Scholarlink

Objective <p>To develop and validate a high-fidelity super-resolution (SR)-enhanced radiomics framework using a Residual Channel Attention Network (RCAN) for non-invasive EGFR mutation prediction in lung adenocarcinoma (LUAD).</p> Methods <p>This retrospective multi-center study included 373 patients, partitioned into training (<i>n</i> = 298) and testing (<i>n</i> = 75) sets. CT images were reconstructed to a 1024 × 1024 matrix via RCAN to restore latent high-frequency textures. A standardized pipeline—including ComBat harmonization, ICC-based fidelity filtering, and LASSO regression—was employed to extract and select resolution-invariant features. Five machine learning classifiers were evaluated, and a combined nomogram integrated the SR-enhanced signature with clinical predictors. Model performance was assessed using AUC, DeLong tests, and decision curve analysis (DCA), with interpretability provided by SHAP analysis.</p> Results <p>The SR-enhanced model significantly outperformed the original-resolution (OR) baseline, increasing the AUC from 0.60 (95% CI: 0.47–0.74) to 0.84 (95% CI: 0.75–0.93) in the testing set (<i>P</i> &lt; 0.001). Consistent performance was maintained across imaging centers (<i>P</i> = 0.555) and histological subtypes. The combined nomogram achieved a robust AUC of 0.86 (95% CI: 0.78–0.94), demonstrating superior calibration and clinical net benefit. SHAP analysis revealed that glszm_ZoneVariance—a marker of intratumoral heterogeneity—was the predominant predictor revealed via SR reconstruction.</p> Conclusion <p>RCAN-driven SR reconstruction effectively addresses CT resolution limitations, capturing fine-grained radiogenomic signatures critical for molecular phenotyping. This high-fidelity framework offers a robust, non-invasive decision-support tool for personalized precision oncology in LUAD.</p> Graphical Abstract <p></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

High-fidelity super-resolution CT radiomics for non-invasive EGFR mutation prediction in lung adenocarcinoma: a multi-center pooled analysis

  • 期刊论文

  • 发表日期：

    2026年6月24日

查看全文
  • Mao-Tong Liu,
  • Tao Zhang,
  • Ming Li

摘要

Objective

To develop and validate a high-fidelity super-resolution (SR)-enhanced radiomics framework using a Residual Channel Attention Network (RCAN) for non-invasive EGFR mutation prediction in lung adenocarcinoma (LUAD).

Methods

This retrospective multi-center study included 373 patients, partitioned into training (n = 298) and testing (n = 75) sets. CT images were reconstructed to a 1024 × 1024 matrix via RCAN to restore latent high-frequency textures. A standardized pipeline—including ComBat harmonization, ICC-based fidelity filtering, and LASSO regression—was employed to extract and select resolution-invariant features. Five machine learning classifiers were evaluated, and a combined nomogram integrated the SR-enhanced signature with clinical predictors. Model performance was assessed using AUC, DeLong tests, and decision curve analysis (DCA), with interpretability provided by SHAP analysis.

Results

The SR-enhanced model significantly outperformed the original-resolution (OR) baseline, increasing the AUC from 0.60 (95% CI: 0.47–0.74) to 0.84 (95% CI: 0.75–0.93) in the testing set (P < 0.001). Consistent performance was maintained across imaging centers (P = 0.555) and histological subtypes. The combined nomogram achieved a robust AUC of 0.86 (95% CI: 0.78–0.94), demonstrating superior calibration and clinical net benefit. SHAP analysis revealed that glszm_ZoneVariance—a marker of intratumoral heterogeneity—was the predominant predictor revealed via SR reconstruction.

Conclusion

RCAN-driven SR reconstruction effectively addresses CT resolution limitations, capturing fine-grained radiogenomic signatures critical for molecular phenotyping. This high-fidelity framework offers a robust, non-invasive decision-support tool for personalized precision oncology in LUAD.

Graphical Abstract