Scholarlink

Purpose <p>Automated coronary artery segmentation from computed tomography coronary angiography (CTCA) can support quantitative analysis, yet performance varies with data characteristics and model configuration. This study systematically evaluates how dataset size, computed tomography (CT) window width and level (W/L) values, model architectures, and vessel geometry affect nnU-Net–based coronary artery segmentation.</p> Methods <p>Using 1000 annotated CTCA scans from the publicly available ImageCAS dataset, we conducted a series of experiments in which we varied the number of training cases, applied different W/L values, compared 2D and multiple 3D nnU-Net architectures (Full-Resolution, Low-Resolution, Cascade, and ensemble), and assessed performance across vessel curvature and tortuosity. All models were evaluated on an independent 200-case test set using Dice similarity coefficient (DSC) and intersection over union (IoU).</p> Results <p>Segmentation performance increased with dataset size and plateaued beyond 100 training cases. W/L values of 800/200 Hounsfield units (HU) and 1300/350 HU slightly improved performance over original images. 3D models outperformed the 2D model, with the 3D ensemble achieving the highest accuracy (DSC 0.8337; 95% confidence interval [CI]: 0.8269–0.8405, IoU 0.7178; 95% CI: 0.7080–0.7275). Performance remained consistent across vessels with different curvature and tortuosity, indicating model robustness to geometric complexity.</p> Conclusion <p>The nnU-Net framework achieves accurate and generalizable coronary artery segmentation across diverse dataset sizes, W/L values, model architectures, and vessel geometries. Optimizing input settings and architectural strategies further enhances segmentation accuracy.</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

Design Rules for Robust Coronary Artery Segmentation: A Systematic Analysis of Dataset Size, Windowing, Architectures, and Vessel Geometry

  • 期刊论文

  • 发表日期：

    2026年1月9日

查看全文
  • Ming-Hui Hung,
  • Yu-Wei Chiang,
  • Hao-Yun Liu,
  • Han-Hsuan Chu,
  • Yu-Sen Huang,
  • Pin-Yi Chiang,
  • Hsin-Ming Chen,
  • Tzung-Dau Wang,
  • Shyh-Jye Chen,
  • Wen-Jeng Lee

摘要

Purpose

Automated coronary artery segmentation from computed tomography coronary angiography (CTCA) can support quantitative analysis, yet performance varies with data characteristics and model configuration. This study systematically evaluates how dataset size, computed tomography (CT) window width and level (W/L) values, model architectures, and vessel geometry affect nnU-Net–based coronary artery segmentation.

Methods

Using 1000 annotated CTCA scans from the publicly available ImageCAS dataset, we conducted a series of experiments in which we varied the number of training cases, applied different W/L values, compared 2D and multiple 3D nnU-Net architectures (Full-Resolution, Low-Resolution, Cascade, and ensemble), and assessed performance across vessel curvature and tortuosity. All models were evaluated on an independent 200-case test set using Dice similarity coefficient (DSC) and intersection over union (IoU).

Results

Segmentation performance increased with dataset size and plateaued beyond 100 training cases. W/L values of 800/200 Hounsfield units (HU) and 1300/350 HU slightly improved performance over original images. 3D models outperformed the 2D model, with the 3D ensemble achieving the highest accuracy (DSC 0.8337; 95% confidence interval [CI]: 0.8269–0.8405, IoU 0.7178; 95% CI: 0.7080–0.7275). Performance remained consistent across vessels with different curvature and tortuosity, indicating model robustness to geometric complexity.

Conclusion

The nnU-Net framework achieves accurate and generalizable coronary artery segmentation across diverse dataset sizes, W/L values, model architectures, and vessel geometries. Optimizing input settings and architectural strategies further enhances segmentation accuracy.