Aortic wall segmentation in 18F-sodium fluoride PET/CT scans: Head-to-head comparison of artificial intelligence-based versus manual segmentation

• Published in: Journal of nuclear cardiology Vol. 29; no. 4; pp. 2001 - 2010
• Main Authors: Piri, Reza, Edenbrandt, Lars, Larsson, Måns, Enqvist, Olof, Nøddeskou-Fink, Amalie Horstmann, Gerke, Oke, Høilund-Carlsen, Poul Flemming
• Format: Journal Article
• Language: English
• Published: Cham Elsevier Inc 01-08-2022; Springer International Publishing; Springer Nature B.V
• Subjects: Angina pectoris; aorta; Artificial intelligence; Automation; bias; Cardiac and Cardiovascular Systems; Cardiology; Coronary vessels; Fluorides; Imaging; Kardiologi; Medical imaging; Medicine; Medicine & Public Health; Nuclear Medicine; Original Article; PET/CT; Radiology; sodium fluoride; Tomography; CNN; AI; ROI; artificial intelligence; sodium fluoride; CT; VOI; NaF; SUV; PET/CT; bias; aorta; PET
• ISSN: 1071-3581; 1532-6551
• DOI: 10.1007/s12350-021-02649-z

We aimed to establish and test an automated AI-based method for rapid segmentation of the aortic wall in positron emission tomography/computed tomography (PET/CT) scans.
For segmentation of the wall in three sections: the arch, thoracic, and abdominal aorta, we developed a tool based on a convolutional neural network (CNN), available on the Research Consortium for Medical Image Analysis (RECOMIA) platform, capable of segmenting 100 different labels in CT images. It was tested on 18F-sodium fluoride PET/CT scans of 49 subjects (29 healthy controls and 20 angina pectoris patients) and compared to data obtained by manual segmentation. The following derived parameters were compared using Bland–Altman Limits of Agreement: segmented volume, and maximal, mean, and total standardized uptake values (SUVmax, SUVmean, SUVtotal). The repeatability of the manual method was examined in 25 randomly selected scans.
CNN-derived values for volume, SUVmax, and SUVtotal were all slightly, i.e., 13-17%, lower than the corresponding manually obtained ones, whereas SUVmean values for the three aortic sections were virtually identical for the two methods. Manual segmentation lasted typically 1-2 hours per scan compared to about one minute with the CNN-based approach. The maximal deviation at repeat manual segmentation was 6%.
The automated CNN-based approach was much faster and provided parameters that were about 15% lower than the manually obtained values, except for SUVmean values, which were comparable. AI-based segmentation of the aorta already now appears as a trustworthy and fast alternative to slow and cumbersome manual segmentation.