# Shape-Based Inductive Bias for Glioma Grading from Tumor Contours

arXiv: https://arxiv.org/abs/2607.26090 · HTML: https://mlsanity.com/paper/2607.26090/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 44 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be](https://mlsanity.com/paper/2110.05861/) (2021)
- [Deep Learning with Functional Inputs](https://mlsanity.com/paper/2006.09590/) (2020)
- [Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation](https://mlsanity.com/paper/2305.06568/) (2023)
- [Geospatial Big Data Handling Theory and Methods: A Review and Research Challenges](https://mlsanity.com/paper/1511.03010/) (2015)
- [Functional Autoencoder for Smoothing and Representation Learning](https://mlsanity.com/paper/2401.09499/) (2024)
- [Neural Networks for Scalar Input and Functional Output](https://mlsanity.com/paper/2208.05776/) (2022)
- [A Functional Approach to Curve Alignment and Shape Analysis](https://mlsanity.com/paper/2503.05632/) (2025)
- [Multivariate Planar Curves: A Statistical Framework for Shape Analysis in Images](https://mlsanity.com/paper/2508.11780/) (2025)

## Abstract (arXiv)

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.