AI-derived marrow PET measures correlate with myeloma burden
Source check: Source checked. Not independent scientific confirmation.
Finding: A convolutional network segmented whole-body bones in PET/CT scans from 35 untreated patients with multiple myeloma. Metabolic-volume measures derived using four of six uptake thresholds showed moderate associations with biopsy plasma-cell infiltration and blood beta-2-microglobulin. Results depended on the chosen threshold and remain exploratory; the study did not establish survival prediction, treatment response or replacement of marrow biopsy.
Technology: Convolutional neural network; automated skeletal segmentation
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- A CNN segments bones and reference tissues, enabling volumetric metabolic measurements that are compared with independently measured clinical biomarkers.
- Test and result
- Clinical associations of automated PET measurements with iliac-crest biopsy infiltration and blood beta-2-microglobulin in 35 untreated patients.
- Limitation / still unknown
- Threshold generalizability, clinical utility and outcome prediction remain unestablished; individual lesions were generally not biopsied and skull/large lytic lesions can be missed.
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/PMC10547616/
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.