EUVIMEDEUVIMED entdecken
Multizentrische Studie

Voxel‐Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression

Linsha Yang, Defeng Liu, Duo Zhang iD, Juan Du, Qinglei Shi iD, Tao Zheng iD

Journal of Magnetic Resonance Imaging · 2026-11 · 64 (5) · 1266-1279

DOI: 10.1002/jmri.70419 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Journal of Magnetic Resonance Imaging, online erschienen am 22.06.2026. Verfasst von Linsha Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Imaging, The First Hospital of Qinhuangdao, Qinhuangdao, People's Republic of China. Hauptthemen laut MEDLINE: Glioma, Brain Neoplasms, Magnetic Resonance Imaging. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Qinhuangdao S&T Plan Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Differentiating true progression (TP) from pseudoprogression (PsP) after chemoradiotherapy in gliomas remains challenging because conventional MRI findings overlap.

Purpose

To assess whether voxel‐level radiomics habitat metrics improve TP/PsP classification and complement clinical and molecular features. Study Type Retrospective, multi‐center. Subjects 193 glioma patients after treatment: 121 in the training set (54.2 ± 11.3 years; 74 men; 85 TP/36 PsP) and 72 in the external testing set (51.4 ± 10.4 years; 44 men; 52 TP/20 PsP). Field Strength/Sequence 3 and 1.5 T; contrast‐enhanced T1‐weighted spin‐echo imaging (T1CE), T2‐weighted fast/turbo spin‐echo imaging (T2WI), T2‐weighted fluid‐attenuated inversion recovery fast/turbo spin‐echo imaging (T2‐FLAIR), diffusion‐weighted echo‐planar imaging (DWI), and arterial spin labeling (ASL). Assessment Voxel‐wise radiomics features were extracted from contrast‐enhancing tumor ROIs. Gaussian mixture models generated soft habitats, from which voxel‐level metrics were calculated. Three models were constructed. The Clinical Model included tumor grade, isocitrate dehydrogenase (IDH) status, O6‐methylguanine‐DNA methyltransferase (MGMT) promoter methylation status, and time interval. Feature selection used least absolute shrinkage and selection operator (LASSO); classifier optimization employed Optuna‐based Bayesian methods. Statistical Tests Receiver operating characteristic (ROC) curve analysis, calibration curves, decision curve analysis (DCA), and SHAP were used. p < 0.05 indicated significance.

Results

In the testing set, the Clinical, Voxel‐wise Habitat, and Combined Models achieved areas under the curve (AUCs) of 0.701 (95% confidence interval [CI]: 0.597–0.806), 0.832 (95% CI: 0.736–0.917), and 0.890 (95% CI: 0.819–0.958), respectively. The Combined Model significantly outperformed the clinical model (difference, 0.189). Voxel‐wise Habitat versus Clinical (difference, 0.131; p = 0.164) and Combined versus Voxel‐wise Habitat comparisons (difference, 0.058; p = 0.105) were not significant. SHAP ranked CBF_habitat_edge_standard_deviation, CBF_habitat_entropy_mean, and T1CE_habitat_edge_standard_deviation as leading contributors. Data Conclusion Voxel‐wise habitat analysis, combined with clinical and molecular features, improved TP/PsP discrimination with interpretable heterogeneity metrics. Evidence Level 3. Technical Efficacy Stage 3.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GliomaBrain NeoplasmsMagnetic Resonance ImagingHumansRadiomicsMaleDisease ProgressionRetrospective StudiesMiddle AgedFemaleROC CurveAdultAgedImage Processing, Computer-AssistedDNA Repair EnzymesBrainChemoradiotherapyDNA Modification MethylasesImage Interpretation, Computer-AssistedTumor Suppressor ProteinsContrast MediaDiffusion Magnetic Resonance Imaging

Stichwörter der Autor:innen

MRIgliomahabitat analysispseudoprogressionradiomicstrue progressionvoxel‐wise

Substanzen

DNA Repair EnzymesDNA Modification MethylasesTumor Suppressor ProteinsContrast MediaMGMT protein, human

Autor:innen und Institutionen

  • Department of Medical Imaging, The First Hospital of Qinhuangdao, Qinhuangdao, People's Republic of China.
  • Department of Medical Imaging, Baoding No. 1 Hospital, Baoding, People's Republic of China.
  • Siemens Ltd., Beijing, People's Republic of China.

ORCID-Profile: Duo Zhang, Qinglei Shi, Tao Zheng

Förderung

  • Qinhuangdao S&T Plan Program

Zitieren

APA

Yang, L., Liu, D., Zhang, D., Du, J., Shi, Q., & Zheng, T. (2026). Voxel‐Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression. Journal of Magnetic Resonance Imaging, 64(5), 1266-1279. https://doi.org/10.1002/jmri.70419

Vancouver

Yang L, Liu D, Zhang D, Du J, Shi Q, Zheng T. Voxel‐Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression. Journal of Magnetic Resonance Imaging. 2026;64(5):1266-1279. doi:10.1002/jmri.70419

BibTeX
@article{Yang2026,
  author = {Yang, Linsha and Liu, Defeng and Zhang, Duo and Du, Juan and Shi, Qinglei and Zheng, Tao},
  title = {Voxel‐Wise Radiomics Habitat Analysis of Posttreatment Gliomas for Noninvasive Differentiation of True Progression and Pseudoprogression},
  journal = {Journal of Magnetic Resonance Imaging},
  year = {2026},
  volume = {64},
  number = {5},
  pages = {1266--1279},
  doi = {10.1002/jmri.70419}
}
Kostenlos starten →