文章：

多模态图神经网络在宫颈镜检查数据分类与可视化中的应用

Multi-Modal Graph Neural Networks for Colposcopy Data Classification and Visualization

原文发布日期：30 April 2025

DOI: 10.3390/cancers17091521

类型: Article

开放获取: 是

英文摘要：

Background: Cervical lesion classification is essential for early detection of cervical cancer. While deep learning methods have shown promise, most rely on single-modal data or require extensive manual annotations. This study proposes a novel Graph Neural Network (GNN)-based framework that integrates colposcopy images, segmentation masks, and graph representations for improved lesion classification. Methods: We developed a fully connected graph-based architecture using GCNConv layers with global mean pooling and optimized it via grid search. A five-fold cross-validation protocol was employed to evaluate performance before (1–100 epochs) and after fine-tuning (101–151 epochs). Performance metrics included macro-average F1-score and validation accuracy. Visualizations were used for model interpretability. Results: The model achieved a macro-average F1-score of 89.4% and validation accuracy of 92.1% before fine-tuning, which improved to 94.56% and 98.98%, respectively, after fine-tuning. LIME-based visual explanations validated models focus on discriminative lesion regions. Conclusions: This study highlights the potential of graph-based multi-modal learning for cervical lesion analysis. Collaborating with the MNJ Institute of Oncology, the framework shows promise for clinical use.

摘要翻译： 

背景：宫颈病变分类对宫颈癌早期检测至关重要。深度学习虽展现出潜力，但现有方法多依赖单模态数据或需大量人工标注。本研究提出一种基于图神经网络（GNN）的新型框架，通过整合阴道镜图像、分割掩码和图表示来提升病变分类性能。 方法：我们采用GCNConv层与全局平均池化构建全连接图架构，并通过网格搜索优化参数。采用五折交叉验证评估模型在微调前（1-100轮）与微调后（101-151轮）的性能，以宏观平均F1分数和验证准确率为核心指标，并利用可视化技术增强模型可解释性。 结果：微调前模型宏观平均F1分数达89.4%，验证准确率为92.1%；微调后分别提升至94.56%和98.98%。基于LIME的可视化解释证实模型能聚焦于具有鉴别性的病变区域。 结论：本研究揭示了基于图结构的多模态学习在宫颈病变分析中的应用潜力。该框架与MNJ肿瘤研究所合作开发，展现出临床转化前景。

原文链接：

Multi-Modal Graph Neural Networks for Colposcopy Data Classification and Visualization