Keywords:
Case-control study, Retrospective, Image registration, Arteriosclerosis, Segmentation, Screening, CAD, CT, Computer applications, Cardiac, Artificial Intelligence, Artificial Intelligence and Machine Learning, Performed at one institution
Authors:
V. Chernina1, M. Pisov1, M. Belyaev1, V. Gombolevskiy1, I. Blokhin1, I. Bekk2, O. Aleshina1, T. Korb1, S. Morozov1; 1Moscow/RU, 2Moscow /RU
DOI:
10.26044/ecr2020/C-10054
Purpose
White adipose tissue can be divided into visceral and subcutaneous adipose tissue. The former surrounds various organs and spaces, including the omentum, mesentery, mediastinum, and perivascular regions [1]. Two functionally different adipose tissue types - epicardial adipose tissue (EAT) and paracardial adipose tissue (PAT) - surround almost all arteries and the heart ( Fig. 1 ) [2].
According to the Multi-Ethnic Study of Atherosclerosis (MESA), the volume of pericardial adipose tissue is an independent predictor of ischemic heart disease (IHD) [3]. The most exciting is the possibility of assessing this predictor at the preclinical stage of the IHD. Estimation of EAT volume from ultra-low-dose CT (ULDCT) used in a screening project may reveal at-risk asymptomatic patients [4].
Volumetric quantitative assessment includes cardiac border identification followed by the delineation of the pericardium to distinguish PAT and EAT. This can be done manually, with a semi-automatic algorithm or a fully automated one [5,6]. The manual and semi-automatic methods are labour-intensive and time-consuming enough to prevent their implementation into routine practice.
The purpose of our study was to develop a novel deep learning algorithm for epicardial fat volume measurement in ultra-low-dose computed tomography (ULDCT) for lung cancer screening.