用自训练和肿瘤感知形变增强，提升脑瘤分割泛化能力。
Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations
- 结合伪标签自训练与局部病变形变增强，提升模型鲁棒性。
- 在BraTS-GoAT验证集上，全瘤Dice达0.881，增强区NSD为0.533。
- 适合需要跨患者群体泛化的医学图像分割研究者参考。
本文针对BraTS 2026挑战中的跨肿瘤泛化分割任务（BraTS-GoAT），提出一种基于nnU-Net框架的半监督方法。该方法采用大残差编码器结构，利用未标注数据生成伪标签进行自训练，并引入肿瘤感知形变增强策略，在保持周围解剖结构的前提下对病灶区域进行局部形变。通过不同置信度伪标签样本比例评估各组件贡献，最终配置在验证集上取得全瘤Dice为0.881、肿瘤核心0.817、增强区0.775，对应NSD分别为0.473、0.490、0.533，优于仅使用标注数据的基线，验证了自训练与形变增强的互补性。源代码已公开于https://github.com/Henrique-zan/brats-goat-2026/。
原文摘要 · Abstract (English)
This work presents an approach to the Generalizability Across Tumors (BraTS-GoAT) task of the BraTS 2026 Challenge, which focuses on robust segmentation of brain tumor sub-regions across a heterogeneous patient population. The proposed method employs the nnU-Net framework with a large residual encoder architecture, integrating a semi-supervised learning technique with pseudo-labels generated from the unlabeled training data and a tumor-aware deformable augmentation that locally deforms the lesion while preserving the surrounding anatomy. We evaluate the individual contributions of each component, as well as their combination, using varying proportions of the most confident pseudo-labeled cases. The submitted configuration for the generalization task achieves Dice and NSD scores of 0.881 and 0.473 for Whole Tumor, 0.817 and 0.490 for Tumor Core, and 0.775 and 0.533 for Enhancing Tumor on the BraTS-GoAT validation set, improving over the labeled-only baselines across all tumor regions and confirming that self-training and the proposed augmentation are complementary. Our source code is publicly available at https://github.com/Henrique-zan/brats-goat-2026/.
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。