What question did this study set out to answer?

This research aims to assess the role of AI in objectively evaluating tertiary lymphoid structures as prognostic markers in HNSCC.

May 29, 2026

AI-powered assessment of tertiary lymphoid structures (TLS) from H&E whole-slide images as a prognostic tool in HNSCC.

Key Points

This research aims to assess the role of AI in objectively evaluating tertiary lymphoid structures as prognostic markers in HNSCC.
Integrative analysis combining transcriptomic and histopathologic data from TCGA HNSCC mRNA expression (N=566).
AI model trained using a foundation model with a 3:1 train-test split of high-quality H&E images (n = 443).
Cox regression used for survival analyses to evaluate AI-predicted TLS enrichment as a predictor of overall survival.
AI model achieved AUC of 0.77 in the training set (n = 332) and 0.85 in the test set (n = 111).
TLS+ group (n = 146) showed median overall survival of 57.9 months compared to 35.4 months in TLS- group (HR 0.72; 95% CI 0.53–0.98; P = 0.039).
TLS enrichment remained an independent predictor of survival after adjusting for age, sex, and stage (HR 0.73; 95% CI 0.54–1.00; P = 0.0499).

Abstract

6024 Background: Tertiary lymphoid structures (TLS) are recognized prognostic markers in Head and Neck Squamous Cell Carcinoma (HNSCC), yet manual assessment from H these labels were used to train a foundation model-based AI using Imagene’s OI Suite powered by CanvOI with a 3:1 train–test split. Survival analyses were performed at the patient level in 443 evaluable patients with high-quality H 95% CI 0.53–0.98; log-rank P = 0.039). After adjustment for age, sex, and stage, AI-predicted TLS enrichment remained independently associated with improved overall survival (HR, 0.73; 95% CI, 0.54–1.00; P = 0.0499). These findings suggest that the AI model successfully translates molecular TLS signatures into histological predictors, capturing critical tumor microenvironment (TME) features that refine risk stratification beyond standard clinicopathologic factors. Conclusions: AI-based H&E WSI analysis helps identify TLS enrichment as a potential predictor of overall survival in HNSCC. This unbiased computational approach provides a reproducible and objective methodology using H&E slides alone, without the need for additional molecular or immunohistochemical assays, thereby supporting immune risk stratification for precision immunotherapy, particularly in resource-limited settings.

Ask AI

Helpful

Bookmark