Automated fat measurements associate with prostate therapy survival
Source check: Source checked. Not independent scientific confirmation.
Finding: Deep-learning body segmentation measured fat compartments on routine PET/CT in 86 men receiving PSMA radioligand therapy. A higher intramuscular-fat proportion was associated with shorter overall survival, with volumetric measurements adding information beyond a single lumbar slice in the same cohort. This retrospective association does not establish a causal effect of fat, independent prediction or improved treatment selection.
Technology: Body and Organ Analysis; deep-learning CT segmentation
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- The pretrained BOA segmentation framework delineates body compartments to derive volumetric fat fractions for clinical survival-association analysis.
- Test and result
- Clinical overall-survival associations of automated three-dimensional and single-slice fat measurements, with multivariable analysis in 86 treated patients.
- Limitation / still unknown
- Independent validation and clinical decision benefit remain unestablished; selection, limited sample size and model fitting/evaluation in the same cohort can produce optimistic estimates.
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/PMC12660389/
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.