Efficacy of human experts and an automated segmentation algorithm in quantifying disease pathology in coronary computed tomography angiography: A head-to-head comparison with intravascular ultrasound imaging.

Autor: Çap M; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK; Department of Cardiology, University of Health Sciences Diyarbakır Gazi Yaşargil Education and Research Hospital, Diyarbakır, Turkey. Electronic address: murat00418@hotmail.com., Ramasamy A; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK., Parasa R; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK; Department of Cardiology, The Essex Cardiothoracic Centre, Basildon, UK., Tanboga IH; Istanbul Nisantasi University Medical School, Department of Cardiology & Biostatistics, Istanbul, Turkey., Maung S; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK., Morgan K; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK., Yap NAL; Barts and the London School of Medicine and Dentistry, London, UK., Abou Gamrah M; Department of Bioengineering, Imperial College London, UK., Sokooti H; Medis Medical Imaging, Leiden, the Netherlands., Kitslaar P; Medis Medical Imaging, Leiden, the Netherlands., Reiber JHC; Medis Medical Imaging, Leiden, the Netherlands; Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands., Dijkstra J; Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands., Torii R; Department of Mechanical Engineering, University College London, London, UK., Moon JC; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Institute of Cardiovascular Sciences, University College London, London, UK., Mathur A; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK., Baumbach A; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK., Pugliese F; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK., Bourantas CV; Department of Cardiology, Barts Heart Centre, Barts Health NHS Trust, London, UK; Centre for Cardiovascular Medicine and Devices, William Harvey Research Institute, Queen Mary University London, UK; Institute of Cardiovascular Sciences, University College London, London, UK. Electronic address: cbourantas@gmail.com.
Jazyk: angličtina
Zdroj: Journal of cardiovascular computed tomography [J Cardiovasc Comput Tomogr] 2024 Mar-Apr; Vol. 18 (2), pp. 142-153. Date of Electronic Publication: 2023 Dec 23.
DOI: 10.1016/j.jcct.2023.12.007
Abstrakt: Background: Coronary computed tomography angiography (CCTA) analysis is currently performed by experts and is a laborious process. Fully automated edge-detection methods have been developed to expedite CCTA segmentation however their use is limited as there are concerns about their accuracy. This study aims to compare the performance of an automated CCTA analysis software and the experts using near-infrared spectroscopy-intravascular ultrasound imaging (NIRS-IVUS) as a reference standard.
Methods: Fifty-one participants (150 vessels) with chronic coronary syndrome who underwent CCTA and 3-vessel NIRS-IVUS were included. CCTA analysis was performed by an expert and an automated edge detection method and their estimations were compared to NIRS-IVUS at a segment-, lesion-, and frame-level.
Results: Segment-level analysis demonstrated a similar performance of the two CCTA analyses (conventional and automatic) with large biases and limits of agreement compared to NIRS-IVUS estimations for the total atheroma (ICC: 0.55 vs 0.25, mean difference:192 (-102-487) vs 243 (-132-617) and percent atheroma volume (ICC: 0.30 vs 0.12, mean difference: 12.8 (-5.91-31.6) vs 20.0 (0.79-39.2). Lesion-level analysis showed that the experts were able to detect more accurately lesions than the automated method (68.2 ​% and 60.7 ​%) however both analyses had poor reliability in assessing the minimal lumen area (ICC 0.44 vs 0.36) and the maximum plaque burden (ICC 0.33 vs 0.33) when NIRS-IVUS was used as the reference standard.
Conclusions: Conventional and automated CCTA analyses had similar performance in assessing coronary artery pathology using NIRS-IVUS as a reference standard. Therefore, automated segmentation can be used to expedite CCTA analysis and enhance its applications in clinical practice.
Competing Interests: Declaration of competing interest All authors have no conflicts of interest to declare.
(Copyright © 2023 Society of Cardiovascular Computed Tomography. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: