OSCR

MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation.

Overview

Authors: Yu Sun1, Yihang Qin2
ORCID iDs: Yihang Qin
  1. School of Special Education, Changchun University, Changchun, China
  2. School of Computer Science and Technology, Changchun University, Changchun, China
Institutions: Changchun University (China)
Journal: PloS one, volume 21, issue 7, article e0351667
Dates: received 27 December 2025; accepted 31 May 2026; published online 15 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.1371/journal.pone.0351667 · PMID 42455878 · PMCID PMC13372159 · OpenAlex W7168382960
Open access: gold, a free copy (OpenAlex)
Categories: structural MRI / diffusion (modality), human (organism), other condition (population), methods / tools (subfield)
Methods: Connectivity, Machine learning, Smoothing, state filtering, decompositions
MeSH: Brain Neoplasms*, Image Processing, Computer-Assisted*, Magnetic Resonance Imaging*, Algorithms, Convolutional Neural Networks, Humans, Uncertainty (* major topic)
Journal subjects: Medicine and Health Sciences, Oncology, Cancers and Neoplasms, Diagnostic Medicine, Diagnostic Radiology, Magnetic Resonance Imaging, Research and Analysis Methods, Imaging Techniques, Radiology and Imaging, Clinical Medicine, Signs and Symptoms, Edema, Biology and Life Sciences, Neuroscience, Cognitive Science, Cognition, Memory, Memory Recall, Learning and Memory, Physical Sciences, Mathematics, Optimization, Computer and Information Sciences, Software Engineering, Preprocessing, Engineering and Technology
Topic: Advanced Neural Network Applications (Computer Vision and Pattern Recognition, Computer Science), according to OpenAlex
Funding: general project of humanities and social sciences research of the ministry of education of the PRC (No. 23YJA740033); key project of the Joint Fund for Free Exploration under Jilin Provincial Natural Science Foundation (No. YDZJ202101ZYTS153); general project of National Natural Science Foundation (No. 62377006)
Citations: not cited yet (Europe PMC); 35 references in the paper

Abstract

Precise segmentation of brain tumors from MRI remains a challenging problem in medical image analysis because tumor regions exhibit substantial size variability, diffuse and infiltrative boundaries, and severe foreground-background imbalance. To address these challenges, we propose MamNet-PT, a hybrid segmentation architecture that integrates efficient long-range dependency modeling, multi-resolution feature aggregation, and uncertainty-aware prediction within a unified framework. First, a selective state-space model is embedded into the U-Net-based feature pathway to capture long-range spatial dependencies with linear computational complexity, which is particularly important for irregular and spatially extended tumor regions. Second, a pre-trained ResNet-50 encoder is used to improve feature robustness under limited annotated medical data. Third, a gated feature interaction mechanism adaptively balances Mamba-derived global contextual features and CNN-derived local boundary features, avoiding simple feature concatenation or uncontrolled module stacking. In addition, a multi-resolution pyramid fusion module strengthens scale-aware representation of small enhancing foci and extensive edema, while Monte Carlo Dropout-based uncertainty estimation provides spatial confidence maps for retrospective confidence characterization and failure-mode analysis. On the BraTS2020 benchmark, MamNet-PT achieves a Dice score of 96.7% and an Intersection over Union of 95.4%, outperforming representative CNN-Transformer and Mamba-based segmentation baselines. Ablation experiments further confirm that the performance gain is attributable to the complementary effects of selective state-space modeling, gated global-local fusion, multi-resolution aggregation, and uncertainty-aware inference. These results suggest that MamNet-PT is a promising research framework for accurate and efficient brain tumor segmentation under retrospective benchmark evaluation.

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

Data Availability

The data underlying the results of this study are available from Kaggle (https://www.kaggle.com/datasets/awsaf49/brats20-dataset-training-validation).

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, 2 authors, 7 MeSH terms, 3 funders, 25 references.

Cite

This paper

Sun, Y., & Qin, Y. (2026). MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation. PloS one, 21(7), e0351667. https://doi.org/10.1371/journal.pone.0351667

BibTeX

@article{sun2026mamnet,
author = {Sun, Yu and Qin, Yihang},
title = {{MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation}},
journal = {PloS one},
year = {2026},
month = jul,
volume = {21},
number = {7},
pages = {e0351667},
publisher = {PLOS},
issn = {1932-6203},
doi = {10.1371/journal.pone.0351667},
url = {https://doi.org/10.1371/journal.pone.0351667},
pmid = {42455878},
pmcid = {PMC13372159}
}

RIS

TY - JOUR
AU - Sun, Yu
AU - Qin, Yihang
TI - MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation
T2 - PloS one
J2 - PLoS One
PY - 2026
DA - 2026/07/15
VL - 21
IS - 7
SP - e0351667
SN - 1932-6203
PB - PLOS
DO - 10.1371/journal.pone.0351667
UR - https://doi.org/10.1371/journal.pone.0351667
LA - en
ER -

CSL-JSON

{
"id": "10.1371/journal.pone.0351667",
"type": "article-journal",
"title": "MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation",
"container-title": "PloS one",
"author": [
{
"family": "Sun",
"given": "Yu"
},
{
"family": "Qin",
"given": "Yihang"
}
],
"container-title-short": "PLoS One",
"volume": "21",
"issue": "7",
"page": "e0351667",
"DOI": "10.1371/journal.pone.0351667",
"PMID": "42455878",
"PMCID": "PMC13372159",
"ISSN": "1932-6203",
"publisher": "PLOS",
"URL": "https://doi.org/10.1371/journal.pone.0351667",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
15
]
]
}
}

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:10.1038/s41598-025-09833-y [code]
A novel hybrid vision UNet architecture for brain tumor segmentation and classification.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, other condition, 1 reference
[2] doi:10.1038/s41598-026-53337-2 [code]
Progression-guided spatiotemporal memory transformers for accurate and consistent longitudinal brain tumor segmentation.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[3] doi:10.1038/s41598-026-50240-8
High-precision brain tumor segmentation with switchable normalization in faster R-CNN architecture.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[4] doi:10.1371/journal.pone.0336514 [code]
Boosting brain tumor segmentation: A novel 3D pooling approach with U-net 3D.
Journal: PloS one
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[5] doi:10.1186/s12929-025-01213-y
Mod-SE(2): a geometric deep learning framework for brain tumor classification and segmentation in MRI images.
Journal: Journal of biomedical science
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[6] doi:10.1038/s41598-025-09539-1
ResSAXU-Net for multimodal brain tumor segmentation from brain MRI.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[7] doi:10.1038/s41598-025-02209-2
An automated deep learning framework for brain tumor classification using MRI imagery.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[8] doi:10.1038/s41598-025-96416-6
Federated learning with integrated attention multiscale model for brain tumor segmentation.
Journal: Scientific reports
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[9] doi:10.1177/19714009231224442
A semi-automatic segmentation method for meningioma developed using a variational approach model.
Journal: The neuroradiology journal
In common: kaggle.com/datasets/awsaf49, methods / tools, structural MRI / diffusion, other condition
[10] doi:
Q-rung orthopair fuzzy framework for multimodal MRI image fusion and U-Net-based segmentation for brain tumor detection
Journal: Frontiers in artificial intelligence
In common: kaggle.com/datasets/awsaf49, methods / tools, 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.

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.

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.