1
|
Gnasso C, Vecsey-Nagy M, Schoepf UJ, Stock J, Zsarnoczay E, Pinos D, Tremamunno G, Giovagnoli V, Seidensticker P, Emrich T, Varga-Szemes A. Evaluation of a Tube Voltage-Based Contrast Media Adaptation in Coronary Computed Tomography Angiography Using Personalized Triphasic Injection Protocols: A Matched Case-Control Study. Acad Radiol 2024:S1076-6332(24)00256-3. [PMID: 38734579 DOI: 10.1016/j.acra.2024.04.039] [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: 02/14/2024] [Revised: 04/16/2024] [Accepted: 04/22/2024] [Indexed: 05/13/2024]
Abstract
RATIONALE AND OBJECTIVES Coronary CT angiography (CCTA) has recently been established as a first-line test in patients with suspected coronary artery disease (CAD). Due to the increased use of CCTA, strategies to reduce radiation and contrast medium (CM) exposure are of high importance. The aim of this study was to evaluate the performance of automated tube voltage selection (ATVS)-adapted CM injection protocol for CCTA compared to a clinically established triphasic injection protocol in terms of image quality, radiation exposure, and CM administration MATERIAL AND METHODS: Patients undergoing clinically indicated CCTA were prospectively enrolled from July 2021 to July 2023. Patients underwent CCTA using a modified triphasic CM injection protocol tailored to the tube voltage by the ATVS algorithm, in a range of 70 to 130 kV with a 10 kV interval. The injection protocol consisted of two phases of mixed CM and saline boluses with different proportions to assure a voltage-specific iodine delivery rate, followed by a third phase of saline flush. This cohort was compared to a control group identified retrospectively and scanned on the same CT system but with a standard triphasic CM protocol. Radiation and contrast dose, subjective and objective image quality (contrast-to-noise-ratio [CNR] and signal-to-noise-ratio [SNR]) were compared between the two groups. RESULTS The final population consisted of 120 prospective patients matched with 120 retrospective controls, with 20 patients in each kV group. The 120 kV group was excluded from the statistical analysis due to insufficient sample size. A significant CM reduction was achieved in the prospective group overall (46.0 [IQR 37.0-52.0] vs. 51.3 [IQR 40.1-73.0] mL, p < 0.001) and at all kV levels too (all pairwise p < 0.001). There were no significant differences in radiation dose (6.13 ± 4.88 vs. 5.97 ± 5.51 mSv, p = 0.81), subjective image quality (median score of 4 [3-5] vs. 4 [3-5], p = 0.40), CNR, and SNR in the aorta and the left anterior descending coronary artery (all p > 0.05). CONCLUSION ATVS-adapted CM injection protocol allows for diagnostic quality CCTA with reduced CM volume while maintaining similar radiation exposure, subjective and objective image quality.
Collapse
Affiliation(s)
- Chiara Gnasso
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; Experimental Imaging Center, IRCCS San Raffaele Scientific Institute, Via Olgettina 60, Milan, Italy
| | - Milan Vecsey-Nagy
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; Heart and Vascular Centre, Semmelweis University, Varosmajor utca 68, Budapest 1122, Hungary
| | - U Joseph Schoepf
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA.
| | - Jonathan Stock
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; Paracelsus Medical University, Nuremberg, Prof.-Ernst-Nathan-Strasse 1, 90419 Nuremberg, Germany
| | - Emese Zsarnoczay
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; MTA-SE Cardiovascular Imaging Research Group, Department of Radiology, Medical Imaging Centre, Semmelweis University, H-1082 Budapest, Üllői út 78, Budapest, Hungary
| | - Daniel Pinos
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA
| | - Giuseppe Tremamunno
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; Radiology Unit, Department of Surgical and Medical Sciences and Translational Medicine, Sapienza University of Rome - Sant'Andrea University Hospital, Via di Grottarossa, 1035-1039, 00189, Rome, Italy
| | - Vincent Giovagnoli
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA
| | - Peter Seidensticker
- Global Medical Affairs Radiology, Bayer US LLC, Pittsburgh, Pennsylvania, USA
| | - Tilman Emrich
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA; Department of Diagnostic and Interventional Radiology, University Medical Center of Johannes Gutenberg University, Langenbeckstr. 1, Mainz 55131, Germany; German Centre for Cardiovascular Research, Mainz 55131, Germany
| | - Akos Varga-Szemes
- Division of Cardiovascular Imaging, Department of Radiology and Radiological Science, Medical University of South Carolina, 25 Courtenay Dr, Charleston, South Carolina 29425, USA
| |
Collapse
|
2
|
Fleitmann M, Uzunova H, Pallenberg R, Stroth AM, Gerlach J, Fürschke A, Barkhausen J, Bischof A, Handels H. Artificial Intelligence-Based Prediction of Contrast Medium Doses for Computed Tomography Angiography Using Optimized Clinical Parameter Sets. Methods Inf Med 2024. [PMID: 38262476 DOI: 10.1055/s-0044-1778694] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/25/2024]
Abstract
OBJECTIVES In this paper, an artificial intelligence-based algorithm for predicting the optimal contrast medium dose for computed tomography (CT) angiography of the aorta is presented and evaluated in a clinical study. The prediction of the contrast dose reduction is modelled as a classification problem using the image contrast as the main feature. METHODS This classification is performed by random decision forests (RDF) and k-nearest-neighbor methods (KNN). For the selection of optimal parameter subsets all possible combinations of the 22 clinical parameters (age, blood pressure, etc.) are considered using the classification accuracy and precision of the KNN classifier and RDF as quality criteria. Subsequently, the results of the evaluation were optimized by means of feature transformation using regression neural networks (RNN). These were used for a direct classification based on regressed Hounsfield units as well as preprocessing for a subsequent KNN classification. RESULTS For feature selection, an RDF model achieved the highest accuracy of 84.42% and a KNN model achieved the best precision of 86.21%. The most important parameters include age, height, and hemoglobin. The feature transformation using an RNN considerably exceeded these values with an accuracy of 90.00% and a precision of 97.62% using all 22 parameters as input. However, also the feasibility of the parameter sets in routine clinical practice has to be considered, because some of the 22 parameters are not measured in routine clinical practice and additional measurement time of 15 to 20 minutes per patient is needed. Using the standard feature set available in clinical routine the best accuracy of 86.67% and precision of 93.18% was achieved by the RNN. CONCLUSION We developed a reliable hybrid system that helps radiologists determine the optimal contrast dose for CT angiography based on patient-specific parameters.
