EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A voxel‐wise uncertainty‐guided framework for glioma segmentation using spherical projection‐based U‐Net and localized refinement

Zhenyu Yang, Chen Yang, Rihui Zhang, Chunhao Wang, Minbin Chen, Fang-Fang Yin

Medical Physics · 2026-03 · 53 (3)

DOI: 10.1002/mp.70360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, online erschienen am 27.02.2026. Verfasst von Zhenyu Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China. Hauptthemen laut MEDLINE: Glioma, Imaging, Three-Dimensional, Magnetic Resonance Imaging, Brain Neoplasms. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate segmentation of glioma subregions from multi‐parametric MRI (MP‐MRI) is critical for clinical management but remains challenging due to tumor heterogeneity and ambiguous tissue boundaries.

Purpose

This study proposes an uncertainty‐guided hybrid segmentation framework that integrates spherical projection‐based 2D modeling with localized 3D refinement to improve segmentation fidelity.

Methods

The framework was validated on the BraTS 2020 dataset ( N = 369). First, a 2D nnU‐Net with spherical projection deformation was employed to generate initial slice‐wise predictions. Crucially, prediction variance across multiple spherical projections was utilized to quantify voxel‐level uncertainty, highlighting regions of low model confidence. A kernel‐based sliding window algorithm then spatially localized 3D subvolumes with high cumulative uncertainty. These targeted regions were subsequently fed into a dedicated 3D nnU‐Net for volumetric refinement. Finally, the global 2D predictions and local 3D refinements were adaptively fused using weights optimized via Particle Swarm Optimization. The proposed method was implemented to segment the enhancing tumor (ET), tumor core (TC) and whole tumor (WT). Performance was evaluated against standalone 2D and 3D nnU‐Net baselines using the Dice Similarity Coefficient (DSC), HD95, sensitivity, and specificity.

Results

The proposed method significantly outperformed 2D and 3D baselines across ET, TC, and WT targets. Notably, it achieved a DSC of 0.8124 for ET (vs. 0.7527 for 2D and 0.7530 for 3D), 0.7499 for TC (vs. 0.7002 for 2D and 0.7027 for 3D), 0.9055 for WT (vs. 0.8989 for 2D and 0.9038 for 3D) and demonstrated consistent gains in HD95 and sensitivity. Quantitative metrics and visualizations confirmed improved spatial coherence and boundary preservation in structurally complex regions.

Conclusion

By utilizing interpretable uncertainty maps as a spatial attention mechanism, this approach dynamically allocates computational resources to anatomically ambiguous regions. The resulting hybrid framework successfully combines 2D efficiency with 3D contextual accuracy, offering a robust solution for automated glioma segmentation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GliomaImaging, Three-DimensionalMagnetic Resonance ImagingBrain NeoplasmsUncertaintyHumans

Stichwörter der Autor:innen

deep learningglioma segmentationspherical projectionuncertainty quantification

Autor:innen und Institutionen

  • Medical Physics Graduate Program, Duke Kunshan University, Kunshan, Jiangsu, China.
  • Jiangsu Provincial University Key (Construction) Laboratory for Smart Diagnosis and Treatment of Lung Cancer, Kunshan, Jiangsu, China.
  • Department of Radiotherapy and Oncology, The First People's Hospital of Kunshan, Kunshan, Jiangsu, China.
  • Department of Radiation Oncology, Duke University, Durham, North Carolina, USA.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yang, Z., Yang, C., Zhang, R., Wang, C., Chen, M., & Yin, F. F. (2026). A voxel‐wise uncertainty‐guided framework for glioma segmentation using spherical projection‐based U‐Net and localized refinement. Medical Physics, 53(3). https://doi.org/10.1002/mp.70360

Vancouver

Yang Z, Yang C, Zhang R, Wang C, Chen M, Yin FF. A voxel‐wise uncertainty‐guided framework for glioma segmentation using spherical projection‐based U‐Net and localized refinement. Medical Physics. 2026;53(3). doi:10.1002/mp.70360

BibTeX
@article{Yang2026,
  author = {Yang, Zhenyu and Yang, Chen and Zhang, Rihui and Wang, Chunhao and Chen, Minbin and Yin, Fang-Fang},
  title = {A voxel‐wise uncertainty‐guided framework for glioma segmentation using spherical projection‐based U‐Net and localized refinement},
  journal = {Medical Physics},
  year = {2026},
  volume = {53},
  number = {3},
  doi = {10.1002/mp.70360}
}
Kostenlos starten →