Scholarlink

<p>Deep learning algorithms for detecting micrometastasis in breast cancer lymph nodes show promising results when used complementarily to improve the efficiency of pathologists’ routines. However, in the current literature, there are critical limitations, poor performance on isolated tumor cells (detection rates&lt;40%), and high false-positive rates due to confusion with nerves or contamination. In this article, we introduce MRNet, a novel multi-resolution dual-task framework that addresses these challenges through task-optimized resolution processing and annotation imprecision handling. Unlike existing approaches that use uniform resolution, our method employs high-resolution patches (level 0) for classification to capture subtle micrometastatic features, while using moderate resolution (level 3) for segmentation to mitigate annotation imprecision inherent in histopathological datasets. Our preprocessing pipeline enables efficient processing of gigapixel whole-slide images without resolution loss, while post-processing reconstruction maintains spatial coherence. We achieved state-of-the-art classification performance with area under the curve <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(= 0.998\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo>=</mo> <mn>0.998</mn> </mrow> </math></EquationSource> </InlineEquation>, while reaching free response operating characteristic<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\( = 0.6124\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo>=</mo> <mn>0.6124</mn> </mrow> </math></EquationSource> </InlineEquation> in localization tasks. Most significantly, our multi-resolution strategy demonstrates that the disconnect between patch-level and slide-level performance in existing methods can be systematically addressed through resolution-aware design.</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

MRNet: A Multi-Resolution Dual-Task Framework for Micrometastases Detection in Breast Cancer Sentinel Lymph Nodes

  • 期刊论文

  • 发表日期：

    2026年4月6日

查看全文
  • Gabriela Kuhn,
  • João B. Rodrigues Neto,
  • Felipe André Zeiser,
  • Mateus Henrique Zeiser,
  • Adriana Vial Roehe,
  • Cristiano André da Costa,
  • Gabriel de Oliveira Ramos

摘要

Deep learning algorithms for detecting micrometastasis in breast cancer lymph nodes show promising results when used complementarily to improve the efficiency of pathologists’ routines. However, in the current literature, there are critical limitations, poor performance on isolated tumor cells (detection rates<40%), and high false-positive rates due to confusion with nerves or contamination. In this article, we introduce MRNet, a novel multi-resolution dual-task framework that addresses these challenges through task-optimized resolution processing and annotation imprecision handling. Unlike existing approaches that use uniform resolution, our method employs high-resolution patches (level 0) for classification to capture subtle micrometastatic features, while using moderate resolution (level 3) for segmentation to mitigate annotation imprecision inherent in histopathological datasets. Our preprocessing pipeline enables efficient processing of gigapixel whole-slide images without resolution loss, while post-processing reconstruction maintains spatial coherence. We achieved state-of-the-art classification performance with area under the curve \(= 0.998\) = 0.998 , while reaching free response operating characteristic \( = 0.6124\) = 0.6124 in localization tasks. Most significantly, our multi-resolution strategy demonstrates that the disconnect between patch-level and slide-level performance in existing methods can be systematically addressed through resolution-aware design.