将皮肤镜图像、毫米级尺度和患者信息融合，提升皮肤病变分类准确率。
GraphDerm: Fusing Imaging, Physical Scale, and Metadata in a Population-Graph Classifier for Dermoscopic Lesions
- 构建包含图像、物理尺度和患者信息的图神经网络模型
- 在ISIC-2019数据集上达到0.9812的AUC，显著优于纯图像模型
- 稀疏图结构仍保持高精度，适合实际部署
皮肤镜检查有助于黑色素瘤分诊，但仅依赖图像的AI模型常忽略患者年龄、性别、病灶位置等元数据及几何分析所需的毫米级尺度。本文提出GraphDerm，一种融合影像、毫米级校准与元数据的群体图分类框架，据我们所知是首个在ISIC规模上应用GNN的皮肤镜分类方法。通过整合ISIC 2018/2019数据集，合成嵌入标尺的图像并生成精确掩码，训练U-Net（SE-ResNet-18）完成病灶与标尺分割，利用标尺掩码两点相关性，通过轻量1D-CNN回归像素/毫米数，实现毫米级尺度估计。从病灶掩码中提取真实尺度特征（面积、周长、回转半径）。节点特征采用EfficientNet-B3；边编码元数据与几何相似性（全连接或阈值化）。采用谱图神经网络进行半监督节点分类，图像模型为基线。结果：标尺与病灶分割的Dice系数分别为0.904和0.908；尺度回归的平均绝对误差为1.5像素（均方根误差6.6）。图模型获得0.9812的AUC，阈值化边约保留25%边时，仍保持0.9788的AUC（图像基线为0.9440），各分类器的AUC普遍在0.97~0.99之间。结论：将校准尺度、病变几何与元数据统一于群体图中，在ISIC-2019上显著优于纯图像流程。稀疏图保持近优性能，表明具备高效部署潜力。具备尺度感知的图模型是皮肤镜辅助决策的有前景方向，未来将优化学习边语义并在更广泛标注基准上评估。
原文摘要 · Abstract (English)
Introduction. Dermoscopy aids melanoma triage, yet image-only AI often ignores patient metadata (age, sex, site) and the physical scale needed for geometric analysis. We present GraphDerm, a population-graph framework that fuses imaging, millimeter-scale calibration, and metadata for multiclass dermoscopic classification, to the best of our knowledge the first ISIC-scale application of GNNs to dermoscopy. Methods. We curate ISIC 2018/2019, synthesize ruler-embedded images with exact masks, and train U-Nets (SE-ResNet-18) for lesion and ruler segmentation. Pixels-per-millimeter are regressed from the ruler-mask two-point correlation via a lightweight 1D-CNN. From lesion masks we compute real-scale descriptors (area, perimeter, radius of gyration). Node features use EfficientNet-B3; edges encode metadata/geometry similarity (fully weighted or thresholded). A spectral GNN performs semi-supervised node classification; an image-only ANN is the baseline. Results. Ruler and lesion segmentation reach Dice 0.904 and 0.908; scale regression attains MAE 1.5 px (RMSE 6.6). The graph attains AUC 0.9812, with a thresholded variant using about 25% of edges preserving AUC 0.9788 (vs. 0.9440 for the image-only baseline); per-class AUCs typically fall in the 0.97-0.99 range. Conclusion. Unifying calibrated scale, lesion geometry, and metadata in a population graph yields substantial gains over image-only pipelines on ISIC-2019. Sparser graphs retain near-optimal accuracy, suggesting efficient deployment. Scale-aware, graph-based AI is a promising direction for dermoscopic decision support; future work will refine learned edge semantics and evaluate on broader curated benchmarks.
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。