Artificial intelligence for automated thoracic aorta diameter measurement using different computed tomography protocols

Introduction Thoracic aortic aneurysm diameter determination is paramount for the decision-making process regarding surgical management. Studies focusing in asymptomatic patients have determined prevalence of 0.16 to 0.36% of TAAs in imaging studies. Several groups have proposed automated aortic measurement tools as propaedeutic and therapeutic instruments. In this study we developed and tested an automatic 3-dimensional (3D) segmentation method for the thoracic aorta, applicable on computed tomography angiography (CTA) acquired using low-dose and standard dose protocol, with and without contrast enhancement; and to accurately calculate the 3D diameter information of the arterial segments. Methods a retrospective cohort of all CT scans acquired in our service between 2016 and 2021 led to the selection of 587 CT exams including low and standard-dose radiation, with and without contrast enhancement. 527 exams were used for neural network training of an algorithm capable of aptly measuring the aortic diameters, using manual measurements performed by three medical specialists as a baseline. Sixty exams were used for validation. The algorithm was developed both for use with the support of PyRadiomics and for a self-made approach. Results Aortic measurement using the algorithm supported by PyRadiomics resulted in mean absolute error values under 2mm. For the self-made approach, mean absolute error values were under 5mm. Conclusion This study presents an effective automated solution for thoracic aortic measurement with good results in sets of standard or low-radiation exams, as well as those acquired with or without contrast enhancement; presenting a possibility for an auxiliary tool for automation of the process of measuring the diameter of the thoracic aorta. ### Competing Interest Statement This research was funded by the Hospital Israelita Albert Einstein Technological Innovation Centre, in partnership with the General Electric Healthcare company, under portents of the Law 8.248, of the 23rd of October of 1991. ### Funding Statement This study was funded by the Hospital Israelita Albert Einstein Technological Innovation Centre, in partnership with the General Electric Healthcare company, under portents of the Law 8.248, of the 23rd of October of 1991. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Ethics committee of Hospital Israelita Albert Einstein gave ethical approval for this work I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable. Yes All data produced in the present study are available upon reasonable request to the authors.