Scholarlink

Background <p>To develop and validate a deep learning model for automated quantification of abdominal aortic calcification scores (AACS) adhering to the Kauppila protocol, with multicenter clinical validation.</p> Methods <p>This retrospective multicenter study analyzed 2,660 lateral lumbar/thoracoabdominal radiographs from four centers, partitioned into development (training: <i>n</i> = 1,478; validation: <i>n</i> = 423) and test cohorts (internal: <i>n</i> = 211; external: <i>n</i> = 157 from Center C and <i>n</i> = 391 from Center D). We proposed the Lumbar Vertebrae Localization-Contrastive Rank-Aware Network (LVLCRNet), incorporating automatic lumbar vertebrae localization, aortic region segmentation, and contrastive rank-aware network for ordinal classification. Comparative analyses against baseline network and Lumbar Vertebrae Localization Network were conducted using expert-annotated AACS as ground truth (GT), evaluated through Wilcoxon matched-paired signed-rank test, intraclass correlation coefficient (ICC), mean absolute error (MAE), coefficient of determination (R²), Bland-Altman analysis, and multiclass accuracy.</p> Results <p>No significant difference was found between LVLCRNet and GT, whereas the baseline network showed significant deviations from GT across all cohorts (<i>p</i> &lt; 0.017, Bonferroni-corrected). LVLCRNet achieved superior agreement with GT, demonstrating R² of 0.858 (internal) and 0.842/0.837 (external), ICC of 0.916 (internal) and 0.904/0.899 (external), and MAE of 1.547 (internal) and 1.189/1.972 (external). Bland-Altman analysis showed minimal systemic bias. Classification accuracy reached 82.94% (internal) and 79.62%/81.59% (external), outperforming comparators by 5.10–9.98%.</p> Conclusion <p>LVLCRNet provides reliable automated AACS through integrated anatomic localization and contrastive rank-aware learning. Its strong generalizability and precision in severity grading support clinical utility for cardiovascular risk stratification.</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

Automated abdominal aortic calcification scoring via deep learning: a multi-center validation of LVLCRNet

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月1日

查看全文
  • Zhehao Zhang,
  • Zhenhong Shao,
  • Guotian Hu,
  • Xiuchao He,
  • Qingqing Lu,
  • Yuning Pan

摘要

Background

To develop and validate a deep learning model for automated quantification of abdominal aortic calcification scores (AACS) adhering to the Kauppila protocol, with multicenter clinical validation.

Methods

This retrospective multicenter study analyzed 2,660 lateral lumbar/thoracoabdominal radiographs from four centers, partitioned into development (training: n = 1,478; validation: n = 423) and test cohorts (internal: n = 211; external: n = 157 from Center C and n = 391 from Center D). We proposed the Lumbar Vertebrae Localization-Contrastive Rank-Aware Network (LVLCRNet), incorporating automatic lumbar vertebrae localization, aortic region segmentation, and contrastive rank-aware network for ordinal classification. Comparative analyses against baseline network and Lumbar Vertebrae Localization Network were conducted using expert-annotated AACS as ground truth (GT), evaluated through Wilcoxon matched-paired signed-rank test, intraclass correlation coefficient (ICC), mean absolute error (MAE), coefficient of determination (R²), Bland-Altman analysis, and multiclass accuracy.

Results

No significant difference was found between LVLCRNet and GT, whereas the baseline network showed significant deviations from GT across all cohorts (p < 0.017, Bonferroni-corrected). LVLCRNet achieved superior agreement with GT, demonstrating R² of 0.858 (internal) and 0.842/0.837 (external), ICC of 0.916 (internal) and 0.904/0.899 (external), and MAE of 1.547 (internal) and 1.189/1.972 (external). Bland-Altman analysis showed minimal systemic bias. Classification accuracy reached 82.94% (internal) and 79.62%/81.59% (external), outperforming comparators by 5.10–9.98%.

Conclusion

LVLCRNet provides reliable automated AACS through integrated anatomic localization and contrastive rank-aware learning. Its strong generalizability and precision in severity grading support clinical utility for cardiovascular risk stratification.