Development and validation of an interpretable prediction model using spatial patterns of tumor-infiltrating lymphocytes in H&E-stained whole-slide images for immune subtyping of lung adenocarcinoma - Takeaways - MDSpire

Development and validation of an interpretable prediction model using spatial patterns of tumor-infiltrating lymphocytes in H&E-stained whole-slide images for immune subtyping of lung adenocarcinoma

  • By

  • Xia Li

  • Hai-Zhen Qin

  • Jing-Yu Wei

  • Kang-Lai Wei

  • Zhao-Quan Huang

  • May 8, 2026

  • 0 min

Share

  • 1

    A transparent predictive model for lung adenocarcinoma immune subtyping was developed using spatial distribution of tumor-infiltrating lymphocytes.

  • 2

    The model achieved an AUC of 0.839 in internal validation and 0.927 in external validation for immune subtype classification.

  • 3

    High-immunity patients showed increased CD8+ T cell and M1 macrophage infiltration, correlating with higher tumor mutation burden.

  • 4

    An automated annotation model demonstrated high accuracy in tissue segmentation and tumor-infiltrating lymphocyte identification.

  • 5

    This cost-effective tool enhances tumor immune status assessment and supports personalized immunotherapy decision-making.

Original Source(s)

Development and validation of an interpretable prediction model using spatial patterns of tumor-infiltrating lymphocytes in H&E-stained whole-slide images for immune subtyping of lung adenocarcinoma

  • by Xia Li, Hai-Zhen Qin, Jing-Yu Wei, Kang-Lai Wei, Zhao-Quan Huang

  • May 8, 2026

Related Content

HHLA2 as an emerging immune checkpoint in lung cancer: linking EGFR signaling, macrophage polarization, and CD8+ T-cell metabolic suppression

Severe IL-6–dominant immune-mediated inflammatory response complicated by probable arginine vasopressin deficiency following ivonescimab-based therapy in advanced EGFR-mutant lung squamous cell carcinoma: a case report

Targeted therapy combined with local consolidative surgery for oligometastatic stage IVA lung adenocarcinoma with CCDC6-RET fusion: a case report