Rofo 2022; 194(S 01): S58-S59
DOI: 10.1055/s-0042-1749921
Abstract
Poster (Wissenschaft)
Herzdiagnostik

Deep Convolutional Neural Networks Improve Long Term Prediction of Major Cardiovascular Events after Coronary Computed Tomography Angiography.

Authors

  • A Chami

    1   Deutsches Herzzentrum München, Klinikum München, München

  • C Schacky v.

    2   Institut für diagnostische und interventionelle Radiologie des Klinikums rechts der Isar, TUM, München

  • R Adolf

    3   Institut für Radiologie und Nuklearmedizin, Deutsches Herzzentrum München, München

  • N Nano

    4   Deutsches Herzzentrum München, Institut für Radiologie und Nuklearmedizin, München

  • E Hendrich

    3   Institut für Radiologie und Nuklearmedizin, Deutsches Herzzentrum München, München

  • A Will

    3   Institut für Radiologie und Nuklearmedizin, Deutsches Herzzentrum München, München

  • S Martinoff

    3   Institut für Radiologie und Nuklearmedizin, Deutsches Herzzentrum München, München

  • M Hadamitzky

    3   Institut für Radiologie und Nuklearmedizin, Deutsches Herzzentrum München, München
Further Information
Also available at
 

Zielsetzung Coronary Computed Tomography Angiography (CCTA) is an established modality for assessing coronary artery disease (CAD). Its role for prognosis assessment is still limited. Deep convolutional neural networks (CNNs) might improve this process by using plaque characteristics that are currently not used.

Material und Methoden The Consecutive CCTAs from patients with suspected CAD examined between October 2004 and January 2018 were analyzed. Primary endpoint was a composite of all-cause mortality, myocardial infarction and late revascularization. The training endpoint additionally included early revascularization. Clinical risk was assessed by Morise score, for conventional CCTA assessment extent of CAD (eoCAD) and segment involvement score (SIS) were used. Semiautomatic post-processing was performed for vessel delineation and annotation of calcified and non-calcified plaque areas. Two-step training of a densenet-121 CNN was done: The full network was trained using the training endpoint, then the feature layer was trained using the primary endpoint. Five times cross validation was performed to ensure that each CNN was evaluated on an unseen set of data.

Ergebnisse The study population comprised 5468 patients. During follow up of 7.2 years, 334 patients reached the primary endpoint in addition 405 early revascularizations occurred.?Outcome correlation of CNN showed an AUC of 0.720±0.010 and 0.631±0.015 for training endpoint and primary endpoint resp. Combining CNN with conventional CT parameters showed improvement of AUC from 0.791 to 0.821 (p<0.0001) and from 0.766 to 0.773 (p<0.0001) for eoCAD and SIS resp. In a stepwise model including clinical risk, conventional CT parameters and CNN, the latter improved prediction from 0.813 to 0.819 (p=0.0022) and from 0.772 to 0.775 (p<0.0013) for eoCAD and SIS resp.

Schlußfolgerungen CNNs are a promising tool to further improve prediction of major cardiovascular events after CCTA.



Publication History

Article published online:
29 August 2022

© 2022. Thieme. All rights reserved.

Georg Thieme Verlag
Rüdigerstraße 14, 70469 Stuttgart, Germany