Region-Wise Bézier Intensity Augmentation for Domain-Generalized Brain Tumor Segmentation with a Mamba U-Net.

Overview

1. Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Kırıkkale University, Kırıkkale 71450, Türkiye
2. Department of Software Engineering, Faculty of Engineering and Natural Sciences, Istanbul Topkapı University, Istanbul 34087, Türkiye
3. Department of Computer Engineering, Faculty of Engineering, Iğdır University, Iğdır 76000, Türkiye
4. Department of Electronics and Information Technologies, Faculty of Architecture and Engineering, Nakhchivan State University, Nakhchivan AZ 7012, Azerbaijan
5. Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Fenerbahce University, Istanbul 34758, Türkiye

Abstract

Background/Objectives: Robust brain-tumor segmentation on contrast-enhanced MRI remains limited by scanner-dependent intensity shifts, scarce annotations, and evaluation protocols that may leak patient-specific information. We propose BA-SwinMamba, a region-wise Bézier intensity augmentation framework built on Swin-UMamba, a selective state-space U-Net that combines hierarchical Swin-style visual modeling with Mamba’s linear-complexity long-range sequence representation. Materials and Methods: During training, independent monotonic or non-monotonic Bézier transfer functions are sampled for tumor and background regions, perturbing lesion-to-background contrast while preserving the binary mask geometry. Fourteen convolutional, transformer-based, and state-space segmentation models were evaluated on the Cheng brain-tumor dataset, comprising 3064 contrast-enhanced T1-weighted slices from 233 patients, using a strictly patient-level five-fold protocol. Single-source domain generalization was assessed by training only on Cheng and testing, without fine-tuning, on two independent target datasets. Results: BA-SwinMamba achieved 89.6% Dice, 82.0% IoU, and 5.9-pixel HD95 on the source domain, outperforming the plain Swin-UMamba backbone by 1.7 Dice points. The benefit was larger under domain shift: mean target-domain Dice increased from 72.7% with Swin-UMamba to 78.3% with BA-SwinMamba. Ablation analysis showed that replacing global Bézier augmentation with the proposed region-wise formulation added 1.5 Dice points. Conclusions: The method introduces no inference-time cost because augmentation is disabled after training, without modifying the deployed network or requiring target-domain labels during model optimization or tuning. The results indicate that lesion-aware intensity perturbation can improve cross-dataset robustness of Mamba-based 2D brain-tumor segmentation, while wider volumetric and multi-institutional validation remains necessary.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper says that its authors' code is available on request: it was not published with the paper, so there is nothing to verify.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none (its code is available on request), so it has no map.

Data

Datasets cited

• figshare:1512427, at figshare; found in “Data Availability Statement”

Data Availability Statement

The primary dataset is publicly available from Figshare (Cheng brain-tumor dataset; doi: 10.6084/m9.figshare.1512427). The cross-domain test datasets are available from their respective repositories. The source code reproducing the experiments will be made available in a public repository upon publication and, in the interim, from the corresponding author upon reasonable request.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 4 authors, 8 keywords, 1 funder, 16 references.

Cite

This paper

Yurdakul, M., Ersoy, M., Özger, F., & Pacal, I. (2026). Region-Wise Bézier Intensity Augmentation for Domain-Generalized Brain Tumor Segmentation with a Mamba U-Net. Journal of clinical medicine, 15(14), 5508. https://doi.org/10.3390/jcm15145508

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.3390/diagnostics16152407

BG-YOLO11s: Boundary-Guided YOLO11 with Bézier Contour Augmentation for Brain Tumour Segmentation in T1-CE MRI.

Journal: Diagnostics (Basel, Switzerland)

In common: figshare 1512427, methods / tools, structural MRI / diffusion, other condition, 3 references, 3 authors

[2] doi:10.3390/brainsci16050468

Advancing Brain Tumor Diagnosis Using Deep Learning: A Systematic and Critical Review on Methodological Approaches to Glioma Segmentation and Classification Through Multiparametric MRI.

Journal: Brain sciences

In common: figshare 1512427, structural MRI / diffusion, other condition, 2 references

[3] doi:10.3390/diagnostics16111745

Brain Tumor Classification and Segmentation in MR Images Using EfficientNet and U-Net++ Models.

Journal: Diagnostics (Basel, Switzerland)

In common: figshare 1512427, methods / tools, structural MRI / diffusion, other condition, 1 reference

[4] doi:10.1186/s42492-026-00230-4

Hierarchical two-stage ensemble of dilated U-net models for brain tumor segmentation.

Journal: Visual computing for industry, biomedicine, and art

In common: figshare 1512427, methods / tools, other condition, 1 reference

[5] doi:10.1186/s40708-026-00325-x

CAE-BrainNet: a statistically validated class-adaptive attention ensemble model for explainable brain tumor classification from MRI.

Journal: Brain informatics

In common: figshare 1512427, structural MRI / diffusion, other condition, 1 reference

[6] doi:10.2196/78300

Deep Learning for Content-Based Medical Image Retrieval in Picture Archiving and Communication Systems for Brain Tumor Detection: Algorithm Development and Validation.

Journal: JMIR medical informatics

In common: figshare 1512427, methods / tools, structural MRI / diffusion, other condition

[7] doi:10.1186/s40708-026-00303-3 [code]

BrainFusionNet: a deep learning and XAI model to understand local, global, and sequential features of MRI images for improved brain tumour detection.

Journal: Brain informatics

In common: figshare 1512427, methods / tools, structural MRI / diffusion, other condition

[8] doi:10.1371/journal.pone.0346821

LHW-Net: An ensemble-based machine learning framework for brain tumor classification.

Journal: PloS one

In common: figshare 1512427, methods / tools, other condition

[9] doi:10.1038/s41598-026-52615-3

MANet: a multimodal attention convolutional neural network for brain tumor classification.

Journal: Scientific reports

In common: figshare 1512427, structural MRI / diffusion, other condition

[10] doi:10.1038/s41598-026-46803-4 [code]

BrainGraphNet-ViT model: a hybrid model combining vision transformers and graph convolutional networks for brain tumor diagnosis.

Journal: Scientific reports

In common: figshare 1512427, structural MRI / diffusion, other condition

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.