2606.10713v1 Jun 09, 2026 eess.IV

++nnU-Net: Scaling nnU-Net with Prefix-Based Data Augmentation

André Ferreira
André Ferreira
Citations: 272
h-index: 9
B. Hinrichs-Puladi
B. Hinrichs-Puladi
Citations: 6
h-index: 2
Gijs Luijten
Gijs Luijten
Institute for Artificial Intelligence in Medicine (IKIM)
Citations: 236
h-index: 7
V. Alves
V. Alves
Citations: 263
h-index: 6
Jan Egger
Jan Egger
Citations: 713
h-index: 10
A. Santos
A. Santos
Citations: 1
h-index: 1
Naida Solak
Naida Solak
Citations: 132
h-index: 3
Lisle Faray de Paiva
Lisle Faray de Paiva
Citations: 1
h-index: 1
Jens Kleesiek
Jens Kleesiek
Citations: 179
h-index: 4

The nnU-Net has demonstrated continuous success in medical segmentation tasks, which heavily rely on the availability and diversity of annotated biomedical data. However, assembling medical imaging cohorts remains challenging due to numerous factors such as privacy regulations and annotation costs. As a result, data augmentation plays a crucial role in increasing data availability while maintaining anatomical feasibility. Hence, we propose the ++nnU-Net, a novel data augmentation module based on image registration that operates prior to preprocessing and training take place. Our framework was evaluated across five different 2D datasets. In this workflow, image data go through a two-stage registration process, generating new warped images. The transformations are then applied to the respective segmentation. In addition, the pipeline computes available disk space, generates supplementary binary synthetic masks and generates checkpoints. We demonstrate that the ++nnU-Net outperforms the nnU-Net baseline, yielding improvements in Dice Similarity Coefficient scores. In the most prominent cases, we observe performance gains of approximately 22\%. These findings highlight the effectiveness of registration-based data augmentation, particularly for 2D medical imaging datasets and suggest that the ++nnU-Net provides a practical and scalable approach for enhancing segmentation performance in data-limited settings. The source code for the ++nnU-Net is available at: https://github.com/sofia-adelie/plusplusnnunet.git

0 Citations
0 Influential
25 Altmetric
125.0 Score
Original PDF
0

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!