Scholarlink

<p>Precise liver tumor segmentation is essential for reliable clinical decision-making, particularly for treatment planning and quantitative assessment. To improve segmentation robustness under heterogeneous image quality and complex tumor appearance, we propose QCSeg-Net, a quality-controlled, coarse-to-fine framework consisting of tumor-presence classification (FALC-Net), image quality screening (IQS-Net), and refined segmentation via RGA-TransUNet. The framework first removes tumor-free slices to reduce redundant computation, then filters degraded images to ensure consistent input quality, and finally performs fine-grained segmentation using multi-scale receptive-field aggregation and a residual-guided Transformer module. Experiments on a liver tumor CT dataset from the Hunan University of Medicine General Hospital demonstrate that QCSeg-Net achieves a 2.09% improvement in IoU over advanced baseline models, while also exhibiting higher stability on small-volume and low-contrast tumors. These results highlight the potential of QCSeg-Net for intelligent auxiliary diagnosis of liver tumors in clinical applications. Code: <a href="https://github.com/luo-ming-hao/QCSeg-Net">https://github.com/luo-ming-hao/QCSeg-Net</a>.</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

QCSeg-Net: a multi-stage quality-controlled liver tumor segmentation model for AI-assisted diagnosis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月18日

查看全文
  • Minghao Luo,
  • Jinghong Wang,
  • Jing Zhou,
  • Jia Wu

摘要

Precise liver tumor segmentation is essential for reliable clinical decision-making, particularly for treatment planning and quantitative assessment. To improve segmentation robustness under heterogeneous image quality and complex tumor appearance, we propose QCSeg-Net, a quality-controlled, coarse-to-fine framework consisting of tumor-presence classification (FALC-Net), image quality screening (IQS-Net), and refined segmentation via RGA-TransUNet. The framework first removes tumor-free slices to reduce redundant computation, then filters degraded images to ensure consistent input quality, and finally performs fine-grained segmentation using multi-scale receptive-field aggregation and a residual-guided Transformer module. Experiments on a liver tumor CT dataset from the Hunan University of Medicine General Hospital demonstrate that QCSeg-Net achieves a 2.09% improvement in IoU over advanced baseline models, while also exhibiting higher stability on small-volume and low-contrast tumors. These results highlight the potential of QCSeg-Net for intelligent auxiliary diagnosis of liver tumors in clinical applications. Code: https://github.com/luo-ming-hao/QCSeg-Net.