Scholarlink

<p>This study presents an integrated multitask deep learning framework for the automated analysis of acral melanoma from whole-slide images (WSIs). We constructed a multiscale WSI dataset with pixel-level annotations and developed a pipeline that sequentially performs classification, segmentation, and morphological quantification. An optimized ResNet50 classifier first screens for malignancy. For malignant cases, our novel D3C-RS-Unet, which integrates dual dilated dynamic convolution and channel attention mechanisms, performs precise tumor segmentation. Finally, key morphological indicators are automatically extracted. Using patient-level fivefold cross-validation, the classifier achieved an accuracy of 0.8947 ± 0.0098. The D3C-RS-Unet significantly outperformed baseline and state-of-the-art models (Dice: 0.8427 ± 0.0057; IoU: 0.8053 ± 0.0071; <i>p</i><sub>adj</sub> &lt; 0.05). Extracted morphological metrics showed excellent agreement with manual annotations (ICCs &gt; 0.93). This end-to-end framework provides objective, reproducible quantitative data, demonstrating significant potential to assist pathological diagnosis and standardize reporting in acral melanoma.</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

A Multitask Deep Learning Approach for Tumor Segmentation and Morphological Quantification in Acral Melanoma Whole-Slide Images

  • 期刊论文

  • 发表日期：

    2026年3月31日

查看全文
  • Xiaodong An,
  • Liu Liu,
  • Mengmeng Liu,
  • Jianwei Liu

摘要

This study presents an integrated multitask deep learning framework for the automated analysis of acral melanoma from whole-slide images (WSIs). We constructed a multiscale WSI dataset with pixel-level annotations and developed a pipeline that sequentially performs classification, segmentation, and morphological quantification. An optimized ResNet50 classifier first screens for malignancy. For malignant cases, our novel D3C-RS-Unet, which integrates dual dilated dynamic convolution and channel attention mechanisms, performs precise tumor segmentation. Finally, key morphological indicators are automatically extracted. Using patient-level fivefold cross-validation, the classifier achieved an accuracy of 0.8947 ± 0.0098. The D3C-RS-Unet significantly outperformed baseline and state-of-the-art models (Dice: 0.8427 ± 0.0057; IoU: 0.8053 ± 0.0071; padj < 0.05). Extracted morphological metrics showed excellent agreement with manual annotations (ICCs > 0.93). This end-to-end framework provides objective, reproducible quantitative data, demonstrating significant potential to assist pathological diagnosis and standardize reporting in acral melanoma.