CT-based Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma ≤ 3 cm: Enhancing Deep Learning Specificity by Waiving Chest Wall Information

Clinical Snapshot

Key Findings

• P Value: Not reported for primary comparison

• Effect Size: AUC 0.91 for VPI-DL model

• Primary Outcome: Prediction accuracy of visceral pleural invasion in lung adenocarcinoma ≤3cm

• Nnt Or Sensitivity: Sensitivity 91%, Specificity 82%, superior to CTR (specificity 63%) and expert assessment (specificity 57%)

• Confidence Interval: Not explicitly reported

Clinical Application

High feasibility as CT imaging is standard preoperative assessment; requires implementation of deep learning infrastructure Relevant to Australian thoracic surgery practice; aligns with NCCN guidelines adopted by Cancer Australia; may require TGA approval for clinical implementation as medical device software Patients with lung adenocarcinoma ≤3cm being considered for surgical resection

Abstract

BACKGROUND: Accurate preoperative prediction of visceral pleural invasion (VPI) in lung adenocarcinoma is essential for guiding surgical decision-making. However, existing prediction models often sacrifice specificity when optimized for high sensitivity, increasing the risk of overtreatment. This study aimed to develop a computed tomography (CT)-based deep learning (DL) model that improves specificity by excluding chest wall information. METHODS: We retrospectively enrolled 835 patients with pathologically confirmed lung adenocarcinoma who underwent complete resection at two medical centers. A VPI-DL model was developed using a four-layer convolutional neural network incorporating a novel attention mechanism trained on chest-wall-masked CT inputs. The model was trained on 692 cases and externally validated on an independent cohort of 143 patients. Performance was benchmarked against the consolidation-to-tumor ratio (CTR), a published DL model, and assessments by three thoracic surgeons. Evaluation metrics included area under the curve (AUC), sensitivity, specificity, and accuracy under a high-sensitivity operating threshold. RESULTS: In external validation, VPI-DL achieved an AUC of 0.91, sensitivity of 91%, specificity of 82%, and accuracy of 83%, outperforming the CTR (specificity 63%), the previously published model (specificity 54%), and thoracic surgeons (specificity 57%) at comparable sensitivity levels. The attention-guided architecture effectively reduced spurious correlations and improved interpretability. CONCLUSION: The proposed VPI-DL model improves the specificity of VPI prediction while preserving high sensitivity. By intentionally excluding chest wall information, the model offers a robust and interpretable tool to aid preoperative planning and minimize the risk of both under- and overtreatment in early-stage lung adenocarcinoma.

References

1. 1.Ou, D. X., Chen, L. W., Chen, K. Y., Wang, H. J., Yang, S. M., Hsieh, M. S., Chou, L. C., Yang, C. F. J., Chang, Y. C., Lin, M. W., Chen, C. M., & Chen, J. S. (2026). CT-based prediction of visceral pleural invasion in lung adenocarcinoma ≤ 3 cm: Enhancing deep learning specificity by waiving chest wall information. Annals of Surgical Oncology. https://doi.org/10.3390/diagnostics12020298