SOURCE-LINKED INTELLIGENCE

Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

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 compone

Read original source ↗ Open in workspace

recordType

paper

region

Global