Unimodal vs. multimodal deep learning for non-invasive MGMT promoter methylation prediction in glioblastoma: A systematic evaluation on the BraTS 2021 dataset

Freddy Oulia, Philippe Charton, Muhammad Kabir, Fabrice Gardebien, Cédric Damour, Frederic Cadet · 2026

Read Unimodal vs. multimodal deep learning for non-invasive MGMT promoter methylation prediction in glioblastoma: A systematic evaluation on the BraTS 2021 dataset by Freddy Oulia, Philippe Charton, Muhammad Kabir, Fabrice Gardebien, Cédric Damour, Frederic Cadet (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351405.txt.

Description

A gene switch helps doctors predict chemotherapy success in glioblastoma. Testing that switch today requires tumor tissue. Freddy Oulia and colleagues asked whether MRI scans could replace the biopsy. They used a public dataset of about five hundred eighty patients. Deep learning models read the scans. The study appeared in PLOS One in 2026.

The team ran nearly fourteen hundred model configurations. Single scan types competed against combined scans. Viewing planes, slice counts, and merge styles all varied. The best single-scan model reached only about sixty-five percent accuracy. Results stayed modest across the whole sweep. The authors conclude scan-based prediction is not clinic-ready. A needle-free test remains a hope, not a tool.

Catalog record

CREATORFreddy Oulia, Philippe Charton, Muhammad Kabir, Fabrice Gardebien, Cédric Damour, Frederic Cadet
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE53114
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0351405

Browse the full library · About the Tower of Babel