Longitudinal MRI learning classifies treated high-grade glioma changes
Source check: Source checked. Not independent scientific confirmation.
Finding: A support-vector machine combined structural and perfusion MRI measurements to classify progression, pseudoprogression and stable disease after high-grade glioma treatment. In a retrospective 64-patient study, longitudinal combined features reached reported accuracy of 94.7% in the 19-patient subset with serial perfusion scans. Repeated internal cross-validation, a mostly clinical imaging reference and feature-selection uncertainty limit generalization; no prospective treatment benefit was demonstrated.
Technology: Radial-basis-function support-vector machine; LASSO feature selection
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- LASSO selects image-derived measurements and an RBF support-vector classifier combines structural/perfusion changes to distinguish recorded post-treatment categories.
- Test and result
- Repeated internal two-fold cross-validation with histology in 13 patients and longitudinal clinical/radiological consensus in the others; serial perfusion available in 19 patients.
- Limitation / still unknown
- External frozen-model performance and clinical benefit remain unestablished; the small serial-scan subset, reference incorporation and feature-selection timing can inflate apparent accuracy.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC8589799/
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: 21 Nov 2026. Review scope: Primary relevant model Methods, Results and limitations; exact primary identity and current primary PubMed correction/retraction relationships checked..
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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.