Scholarlink

<p>Accurate segmentation in medical imaging requires loss functions that capture both regional overlap and boundary alignment. This study evaluates composite losses combining binary cross-entropy (BCE) and a boundary-based term under fixed and adaptive weighting schemes, using U-Net and SwinUNETR on the MM-WHS dataset. For U-Net, a small boundary contribution with adaptive weighting yielded the best results: Standard SoftAdapt (90/10 BCE + BoundaryDoU) achieved the highest Dice score (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(0.932 \pm 0.01\)</EquationSource> </InlineEquation>), surpassing both the baseline (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(0.923 \pm 0.01\)</EquationSource> </InlineEquation>) and fixed ratios. In contrast, SwinUNETR achieved its strongest performance with a fixed 70% BCE + 10% boundary ratio (0.919 ± 0.02). The result showed that combining a boundary-based loss term helps improve the segmentation accuracy. However, the performance gain is dependent on the architecture of the segmentation model; convolution-based U-Net benefited from the adaptive loss weighting scheme, whereas Transformer-based SwinUNETR without strong inductive bias did not benefit from increased influence of the boundary loss term.</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

Adaptive composite loss for volumetric whole heart segmentation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月25日

查看全文
  • Krittanat Sutassananon,
  • Worapan Kusakunniran,
  • Mehmet Orgun,
  • Thanongchai Siriapisith

摘要

Accurate segmentation in medical imaging requires loss functions that capture both regional overlap and boundary alignment. This study evaluates composite losses combining binary cross-entropy (BCE) and a boundary-based term under fixed and adaptive weighting schemes, using U-Net and SwinUNETR on the MM-WHS dataset. For U-Net, a small boundary contribution with adaptive weighting yielded the best results: Standard SoftAdapt (90/10 BCE + BoundaryDoU) achieved the highest Dice score ( \(0.932 \pm 0.01\) ), surpassing both the baseline ( \(0.923 \pm 0.01\) ) and fixed ratios. In contrast, SwinUNETR achieved its strongest performance with a fixed 70% BCE + 10% boundary ratio (0.919 ± 0.02). The result showed that combining a boundary-based loss term helps improve the segmentation accuracy. However, the performance gain is dependent on the architecture of the segmentation model; convolution-based U-Net benefited from the adaptive loss weighting scheme, whereas Transformer-based SwinUNETR without strong inductive bias did not benefit from increased influence of the boundary loss term.