# New Insights into Molecular Mechanisms and Radiomics in Non-Contrast CT for Aortic Dissection: A Case Report and Literature Review

## TL;DR

This paper discusses how non-contrast CT scans, combined with AI and molecular insights, can help detect aortic dissection when contrast imaging is not possible.

## Contribution

The paper introduces the potential of AI and radiomic analysis to enhance non-contrast CT for aortic dissection diagnosis and link imaging features to molecular mechanisms.

## Key findings

- Non-contrast CT can reveal critical signs of aortic dissection in patients unable to receive contrast.
- AI and radiomic analysis may detect subtle imaging features related to molecular changes in aortic dissection.
- Combining AI interpretation with molecular insights could improve diagnosis and treatment strategies.

## Abstract

Background: Computed tomography (CT) angiography is widely regarded as the gold standard for diagnosing acute aortic dissection. However, in patients with contraindications to iodinated contrast media, such as those with renal insufficiency or hemodynamic instability, non-contrast CT may offer a viable alternative for initial evaluation. Understanding the molecular mechanisms underlying aortic dissection, including extracellular matrix degradation, smooth muscle cell apoptosis, and inflammatory pathways, is crucial for developing novel diagnostic and therapeutic approaches. This report describes a single case of acute Stanford type A aortic dissection initially detected on non-contrast CT. Case Presentation: We describe a 74-year-old man who presented to the emergency department with fever and suspected infection, but without chest pain. An incidental finding on non-contrast CT revealed ascending aortic dilatation, pericardial effusion, and a suspected intimal flap. Subsequent CT angiography confirmed a Stanford type A aortic dissection. Conclusions: This case highlights the potential value of non-contrast CT in the early detection of aortic dissection, particularly when CT angiography cannot be performed. Recent advances in artificial intelligence (AI) and radiomic analysis have shown promise in augmenting the diagnostic capabilities of non-contrast CT by identifying subtle imaging features that may correlate with underlying molecular pathology and elude human observers. Emerging evidence suggests that radiomic features may reflect molecular alterations in the aortic wall, including metalloproteinase activity, collagen degradation, and inflammatory cell infiltration. Incorporating AI-assisted interpretation alongside insights into molecular mechanisms could facilitate earlier diagnosis, improve risk stratification, and guide personalized treatment strategies in critically ill patients. Although non-contrast CT has limited sensitivity for aortic dissection, it may still reveal crucial findings in selected cases and should be considered when contrast-enhanced imaging is not feasible. Ongoing progress in AI, radiomics, and molecular biomarker research may further expand the clinical applications of non-contrast CT in emergency cardiovascular care and bridge the gap between imaging phenotypes and molecular endotypes. These findings are hypothesis-generating and require validation in larger cohorts before clinical generalization.