LiteFreqMamba:lightweight frequency-enhanced Mamba for efficient 3D brain tumor segmentation.
Overview
Abstract
Introduction: State Space Models (SSMs) have demonstrated strong potential for 3D brain tumor segmentation owing to their linear computational complexity. However, conventional Mamba-based models are often limited by spectral bias, which favors low-frequency information while overlooking high-frequency boundary details, as well as by spatial disruption introduced by 1D scanning.
Methods: We propose LiteFreqMamba, a novel frequency-enhanced architecture for accurate and efficient 3D brain tumor segmentation. LiteFreqMamba is designed to improve boundary representation and spatial modeling through several key components. First, a Decomposed Frequency-Spatial Convolution (DFS-Conv) encoder is introduced to explicitly decompose features and capture high-frequency boundary information in shallow layers, thereby alleviating boundary ambiguity. Second, a Mamba-Attention Hybrid Bottleneck (MAHB) is developed to preserve spatial structure by combining the 2D-Selective-Scan (SS2D) mechanism for linear-complexity spatial mixing with dense self-attention for finegrained pixel-wise dependency modeling. In addition, Frequency-Calibrated Skip Connections (FCSC) are proposed to dynamically suppress noise in high-frequency feature injection, and a Lightweight 3D Convolutional (LWT-3D Conv) decoder is employed for efficient feature reconstruction.
Results: Extensive experiments on the BraTS2020 and BraTS2021 benchmarks show that LiteFreqMamba surpasses existing efficient segmentation models and achieves a better balance between inference speed and segmentation accuracy.
Discussion: LiteFreqMamba is designed to improve high-frequency boundary representation and preserve spatial dependencies in Mamba-based architectures. The proposed framework provides an efficient and accurate solution for 3D brain tumor image segmentation.
Reproduced under the paper's license (CC BY), from the paper cited above.
Code
The paper links to its data and to no code of its authors: see the Data section.
Tracing map
A tracing map links a paper to the code its authors published: this paper has none, so it has no map.
Data
Datasets cited
- kaggle.com/
datasets/ , at Kaggle; found in “Data availability statement”dschettler8845
Data availability statement
Publicly available datasets were analyzed in this study. This data can be found here: The datasets used in this study is publicly available from Multimodal Brain Tumor Segmentation Challenge. BraTS2020: https://
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, pages, dates, 5 authors, 5 keywords, 17 references.
Cite
This paper
Hou, X., Yao, J., Li, Q., Xu, C., & Dong, W. (2026). LiteFreqMamba:lightweigh
BibTeX
@article{hou2026litefreq
author = {Hou, Xiangning and Yao, Jun and Li, Qiaochu and Xu, Caocao and Dong, Wenxin},
title = {{LiteFreqMamba:lightwei
journal = {Frontiers in oncology},
year = {2026},
month = sep,
volume = {16},
pages = {1928589},
publisher = {Frontiers Media SA},
issn = {2234-943X},
doi = {10.3389/
url = {https://
pmid = {42760981},
pmcid = {PMC13585600}
}
RIS
TY - JOUR
AU - Hou, Xiangning
AU - Yao, Jun
AU - Li, Qiaochu
AU - Xu, Caocao
AU - Dong, Wenxin
TI - LiteFreqMamba:lightweigh
T2 - Frontiers in oncology
J2 - Front Oncol
PY - 2026
DA - 2026/
VL - 16
SP - 1928589
SN - 2234-943X
PB - Frontiers Media SA
DO - 10.3389/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.3389/
"type": "article-journal",
"title": "LiteFreqMamba:lightweig
"container-title": "Frontiers in oncology",
"author": [
{
"family": "Hou",
"given": "Xiangning"
},
{
"family": "Yao",
"given": "Jun"
},
{
"family": "Li",
"given": "Qiaochu"
},
{
"family": "Xu",
"given": "Caocao"
},
{
"family": "Dong",
"given": "Wenxin"
}
],
"container-title-short":
"volume": "16",
"page": "1928589",
"DOI": "10.3389/
"PMID": "42760981",
"PMCID": "PMC13585600",
"ISSN": "2234-943X",
"publisher": "Frontiers Media SA",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
9,
4
]
]
}
}
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/s25102985
- DiffBTS: A Lightweight Diffusion Model for 3D Multimodal Brain Tumor Segmentation.Journal: Sensors (Basel, Switzerland)In common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 5 references
- [2] doi:10.1038/s41598-025-96416-6
- Federated learning with integrated attention multiscale model for brain tumor segmentation.Journal: Scientific reportsIn common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 3 references
- [3] doi:10.1016/j.dib.2025.111287
- GBM-Reservoir: Brain tumor (Glioblastoma Multiforme) MRI dataset collection with ground truth segmentation masks.Journal: Data in briefIn common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 3 references
- [4] 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 sciencesIn common: other condition, 7 references
- [5] doi:10.3390/s25092800 [code]
- A Multidimensional Particle Swarm Optimization-Based Algorithm for Brain MRI Tumor Segmentation.Journal: Sensors (Basel, Switzerland)In common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 2 references
- [6] doi:10.1038/s41598-026-48496-1 [code]
- A unified FLAIR hyperintensity segmentation model for various CNS tumor types and acquisition time points.Journal: Scientific reportsIn common: methods / tools, other condition, 6 references
- [7] doi:10.3389/fradi.2023.1336902
- Using a generative adversarial network to generate synthetic MRI images for multi-class automatic segmentation of brain tumors.Journal: Frontiers in radiologyIn common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 1 reference
- [8] doi:10.3389/fpubh.2023.1091850 [code]
- MRI brain tumor segmentation using residual Spatial Pyramid Pooling-powered 3D U-Net.Journal: Frontiers in public healthIn common: methods / tools, other condition, 5 references
- [9] doi:10.3390/diagnostics15121552
- The Teacher-Assistant-Studen
t Collaborative and Competitive Network for Brain Tumor Segmentation with Missing Modalities. Journal: Diagnostics (Basel, Switzerland)In common: kaggle.com/datasets/dschettler8845, methods / tools, other condition, 1 reference - [10] doi:10.1364/boe.579532 [code]
- Brain-SAM: a general automatic SAM-based segmentation model for brain science images.Journal: Biomedical optics expressIn common: methods / tools, 4 references
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.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
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, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
