arXiv 2512.069492026-05-11cs.CV

我们能否超越视觉特征？面向非黑色素瘤皮肤组织病理学的神经组织关系建模

Can We Go Beyond Visual Features? Neural Tissue Relation Modeling for Relational Graph Analysis in Non-Melanoma Skin Histology

Mohamed bin Zayed University of AI（Mohamed bin Zayed人工智能大学）；School of Information and Data Sciences（信息与数据科学学院）；Vellore Institute of Technology（维洛雷理工学院）；Loughborough University（洛桑大学）；MD Anderson Cancer Center, The University of Texas（MD安德森癌症中心，德克萨斯大学）

Shravan Venkatraman, Muthu Subash Kavitha, Joe Dhanith P R, V Manikandarajan, Jia Wu

备注：: CVPR 2026 Workshops

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出神经组织关系建模（NTRM），通过引入组织级图神经网络，改进皮肤病理学图像分割，提升对组织间关系的建模能力，在非黑色素瘤皮肤癌分割数据集上取得更优性能。

摘要：

组织病理学图像分割对于皮肤癌诊断中的组织结构界定至关重要，但建模空间上下文和组织间关系仍具挑战性，特别是在重叠或形态相似的组织区域。当前基于卷积神经网络（CNN）的方法主要依赖视觉纹理，通常将组织视为独立区域，难以编码生物上下文。为此，我们引入神经组织关系建模（NTRM），一种新的分割框架，通过在CNN中引入组织级图神经网络，建模不同组织类型间的空间和功能关系。NTRM在预测的区域上构建图，通过信息传递传播上下文信息，并通过空间投影优化分割。与先前方法不同，NTRM明确编码组织间依赖关系，使边界密集区域的预测更加结构化。在非黑色素瘤皮肤癌分割基准数据集上，NTRM优于现有最先进方法，其Dice相似度系数比评估方法中表现最好的模型高4.9%至31.25%。我们的实验表明，关系建模相比缺乏组织级结构意识的局部感受野架构，提供了更原理化的路径，以实现更上下文感知和可解释的组织学分割。我们的代码可在https://github.com/shravan-18/NTRM获取。

英文摘要：

Histopathology image segmentation is essential for delineating tissue structures in skin cancer diagnostics, but modeling spatial context and inter-tissue relationships remains a challenge, especially in regions with overlapping or morphologically similar tissues. Current convolutional neural network (CNN)-based approaches operate primarily on visual texture, often treating tissues as independent regions and failing to encode biological context. To this end, we introduce Neural Tissue Relation Modeling (NTRM), a novel segmentation framework that augments CNNs with a tissue-level graph neural network to model spatial and functional relationships across tissue types. NTRM constructs a graph over predicted regions, propagates contextual information via message passing, and refines segmentation through spatial projection. Unlike prior methods, NTRM explicitly encodes inter-tissue dependencies, enabling structurally coherent predictions in boundary-dense zones. On the benchmark Histopathology Non-Melanoma Skin Cancer Segmentation Dataset, NTRM outperforms state-of-the-art methods, achieving a robust Dice similarity coefficient that is 4.9\% to 31.25\% higher than the best-performing models among the evaluated approaches. Our experiments indicate that relational modeling offers a principled path toward more context-aware and interpretable histological segmentation, compared to local receptive-field architectures that lack tissue-level structural awareness. Our code is available at https://github.com/shravan-18/NTRM.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。