Collapse
Affiliation(s)
- Marja Fleitmann
- Artificial Intelligence in Medical Imaging, German Research Center for Artificial Intelligence, Kaiserslautern, Germany
| | - Hristina Uzunova
- Artificial Intelligence in Medical Imaging, German Research Center for Artificial Intelligence, Kaiserslautern, Germany
| | - René Pallenberg
- Institute for Signal Processing, University of Lübeck, Schleswig-Holstein, Germany
| | - Andreas M Stroth
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein (UKSH) Lübeck, Lübeck, Germany
| | - Jan Gerlach
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein (UKSH) Lübeck, Lübeck, Germany
| | - Alexander Fürschke
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein (UKSH) Lübeck, Lübeck, Germany
| | - Jörg Barkhausen
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein (UKSH) Lübeck, Lübeck, Germany
| | - Arpad Bischof
- Department of Radiology and Nuclear Medicine, University Hospital Schleswig-Holstein (UKSH) Lübeck, Lübeck, Germany
- IMAGE Information Systems Europe, Rostock, Germany
| | - Heinz Handels
- Artificial Intelligence in Medical Imaging, German Research Center for Artificial Intelligence, Kaiserslautern, Germany
- Institute of Medical Informatics, University of Lübeck, Schleswig-Holstein, Germany
| |
Collapse
|
3
|
Wang K, Wang X, Zheng S, Li C, Jin L, Li M. Dedicated CCTA Followed by High-Pitch Scanning versus TRO-CT for Contrast Media and Radiation Dose Reduction: A Retrospective Study. Diagnostics (Basel) 2022; 12:diagnostics12112647. [PMID: 36359488 PMCID: PMC9688948 DOI: 10.3390/diagnostics12112647] [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: 09/20/2022] [Revised: 10/22/2022] [Accepted: 10/27/2022] [Indexed: 11/16/2022] Open
Abstract
We aimed to compare dedicated coronary computed tomography angiography (CCTA) followed by high-pitch scanning and triple-rule-out computed tomography angiography (TRO-CTA) in terms of radiation dose, contrast media (CM) use, and image quality. Patients with acute chest pain were retrospectively enrolled and assigned to group A (n = 55; scanned with dedicated CCTA followed by high-pitch scanning) or group B (n = 45; with TRO-CTA). Patient characteristics, radiation dose, CM use, and quantitative parameters (CT value, image noise, signal-to-noise ratio, contrast-to-noise ratio, and image quality score) of pulmonary arteries (PAs), thoracic aortae (TAs), and coronary arteries (CAs) were compared. The total effective dose was significantly lower in group A (6.25 ± 2.94 mSv) than B (8.93 ± 4.08 mSv; p < 0.001). CM volume was significantly lower in group A (75.7 ± 8.9 mL) than B (95.0 ± 0 mL; p < 0.001). PA and TA image quality were significantly better in group B, whereas that of CA was significantly better in group A. Qualitative image scores of PA and TA scans rated by radiologists were similar, whereas that of CA scans was significantly higher in group A than B (p < 0.001). Dedicated CCTA followed by high-pitch scanning demonstrated lower radiation doses and CM volume without debasing qualities of PA, TA, and CA scans than did TRO-CTA.
Collapse
Affiliation(s)
- Kun Wang
- Radiology Department, Huadong Hospital Affiliated to Fudan University, Shanghai 200040, China
| | - Xiaodong Wang
- Shanghai Changfeng Community Health Service Center of Putuo District, Shanghai 200062, China
| | - Shaoqiang Zheng
- Department of Radiology, Tongji Hospital, School of Medicine, Tongji University, Shanghai 200065, China
| | - Cheng Li
- Radiology Department, Huadong Hospital Affiliated to Fudan University, Shanghai 200040, China
| | - Liang Jin
- Radiology Department, Huadong Hospital Affiliated to Fudan University, Shanghai 200040, China
- Correspondence: (L.J.); (M.L.); Tel.: +86-137-6114-8449 (L.J.); +86-138-1662-0371 (M.L.); Fax: +86-021-6248-3180 (L.J. & M.L.)
| | - Ming Li
- Radiology Department, Huadong Hospital Affiliated to Fudan University, Shanghai 200040, China
- Institute of Functional and Molecular Medical Imaging, Fudan University, Shanghai 200040, China
- Correspondence: (L.J.); (M.L.); Tel.: +86-137-6114-8449 (L.J.); +86-138-1662-0371 (M.L.); Fax: +86-021-6248-3180 (L.J. & M.L.)
| |
Collapse
|