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
Methods and materials
The sample size was 500 patients (men-to-women ratio, 1:1) ( Fig. 2 ). Random recruitment was carried out in 5 age groups (from 50 to 75 years), a hundred patients in each age group, equally smokers and non-smokers.
Additionally, we randomly selected 100 cases (equally ULDCT and CT) to test robustness ( Fig. 3 ).
Two radiologists with 5-year experience in thoracic radiology manually tagged each study. The fat density threshold was from -190 HU to -30 HU. The robustness of measurements was assessed with Syngo.via.
Equipment
We performed chest ULDCT studies on Toshiba Aquilion 64 unit using specially designed low-dose protocols for different patient weight categories (up to 69 kg, from 70 to 89 kg, over 90 kg). The scan parameters were as follows: tube voltage (kV) 135 kV, tube current (mA) from 15 mA to 25 mA (depending on weight), tube rotation speed (rotation time) 0.50 sec, 1.484 pitch, slice thickness 1 mm. The scan length was set from lung apex to lung sinuses. All examinations were performed with a radiation dose up to 1 mSv, which meets the criteria of preventive X-ray examinations in the Russian Federation for the adult population.
We performed routine chest CT examinations on Toshiba Aquilion 64 unit with a standard protocol: tube voltage (kV) 120 kV, 50 mA tube current (mA), tube rotation speed (rotation time) 0.50 sec, 0.938 pitch, slice thickness 1 mm.
The institutional review board approved this retrospective study, and written informed consent was waived.
No funding was received for this work.