Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
May 6, 2026Cancer Research CommunicationsOpen Access

MRI Deep Learning for Differentiating Glioblastoma, IDH-Wildtype from Central Nervous System Diffuse Large B-cell Lymphoma

View Full Paper
Ask AI
Bookmark
Share

Authors

MMMana MoassefiPDPaul A. DeckerGCGian Marco Conte

Discussion

Loading...

Member takes

Overview

Deep learning demonstrates accurate differential diagnosis of glioblastoma in 239 patients, suggesting new imaging strategies.

Key Points

  • This research aims to utilize deep learning on MRI to differentiate between glioblastoma and CNS diffuse large B-cell lymphoma.
  • Used T1 post-contrast and T2-weighted MRI sequences for analysis.
  • Conducted a three-stage temporal study design with 146 matched patients for model development.
  • Tested models on independent cohorts and evaluated performance using AUC and cross validation.
  • Achieved AUC of 0.84 for the ensemble approach on the prospective test cohort.
  • Obtained AUC of 0.83 for the loss approach, indicating robust prediction performance.
  • Stratified AUC analysis showed consistent performance across sex and age.

Cite This Study

Moassefi et al. (2026) studied this question.

synapsesocial.com/papers/69faa2e204f884e66b533653https://doi.org/10.1158/2767-9764.crc-25-0710
View Full Paper
Ask AI
Bookmark
Share