Abstract
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 best-performing arrangement 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/.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/BraTS_GoAT_010.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=mIIiA4qLag
BibTex
@InProceedings{ZanHen_Generalizable_MICCAISAT2026,
author = { Zan Grande, Henrique AND Alves, Jeovane Honorio AND Laroca, Rayson AND Hochuli, Andre Gustavo},
title = { { Generalizable Brain Tumor Segmentation with Self-Training and Tumor-Aware Deformations } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17254},
month = {pending},
page = {pending}
}