EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

IDH Mutation Assessment in Gliomas from Anatomical MRI Using Deep Learning: A Comparative Analysis of Centralized and Federated Learning Frameworks

Abdullah Bas iD, Esin Ozturk-Isik iD

Diagnostics · 20.02.2026 · 16 (4) · 623

DOI: 10.3390/diagnostics16040623 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 20.02.2026. Verfasst von Abdullah Bas und 1 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Biomedical Engineering, Bogazici University, Istanbul 34684, Türkiye. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Isocitrate dehydrogenase (IDH) mutation is a key prognostic indicator in diffuse gliomas; however, it is clinically determined from invasive tissue sampling. Non-invasive preoperative identification of IDH mutation from routine anatomical MRI could support treatment decision making. This study evaluated deep learning models for IDH mutation detection using routine anatomical MRI (post-contrast T1-weighted (T1c), T2-weighted, and fluid attenuated inversion recovery (FLAIR) MRI) and quantified how tumor-focused image preprocessing and different training schemes, centralized learning (CL) versus federated learning (FL) with alternative aggregation strategies, affected model performance.

Methods

Anatomical MRI from 501 diffuse glioma patients in the UCSF Preoperative Diffuse Glioma MRI (UCSF-PDGM) dataset was analyzed using a deep learning classifier built on a 2D U-Net encoder, with age and sex included as covariates. Two methods of tumor-focused image preprocessing, Naïve Soft Filtering (NSF) and Gradient-Based Soft Filtering (GBSF), were compared. Centralized learning (CL) was benchmarked against federated learning (FL) using Federated Averaging (FA) and Federated Trimmed Mean (FTM) aggregation strategies. Model performance was compared in terms of accuracy, precision, recall, F1 score, specificity, and the area under the receiver operating characteristic curve (ROC-AUC).

Results

The CL model with NSF achieved the best test performance (accuracy = 0.949, F1 = 0.951, ROC-AUC = 0.971), with NSF consistently outperforming GBSF. FL’s performance decreased relative to CL’s, but the FA strategy outperformed FTM (FTM accuracy = 0.915 vs. FA accuracy = 0.949), which indicates that the FL aggregation strategy has an influence on model performance.

Conclusions

Deep learning applied to routine anatomical MRI could classify IDH mutation status with high accuracy. Context-preserving image preprocessing with NSF substantially improved performance across training schemes. FL provides a privacy-preserving alternative to CL, but incurs a measurable performance degradation that is sensitive to the choice of aggregation strategy.

Schlagwörter

Stichwörter der Autor:innen

FLAIRMRIT2-weightedfederated learninggliomaisocitrate dehydrogenase (IDH)post-contrast T1-weighted

Autor:innen und Institutionen

  • Institute of Biomedical Engineering, Bogazici University, Istanbul 34684, Türkiye.
  • Center for Targeted Therapy Technologies, Bogazici University, Istanbul 34684, Türkiye.

ORCID-Profile: Abdullah Bas, Esin Ozturk-Isik

Zitieren

APA

Bas, A., & Ozturk-Isik, E. (2026). IDH Mutation Assessment in Gliomas from Anatomical MRI Using Deep Learning: A Comparative Analysis of Centralized and Federated Learning Frameworks. Diagnostics, 16(4), 623. https://doi.org/10.3390/diagnostics16040623

Vancouver

Bas A, Ozturk-Isik E. IDH Mutation Assessment in Gliomas from Anatomical MRI Using Deep Learning: A Comparative Analysis of Centralized and Federated Learning Frameworks. Diagnostics. 2026;16(4):623. doi:10.3390/diagnostics16040623

BibTeX
@article{Bas2026,
  author = {Bas, Abdullah and Ozturk-Isik, Esin},
  title = {IDH Mutation Assessment in Gliomas from Anatomical MRI Using Deep Learning: A Comparative Analysis of Centralized and Federated Learning Frameworks},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {4},
  pages = {623},
  doi = {10.3390/diagnostics16040623}
}
Kostenlos starten →