用超像素修正边界，提升弱监督病理图像分割精度
Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images
- 通过超像素聚类与洪水填充优化特征图边界
- 在乳腺癌数据集上达71.08% mIoU，边界更清晰
- 适合需要低标注成本的病理图像分割场景
随着深度学习快速发展，计算病理学在癌症诊断与分型方面取得显著进展。组织分割是核心挑战，对预后和治疗决策至关重要。弱监督语义分割（WSSS）通过使用图像级标签替代像素级标签，降低了标注成本。然而，基于类别激活图（CAM）的方法仍存在空间分辨率低、边界模糊的问题。为此，我们提出一种多层级超像素修正算法，利用超像素聚类与洪水填充技术精修CAM边界。实验结果表明，该方法在乳腺癌分割数据集上达到71.08%的mIoU，显著改善了肿瘤微环境边界的识别效果。
原文摘要 · Abstract (English)
With the rapid advancement of deep learning, computational pathology has made significant progress in cancer diagnosis and subtyping. Tissue segmentation is a core challenge, essential for prognosis and treatment decisions. Weakly supervised semantic segmentation (WSSS) reduces the annotation requirement by using image-level labels instead of pixel-level ones. However, Class Activation Map (CAM)-based methods still suffer from low spatial resolution and unclear boundaries. To address these issues, we propose a multi-level superpixel correction algorithm that refines CAM boundaries using superpixel clustering and floodfill. Experimental results show that our method achieves great performance on breast cancer segmentation dataset with mIoU of 71.08%, significantly improving tumor microenvironment boundary delineation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。