A weakly supervised deep learning framework for automated PD-L1 expression analysis in lung cancer.
Source check: Source checked. Not independent scientific confirmation.
Finding: Weakly supervised multiple-instance learning estimated lung-cancer PD-L1 scores with pathologist agreement in internal and external patient cohorts. The bibliographic records retrieved do not state an author affiliation.
Technology: ResNet18 plus attention and multiple-instance learning use slide-level pathologist labels; patient-level split produced internal and external evaluation.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- ResNet18 plus attention and multiple-instance learning use slide-level pathologist labels; patient-level split produced internal and external evaluation.
- Test and result
- Pathologist-referenced TPS validation reports ICC 0.960 and external accuracy 81.7%; diagnostic assistance only, with prospective utility untested.
- Limitation / still unknown
- Weakly supervised multiple-instance learning estimated lung-cancer PD-L1 scores with pathologist agreement in internal and external patient cohorts. Primary Results describe the specific comparator, cohort or experimental check; limitations are stated narrowly.
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/immunology/articles/10.3389/fimmu.2025.1540087/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: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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.