NeuroSPFNet: Vision-Language Semantic Prior-Guided Frequency-Enhanced Network for Brain Tumor Segmentation in Multimodal MRI.

Overview

1. Department of Computer Information Engineering, Kunsan National University, Gunsan 54150, Republic of Korea

Abstract

Accurate brain tumor segmentation in multimodal magnetic resonance imaging (MRI) scans is essential for quantitative neuro-oncology analysis, treatment planning, and longitudinal disease monitoring. However, automatic delineation remains challenging because glioma subregions exhibit heterogeneous appearance across T1-weighted (T1), contrast-enhanced T1-weighted (T1ce), T2-weighted (T2), and fluid-attenuated inversion recovery (FLAIR) sequences; weak and irregular lesion boundaries; and severe scale variation between edema, tumor core, and enhancing tumor regions. This paper presents NeuroSPFNet, a vision–language semantic prior-guided frequency-enhanced segmentation framework for tumor subregion delineation in multimodal MRI volumes. NeuroSPFNet integrates four complementary components: a Clinical Vision–Language Prior Component (CVLPC) for category-level semantic guidance; a Frequency-Enhanced Boundary Module (FEBM) for boundary-sensitive representation learning; a Multi-Scale Lesion-Dominated Fusion Module (MLDFM) for hierarchical lesion aggregation; and a Lesion-Semantic Boundary Consistency Loss (LSBCL) for jointly constraining region overlap, boundary quality, and semantic alignment. The task-specific contribution lies in the closed coupling of shared BraTS-region semantic prototypes, gated frequency responses, lesion-weighted multiscale features, and semantic-boundary supervision within one volumetric segmentation pipeline. On the Brain Tumor Segmentation (BraTS) 2021 benchmark, NeuroSPFNet achieved Dice scores of 91.94%, 88.84%, and 85.38% for whole tumor, tumor core, and enhancing tumor, respectively, with a mean Dice of 88.72% and a mean 95th-percentile Hausdorff distance (HD95) of 3.58 mm. Ablation studies show distinct effects across subregions and metrics: semantic priors primarily strengthen tumor-core and enhancing-tumor discrimination, whereas frequency and boundary constraints primarily reduce contour error. NeuroSPFNet also attains competitive performance under the current setting, with moderate computational overhead of 42.58 million parameters, 78.60 billion floating-point operations (GFLOPs), and 265 ms per volume.

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

Code

The paper links to its data, not to its authors' code: 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

• synapse.org/synapse:syn25829067/wiki — at Synapse; found in “Data Availability Statement”

Data Availability Statement

The 1251 labeled BraTS 2021 cases used for model development are available through the official BraTS 2021 Synapse portal (https://www.synapse.org/Synapse:syn25829067/wiki/626944, accessed on 28 July 2026), subject to the benchmark terms and data use agreement. The 219 label-withheld challenge cases were not used to calculate the locally reported metrics.

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, 3 authors, 8 keywords, 7 MeSH terms, 1 funder, 17 references.

Cite

This paper

Liu, Y., Shin, S.-Y., & Lee, H.-A. (2026). NeuroSPFNet: Vision-Language Semantic Prior-Guided Frequency-Enhanced Network for Brain Tumor Segmentation in Multimodal MRI. Sensors (Basel, Switzerland), 26(15), 4963. https://doi.org/10.3390/s26154963

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/diagnostics16172806

Brain Tumor Segmentation and Grading on MRI Using Deep Learning: A Systematic Literature Review and Benchmark-Driven Comparative Analysis.

Journal: Diagnostics (Basel, Switzerland)

In common: methods / tools, structural MRI / diffusion, other condition, 8 references

[2] doi:10.21037/qims-2026-0792 [code]

An nnU-Net-based framework with adaptive feature representation for 3D brain tumor segmentation.

Journal: Quantitative imaging in medicine and surgery

In common: methods / tools, structural MRI / diffusion, other condition, 5 references

[3] doi:10.3389/frai.2026.1841639 [code]

Label tree semantic losses for rich multi-class medical image segmentation.

Journal: Frontiers in artificial intelligence

In common: 5 references

[4] doi:10.3390/diagnostics16111588 [code]

Bridging Annotation Gaps: Hierarchical Self-Support Learning for Brain Tumor Segmentation.

Journal: Diagnostics (Basel, Switzerland)

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

[5] doi:10.3390/jimaging12070288

GDNet: A Robust 2.5D Multimodal MRI Brain Tumor Segmentation Framework with EMA Stabilization and Tumor-Aware Sampling.

Journal: Journal of imaging

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

[6] doi:10.1038/s41598-026-60525-7

Superfast prediction of brain tumours through adaptive incremental pre-training and re-training through transfer learning using state-of-the-art ResNet18 architectural model.

Journal: Scientific reports

In common: structural MRI / diffusion, other condition, 3 references

[7] doi:10.1186/s40708-026-00298-x [code]

SegAnyNeuron: a neural image segmentation network with strong generalization performance by modeling image intensity variation.

Journal: Brain informatics

In common: methods / tools, 3 references

[8] doi:10.3390/s26165021

Automatic Segmentation of Ischaemic Stroke Lesions Using Transformers and Convolutional Neural Networks Applied to Multimodal Neuroimaging.

Journal: Sensors (Basel, Switzerland)

In common: methods / tools, 3 references

[9] doi:10.1371/journal.pone.0351953 [code]

GL-Net: A knowledge-guided Gaussian-gated and layered refinement network for 3D MRI segmentation of brain gliomas.

Journal: PloS one

In common: methods / tools, structural MRI / diffusion, other condition, 2 references

[10] doi:10.3390/diagnostics16152385

POWDR: Pathology-Preserving Outpainting with Wavelet Diffusion for 3D MRI.

Journal: Diagnostics (Basel, Switzerland)

In common: methods / tools, structural MRI / diffusion, 3 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.

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.