用形状特征提升胶质瘤分级准确率，比传统像素方法更准更省参数。
Shape-Based Inductive Bias for Glioma Grading from Tumor Contours
- 将肿瘤轮廓形状对齐并拆解为频域特征序列，构建形状感知表示
- 模型在BraTS2020数据上达71.5%平衡准确率，低级别胶质瘤F1达54.9%
- 仅需数千到十余万参数，远少于像素模型，适合临床部署
胶质瘤分级常被当作像素问题处理，但真正信号在于形状。本文提出一种基于函数的形状对齐框架，将闭合轮廓分解为全局形变与残差傅里叶形状，并按频率排序组织为令牌。在BraTS~2020肿瘤轮廓的五折患者独立交叉验证中，紧凑型多层感知机（MLP）达到最高均值平衡准确率71.5%，优于ResNet-18的65.9%和ViT-Tiny的63.3%；其平均低级别胶质瘤F1为54.9%。合并外折结果的平衡准确率为72.4%（患者自助法95%置信区间：66.4–77.8%）。所选MLP参数量为2.9k–117.3k，至少比像素基线少46倍。在无噪声模拟中，形状模型表现达56.3–71.5%，而像素模型始终维持在50.0–52.5%。本工作证明，在表示层面引入形状先验可提升可解释性、可扩展性并实现显著降维。
原文摘要 · Abstract (English)
Glioma grading from tumor contours is often treated as a pixel problem even when the signal of interest is shape. We align closed contours with a functional shape-alignment framework, separate global deformation from residual Fourier shape, and organize these quantities as frequency-ordered tokens. In five-fold patient-disjoint cross-validation on BraTS~2020 tumor contours, with model selection performed using grouped inner validation, a compact multilayer perceptron (MLP) achieves the highest mean balanced accuracy at 71.5\%, compared with 65.9\% for ResNet-18 and 63.3\% for ViT-Tiny. It also gives the highest mean low-grade glioma F1 at 54.9\%. Its pooled out-of-fold balanced accuracy is 72.4\% (patient-bootstrap 95\% CI: 66.4--77.8\%). The selected MLPs use 2.9k--117.3k parameters across folds, at least 46 times fewer than the pixel baselines. In a controlled noise-free simulation, shape-based models reach 56.3--71.5\% balanced accuracy while the pixel models remain at 50.0--52.5\%. This work demonstrates how incorporating a shape-based inductive bias at the representation level can improve interpretability and scalability while enabling substantial dimensionality reduction.
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。