To develop and validate computed tomography (CT)-based prediction models for malignancy in part-solid pulmonary nodules (PSNs), enhancing clinical decision-making.
Key Findings:
Malignant nodules were associated with older age (59 ± 10 vs. 56 ± 11 years, p = 0.018) and female predominance (62.6% vs. 43.3%, P = 0.006).
Specific CT features (irregular shape, lobulation, spiculation) were significantly more common in malignant nodules (all P < 0.05).
Vascular patterns IV (interruption) and V (distortion) were significantly more prevalent in malignant nodules (43.9% vs. 14.4%, and 51.4% vs. 5.2%, respectively; both P < 0.001).
Model 2, incorporating vascular types IV and V, showed superior predictive performance with AUC of 0.916 in training and 0.898 in testing.
Interpretation:
Qualitative CT assessment of vascular interruption and distortion significantly enhances malignancy prediction in PSNs compared to conventional morphological features.
Limitations:
Retrospective design may introduce selection bias, affecting the reliability of results.
Single-center study limits generalizability to broader populations.
Conclusion:
Integrating vascular patterns into CT assessments offers excellent diagnostic accuracy and clinical utility for preoperative risk stratification of PSNs, potentially improving patient management.
