Back to the list
Congress: ECR25
Poster Number: C-10229
Type: Poster: EPOS Radiologist (scientific)
Authorblock: G. Tremamunno1, A. Varga-Szemes2, D. Kravchenko2, M. T. Hagar2, U. J. Schoepf2, A. Laghi1, M. Vecsey-Nagy2, T. S. Emrich2; 1Rome/IT, 2Charleston, SC/US
Disclosures:
Giuseppe Tremamunno: Nothing to disclose
Akos Varga-Szemes: Research/Grant Support: Siemens Healtineers
Dmitrij Kravchenko: Nothing to disclose
Muhammad Taha Hagar: Nothing to disclose
Uwe Joseph Schoepf: Research/Grant Support: Siemens Healthineers
Andrea Laghi: Nothing to disclose
Milán Vecsey-Nagy: Nothing to disclose
Tilman Stephan Emrich: Research/Grant Support: Siemens Healthineers
Keywords: Artificial Intelligence, CAD, CT-Angiography, CAD, Arteriosclerosis
Purpose Artificial intelligence (AI) is rapidly advancing in cardiac imaging, with numerous software tools either under development or already available for automated, fast, and accurate evaluation of the coronary vessels.1The recent introduction of dual-source photon-counting detector CT (PCD-CT) in clinical practice has exhibited several technical advantages over conventional energy-integrating detector (EID)-CT, such as higher contrast-to-noise ratios, reduced electronic noise, and improved spatial resolution.2-3 To date, automatic coronary analysis (ACA) software solutions have been employed and tested exclusively on EID-CTs, leaving their...
Read more Methods and materials The local Institutional Review Board approved the protocol of this prospective, single-center, observational study. All subjects gave written, informed consent. Consecutive patients referred for standard of care imaging on an EID-CT system were recruited for a research CT scan within 30 days on a PCD-CT. Research scans were conducted on a first-generation clinical dual-source PCD-CT system using the UHR acquisition mode with a gantry rotation time of 0.25 seconds and a collimation of 120×0.2 mm. An AI algorithm automatically assessed percentage...
Read more Results Patient characteristicsOut of 97 patients who consented to participate, 32 (26 male [81.3%], 68.6 ± 6.8 years of age) patients were available for final analysis as detailed in Figure 1. The median interval between scans was 14.5 days (range: 7.8-18.2). Details of patient characteristics are summarized in Table 2.Automatic coronary analysis A total of 401 segments and 185 plaques were identified and automatically evaluated by the DL algorithm in both the UHR PCD-CT and EID-CT datasets. Among these, 71 (38.4%)...
Read more Conclusion In conclusion, DL based ACA demonstrated robust performance with substantial agreement with experts and better agreement with the ICA reference standard on UHR PCD-CT imaging compared to EID-CT. DL assisted coronary assessments are a promising supportive tool for radiologists and may act as a valuable pre-reading resource, helping clinicians improve efficiency and manage heavier workloads in daily practice.
Read more References van Assen M, Razavi AC, Whelton SP, De Cecco CN. Artificial intelligence in cardiac imaging: where we are and what we want. Eur Heart J. 2023 Feb 14;44(7):541–3. Willemink MJ, Persson M, Pourmorteza A, Pelc NJ, Fleischmann D. Photon-counting CT: Technical Principles and Clinical Prospects. Radiology. 2018 Nov;289(2):293–312. Vecsey-Nagy M, Tremamunno G, Schoepf UJ, Gnasso C, Zsarnóczay E, Fink N, et al. Intraindividual Comparison of Ultrahigh-Spatial-Resolution Photon-Counting Detector CT and Energy-Integrating Detector CT for Coronary Stenosis Measurement. Circ Cardiovasc Imaging. 2024 Oct;17(10):e017112....
Read more
GALLERY