AI-based characterization of lymphoid structures and the tumor microenvironment reveals lower mature tertiary lymphoid structures, lymph-node follicles, and plasma cells after neoadjuvant therapy in l
Source check: Source checked. Not independent scientific confirmation.
Finding: Deep-learning models quantified immune cells and lymphoid structures in lung squamous-cell carcinoma samples. In a 40-patient discovery cohort, neoadjuvant-treated cases had fewer stromal plasma cells and fewer mature tertiary or secondary lymphoid structures in specified compartments; an independent 458-patient cohort linked stromal plasma-cell density and lymphocyte–plasma-cell colocalization with longer survival. The observational comparison does not show that treatment caused these differences.
Technology: Deep-learning tissue and cell models quantified immune-cell densities, co-localization, and TLS/SLS maturity from H&E slides, supporting comparison of tumor and lymph-node immune architecture.
Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Deep-learning tissue and cell models quantified immune-cell densities, co-localization, and TLS/SLS maturity from H&E slides, supporting comparison of tumor and lymph-node immune architecture.
- Test and result
- The TLS model was evaluated on held-out annotated slides; the study also tested survival associations in an independent 458-patient cohort.
- Limitation / still unknown
- Small observational treatment comparison; model errors and cohort differences limit interpretation, and causal treatment effects are not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://arxiv.org/abs/2611.12855v1
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 full text, including Methods and Results; first result-bearing version and date verified from primary record..
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 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.