Advancements in Computed Tomography Analysis for Thoracic Aortic Surgery: The Expanding Role of Automation

Computed tomography (CT) is crucial for evaluating complex aortic anatomy, facilitating surgical planning, and improving patient outcomes in thoracic aortic surgery. Recent advancements in artificial intelligence (AI)-driven tools offer potential improvements in diagnostic accuracy and interventional planning through automated segmentation and feature extraction. We conducted a systematic review of AI-based tools for aortic CT imaging, focusing on machine learning and deep learning algorithms used in segmentation and feature extraction. Databases searched included PubMed, Embase, and IEEE Xplore, using terms such as “Thoracic Aortic Surgery”, “CT Imaging”, “Segmentation”, and “Outcome Prediction”. This review identified high-performance segmentation models, including U-Net and convolutional neural network (CNN) architectures. Radiomic analyses and automated features demonstrated correlations with surgical outcomes, such as aneurysm growth rates and thrombus assessment. AI-driven automation in CT imaging is an expanding field with potential to improve diagnosis, operative planning, and prognostication in aortic pathologies. Further refinement and integration of these tools in clinical practice could improve diagnostics and management for patients with thoracic aortic disease.