English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

AI Characterization of Tertiary Lymphoid Structures and Tumor Microenvironment in Neoadjuvant-Treated Lung Squamous Cell Carcinoma

Forum topic · 小凯 · 2026-11-10

Summary

This arXiv paper (2611.12855) applies AI-based analysis of H&E whole-slide images to compare tertiary lymphoid structures (TLS), lymph-node follicles (SLS), and immune cell composition between neoadjuvant-treated (neoLUSC, n=20) and therapy-naive (naivLUSC, n=20) lung squamous cell carcinoma patients. Using the Aignostics Atlas H&E tissue analysis model and pathologist-validated deep learning models, the authors found that neoLUSC tumors had 72% lower stromal plasma cell density (p=0.004) and 48% lower stromal lymphocyte density (p=0.015), plus fewer mature TLS in tumors (p=0.034) and mature SLS in distant lymph nodes (p=0.003). The plasma cell-tumor coupling seen in naive tumors (rho=0.54) was absent after neoadjuvant therapy (rho=0.07). In an independent validation cohort (n=458), stromal plasma cell density (HR 0.69) and lymphocyte-plasma cell co-localization (HR 0.66) associated with longer survival, suggesting a candidate prognostic biomarker axis.

Paper Overview

Field: Computer Vision Authors: Arne Schmidt, Justin Nieder, Cornelius Boehm, Julika Ribbat-Idel, Marius Teodorescu Published: 2026-11-09 arXiv: 2611.12855

Abstract (English)

Mature tertiary lymphoid structures (TLS) containing germinal centers and mature lymph-node follicles (secondary lymphoid structures, SLS) sustain plasma cell responses that shape prognosis and immunotherapy benefit in lung cancer. How this regional axis differs between neoadjuvant-treated and therapy-naive tumors was previously unclear.

The authors analyzed H&E whole-slide images from resected tumors and paired proximal/distal lymph nodes of 20 matched neoadjuvant-treated (neoLUSC) and 20 therapy-naive (naivLUSC) lung squamous cell carcinoma patients. The Aignostics Atlas H&E tissue analysis model quantified cell densities and co-localization per tissue compartment; a dedicated deep learning model validated against pathologist annotations detected TLS/SLS and assessed maturity. Prognostic value was tested in an independent cohort (n=458, including 46 treated cases).

Key Findings

  • Stromal plasma cell density was 72% lower in neoLUSC tumors (p=0.004); stromal lymphocyte density was 48% lower (p=0.015). Macrophages and granulocytes showed no significant difference.
  • Total and immature TLS counts were unchanged, but mature TLS in tumors (p=0.034) and mature SLS in tumor-distant lymph nodes (p=0.003) were lower in neoLUSC.
  • Peri-TLS plasma cell density correlated with tumor lymphocyte density in naivLUSC (rho=0.54, p=0.017), but this association was absent in neoLUSC (rho=0.07).
  • In the validation cohort, stromal plasma cell density (HR 0.69, p=0.011) and lymphocyte-plasma cell co-localization (HR 0.66, p=0.004) were associated with longer survival, while neoadjuvant treatment status was associated with shorter survival (HR 1.50, p=0.026).

Conclusion

Neoadjuvant therapy is associated with a reduction in mature lymphoid structures and weakened humoral compartment-tumor coupling, rather than a global dampening of immune readouts. The stromal plasma cell / co-localization axis is a candidate prognostic biomarker.

--- *Automatically collected on 2026-11-11*

Tags

#lung-squamous-cell-carcinoma#tertiary-lymphoid-structures#tumor-microenvironment#computational-pathology#neoadjuvant-therapy#prognostic-biomarker#deep-learning#whole-slide-imaging

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178637022