photon-Counting Computed Tomography in Vascular Applications-Technical Background and Post-Processing Techniques. Diagnostics (Basel) 2024; 14:1223. [PMID: 38928639 PMCID: PMC11202784 DOI: 10.3390/diagnostics14121223] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Revised: 05/30/2024] [Accepted: 06/06/2024] [Indexed: 06/28/2024] Open
Abstract
The field of computed tomography (CT), which is a basic diagnostic tool in clinical practice, has recently undergone rapid technological advances. These include the evolution of dual-energy CT (DECT) and development of photon-counting computed tomography (PCCT). DECT enables the acquisition of CT images at two different energy spectra, which allows for the differentiation of certain materials, mainly calcium and iodine. PCCT is a recent technology that enables a scanner to quantify the energy of each photon gathered by the detector. This method gives the possibility to decrease the radiation dose and increase the spatial and temporal resolutions of scans. Both of these techniques have found a wide range of applications in radiology, including vascular studies. In this narrative review, the authors present the principles of DECT and PCCT, outline their advantages and drawbacks, and briefly discuss the application of these methods in vascular radiology.
Collapse
Affiliation(s)
- Marcin Stański
- Department of General Radiology and Neuroradiology, Poznan University of Medical Sciences, 61-701 Poznań, Poland;
| | - Ilona Michałowska
- Department of Radiology, National Institute of Cardiology, 04-628 Warsaw, Poland;
| | - Adam Lemanowicz
- Department of Radiology and Diagnostic Imaging, Nicolaus Copernicus University, Collegium Medicum, 85-067 Bydgoszcz, Poland; (A.L.); (P.R.); (A.S.); (Z.S.)
| | - Katarzyna Karmelita-Katulska
- Department of General Radiology and Neuroradiology, Poznan University of Medical Sciences, 61-701 Poznań, Poland;
| | - Przemysław Ratajczak
- Department of Radiology and Diagnostic Imaging, Nicolaus Copernicus University, Collegium Medicum, 85-067 Bydgoszcz, Poland; (A.L.); (P.R.); (A.S.); (Z.S.)
| | - Agata Sławińska
- Department of Radiology and Diagnostic Imaging, Nicolaus Copernicus University, Collegium Medicum, 85-067 Bydgoszcz, Poland; (A.L.); (P.R.); (A.S.); (Z.S.)
| | - Zbigniew Serafin
- Department of Radiology and Diagnostic Imaging, Nicolaus Copernicus University, Collegium Medicum, 85-067 Bydgoszcz, Poland; (A.L.); (P.R.); (A.S.); (Z.S.)
| |
Collapse
|
5
|
Winkelmann MT, Gassenmaier S, Walter SS, Artzner C, Nikolaou K, Bongers MN. Differentiation of Hamartomas and Malignant Lung Tumors in Single-Phased Dual-Energy Computed Tomography. Tomography 2024; 10:255-265. [PMID: 38393288 PMCID: PMC10892507 DOI: 10.3390/tomography10020020] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Revised: 01/30/2024] [Accepted: 02/08/2024] [Indexed: 02/25/2024] Open
Abstract
This study investigated the efficacy of single-phase dual-energy CT (DECT) in differentiating pulmonary hamartomas from malignant lung lesions using virtual non-contrast (VNC), iodine, and fat quantification. Forty-six patients with 47 pulmonary lesions (mean age: 65.2 ± 12.1 years; hamartomas-to-malignant lesions = 22:25; male: 67%) underwent portal venous DECT using histology, PET-CT and follow-up CTs as a reference. Quantitative parameters such as VNC, fat fraction, iodine density and CT mixed values were statistically analyzed. Significant differences were found in fat fractions (hamartomas: 48.9%; malignancies: 22.9%; p ≤ 0.0001) and VNC HU values (hamartomas: -20.5 HU; malignancies: 17.8 HU; p ≤ 0.0001), with hamartomas having higher fat content and lower VNC HU values than malignancies. CT mixed values also differed significantly (p ≤ 0.0001), but iodine density showed no significant differences. ROC analysis favored the fat fraction (AUC = 96.4%; sensitivity: 100%) over the VNC, CT mixed value and iodine density for differentiation. The study concludes that the DECT-based fat fraction is superior to the single-energy CT in differentiating between incidental pulmonary hamartomas and malignant lesions, while post-contrast iodine density is ineffective for differentiation.
Collapse
Affiliation(s)
- Moritz T. Winkelmann
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
| | - Sebastian Gassenmaier
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
| | - Sven S. Walter
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
| | - Christoph Artzner
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
- Institute of Radiology: Diakonie Klinikum Stuttgart, 70174 Stuttgart, Germany
| | - Konstantin Nikolaou
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
| | - Malte N. Bongers
- Department for Diagnostic and Interventional Radiology, University Hospital Tuebingen, 72076 Tuebingen, Germany; (S.G.); (S.S.W.); (C.A.); (K.N.); (M.N.B.)
| |
Collapse
|
6
|
Kazimierczak W, Kazimierczak N, Serafin Z. Review of Clinical Applications of Dual-Energy CT in Patients after Endovascular Aortic Repair. J Clin Med 2023; 12:7766. [PMID: 38137834 PMCID: PMC10743598 DOI: 10.3390/jcm12247766] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2023] [Revised: 12/08/2023] [Accepted: 12/16/2023] [Indexed: 12/24/2023] Open
Abstract
Abdominal aortic aneurysms (AAAs) are a significant cause of mortality in developed countries. Endovascular aneurysm repair (EVAR) is currently the leading treatment method for AAAs. Due to the high sensitivity and specificity of post-EVAR complication detection, CT angiography (CTA) is the reference method for imaging surveillance in patients after EVAR. Many studies have shown the advantages of dual-energy CT (DECT) over standard polyenergetic CTA in vascular applications. In this article, the authors briefly discuss the technical principles and summarize the current body of literature regarding dual-energy computed tomography angiography (DECTA) in patients after EVAR. The authors point out the most useful applications of DECTA in this group of patients and its advantages over conventional CTA. To conduct this review, a search was performed using the PubMed, Google Scholar, and Web of Science databases.
Collapse
Affiliation(s)
- Wojciech Kazimierczak
- Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, 85-067 Bydgoszcz, Poland
- Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland
| | - Natalia Kazimierczak
- Kazimierczak Private Medical Practice, Dworcowa 13/u6a, 85-009 Bydgoszcz, Poland
| | - Zbigniew Serafin
- Collegium Medicum, Nicolaus Copernicus University in Torun, Jagiellońska 13-15, 85-067 Bydgoszcz, Poland
| |
Collapse
|