AI Science Tracker
EN

Longitudinal MRI learning classifies treated high-grade glioma changes

University College London; University College London Hospitals; The Netherlands Cancer Institute · 28 May 2021 · medicine

Discovery

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.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.