Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 1, 2025Neuro-OncologyOpen Access

IMG-87. Differentiation of IDH-Wildtype Glioblastoma and Primary Central Nervous System Lymphoma Using 3D Deep Learning on MRI

View Full Paper
Ask AI
Bookmark
Share

Authors

MMMana MoassefiGCGian-Marco ContePDPaul Decker

Discussion

Loading...

Member takes

Overview

Automated models differentiate glioblastoma from lymphoma on MRI, suggesting effective diagnostic support.

Key Points

  • This research aims to differentiate between glioblastoma and primary central nervous system lymphoma using advanced imaging techniques.
  • Developed deep learning models utilizing multi-sequence MRI data from 146 PCNSL and 146 GBM cases.
  • Trained a 3D-DenseNet121 convolutional neural network with loss-based model selection and ensemble prediction strategies.
  • Evaluated model performance on an independent validation set including additional MRI cases from external sources.
  • The loss-based model achieved an AUC of 0.83 with multi-sequence MRI input.
  • The ensemble model reached an AUC of 0.82, indicating strong diagnostic performance across demographics.
  • Model performance was better for subjects older than 50 years compared to younger subjects.

Cite This Study

Moassefi et al. (2025) studied this question.

synapsesocial.com/papers/69254366c0ce034ddc3583d6https://doi.org/10.1093/neuonc/noaf201.1166
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1MRI Deep Learning for Differentiating Glioblastoma, IDH-Wildtype from Central Nervous System Diffuse Large B-cell Lymphoma2026
  2. 2IMG-38. Differentiating adult diffuse IDH-mutant glioma from molecular glioblastoma IDH-wildtype using deep learning on MRI2025
  3. 3Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: CT vs MRI2025
  4. 4Automatic segmentation and classification of GBM and SBM using a 3D deep learning model on multiparametric MRI: a multi-center study2025
  5. 5IMG-47. How does deep learning/machine learning perform in comparison to radiologists in distinguishing glioblastomas (or grade IV astrocytomas) from primary CNS lymphomas?: a meta-analysis and systematic review2025