Scholarlink

Background <p>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.</p> Methods <p>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.</p> Results <p>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.</p> Conclusion <p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 发表日期：

    2026年1月21日

查看全文
  • De-Xiang Ou,
  • Li-Wei Chen,
  • Kuan-Yu Chen,
  • Hao-Jen Wang,
  • Shun-Mao Yang,
  • Min-Shu Hsieh,
  • Li-Chieh Chou,
  • Chi-Fu Jeffrey Yang,
  • Yeun-Chung Chang,
  • Mong-Wei Lin,
  • Chung-Ming Chen,
  • Jin-Shing Chen

摘要

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.