잠시만 기다려 주세요. 로딩중입니다.

Deep learning approach for the segmentation of aneurysmal ascending aorta

Biomedical Engineering Letters 2021년 11권 1호 p.15 ~ 24
Comelli Albert, Dahiya Navdeep, Stefano Alessandro, Benfante Viviana, Gentile Giovanni, Agnese Valentina, Raffa Giuseppe M., Pilato Michele, Yezzi Anthony, Petrucci Giovanni, Pasta Salvatore,
소속 상세정보
 ( Comelli Albert ) - National Research Council of Italy Institute of Molecular Bioimaging and Physiology
 ( Dahiya Navdeep ) - Georgia Institute of Technology Department of Electrical and Computer Engineering
 ( Stefano Alessandro ) - National Research Council of Italy Institute of Molecular Bioimaging and Physiology
 ( Benfante Viviana ) - National Research Council of Italy Institute of Molecular Bioimaging and Physiology
 ( Gentile Giovanni ) - IRCCS-ISMETT Department of Diagnostic and Therapeutic Services
 ( Agnese Valentina ) - IRCCS-ISMETT Department for Treatment and Study of Cardiothoracic Diseases and Cardiothoracic Transplantation
 ( Raffa Giuseppe M. ) - IRCCS-ISMETT Department for Treatment and Study of Cardiothoracic Diseases and Cardiothoracic Transplantation
 ( Pilato Michele ) - IRCCS-ISMETT Department for Treatment and Study of Cardiothoracic Diseases and Cardiothoracic Transplantation
 ( Yezzi Anthony ) - Georgia Institute of Technology Department of Electrical and Computer Engineering
 ( Petrucci Giovanni ) - University of Palermo Department of Engineering
 ( Pasta Salvatore ) - University of Palermo Department of Engineering

Abstract


Diagnosis of ascending thoracic aortic aneurysm (ATAA) is based on the measurement of the maximum aortic diameter, but size is not a good predictor of the risk of adverse events. There is growing interest in the development of novel image-derived risk strategies to improve patient risk management towards a highly individualized level. In this study, the feasibility and efficacy of deep learning for the automatic segmentation of ATAAs was investigated using UNet, ENet, and ERFNet techniques. Specifically, CT angiography done on 72 patients with ATAAs and different valve morphology (i.e., tricuspid aortic valve, TAV, and bicuspid aortic valve, BAV) were semi-automatically segmented with Mimics software (Materialize NV, Leuven, Belgium), and then used for training of the tested deep learning models. The segmentation performance in terms of accuracy and time inference were compared using several parameters. All deep learning models reported a dice score higher than 88%, suggesting a good agreement between predicted and manual ATAA segmentation. We found that the ENet and UNet are more accurate than ERFNet, with the ENet much faster than UNet. This study demonstrated that deep learning models can rapidly segment and quantify the 3D geometry of ATAAs with high accuracy, thereby facilitating the expansion into clinical workflow of personalized approach to the management of patients with ATAAs.

키워드

Deep learning; Segmentation; Aorta; Aneurysm; Aortic valve

원문 및 링크아웃 정보

등재저널 정보