发表机构
University of Victoria; Université du Québec à Montréal（维多利亚大学; 魁北克大学蒙特利尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对胶质瘤分级任务，提出融入基于形状的归纳偏置的方法，通过功能形状对齐框架处理肿瘤轮廓，在 BraTS~2020 数据集上取得优于像素基线的性能，且模型参数大幅减少。
AI 中文摘要
从肿瘤轮廓进行胶质瘤分级时，即便感兴趣的信号是形状，该任务也常被当作像素问题处理。我们采用功能形状对齐框架对齐闭合轮廓，将全局变形与残差傅里叶形状分离，并把这些量组织为按频率排序的 token。在针对 BraTS~2020 肿瘤轮廓的五折患者不相交交叉验证中，采用分组内部验证进行模型选择，紧凑多层感知机（MLP）取得了最高的平均平衡准确率，达 71.5%，而 ResNet-18 为 65.9%，ViT-Tiny 为 63.3%；其平均低级别胶质瘤 F1 也最高，达 54.9%。它的聚合折外平衡准确率为 72.4%（患者自助法 95% 置信区间：66.4--77.8%）。所选 MLP 在各折使用 2.9k--117.3k 参数，比像素基线少至少 46 倍。在受控无噪声模拟中，基于形状的模型达到 56.3--71.5% 的平衡准确率，而像素模型仅保持在 50.0--52.5%。本研究表明，在表示层面融入基于形状的归纳偏置，可提升可解释性与可扩展性，同时实现大幅降维。
英文摘要
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.
