MRI radiomics differentiated gliosarcoma from glioblastoma
Source check: Source checked. Not independent scientific confirmation.
Finding: In a retrospective MRI cohort of 83 pathology-confirmed gliosarcomas and 100 glioblastomas, the best tumor-mass radiomics model (LASSO plus SVM) achieved AUC 0.85 and accuracy 0.77 on held-out patients and outperformed the tested neuroradiologist readings. This single-center diagnostic comparison does not establish prospective clinical utility.
Technology: LASSO feature selection and support-vector machine radiomics classifier
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Radiomics feature selection and supervised classification distinguished gliosarcoma from glioblastoma using MRI tumor-mass and edema features.
- Test and result
- Patient-level training and held-out evaluation in a single-center retrospective cohort with pathology labels; no external validation is reported.
- Limitation / still unknown
- No independent, prospective or clinical-impact evaluation is reported unless specified in the tested field.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.699789/full
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
Review date: 22 Nov 2026. Review scope: Read the original full text, including author affiliations, Methods and Results; checked the first result-bearing version and active/archive catalog for same-result records..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.