68/100

Moderate evidence

GainPublished recordHealthGood Space

Integrating Intratumoral and Peritumoral Features via a Cross-Attention Transformer on Super-resolution MRI for Glioblastoma Survival Risk Stratification: A Multicenter Study

Truvace record
TRV-2026-3070raw data (JSON)
Version
v1Published
First published
Evidence type
Controlled or validated comparison
Sources
1 sourcePeer-reviewed
sha256
884f13d6347c…check it

Rationale and objectives To develop and validate a Cross-Region Transformer using super-resolution (SR) magnetic resonance imaging (MRI) to integrate intratumoral and peritumoral features for overall survival (OS) prediction in glioblastoma. Materials and methods This multicenter study included 362 patients (training, n = 228; internal test, n = 57; external validation, n = 77). Preoperative contrast-enhanced T1-weighted and T2-weighted MRI underwent generative adversarial network-based SR reconstruction. Intrat…

The gain

In a multicenter study of 362 glioblastoma patients, an AI risk score from super-resolution MRI separated external-validation patients into groups with median survival of 7.5 versus 23.5 months.

What this doesn’t fix

Discrimination fell from training (C-index 0.787) to internal test (0.711) and external validation (0.726), and the advantage over single-region and concatenation models was described only as numerically higher.

Sources

1 on file
  1. Academic Radiologydoi:10.1016/j.acra.2026.10.014
    Peer-reviewed2026-11-18

Cite this record

v1

Truvace Impact Record TRV-2026-3070, v1: “Integrating Intratumoral and Peritumoral Features via a Cross-Attention Transformer on Super-resolution MRI for Glioblastoma Survival Risk Stratification: A Multicenter Study.” Truvace, 2026-11-20. /record/TRV-2026-3070 (accessed on the day you copy it). sha256 884f13d6347c8f8a…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv1884f13d6347c…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-3070 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.