Cancer-Associated Lymphoid Aggregates in Histology Images: Manual and Deep Learning-Based Quantification Approaches

Methods Mol Biol. 2025:2864:231-246. doi: 10.1007/978-1-0716-4184-2_12.

Abstract

Quantification of lymphoid aggregates including tertiary lymphoid structures (TLS) with germinal centers in histology images of cancer is a promising approach for developing prognostic and predictive tissue biomarkers. In this article, we provide recommendations for identifying lymphoid aggregates in tissue sections from routine pathology workflows such as hematoxylin and eosin staining. To overcome the intrinsic variability associated with manual image analysis (such as subjective decision-making, attention span), we recently developed a deep learning-based algorithm called HookNet-TLS to detect lymphoid aggregates and germinal centers in various tissues. Here, we additionally provide a guideline for using manually annotated images for training and implementing HookNet-TLS for automated and objective quantification of lymphoid aggregates in various cancer types.

Keywords: Anti-tumor immunity; Deep learning; Germinal center; Image analysis; Lymphoid aggregate; Quantitative pathology; Tertiary lymphoid structure; Tumor microenvironment.

MeSH terms

  • Algorithms
  • Deep Learning*
  • Germinal Center / pathology
  • Humans
  • Image Processing, Computer-Assisted* / methods
  • Neoplasms* / pathology
  • Staining and Labeling / methods
  • Tertiary Lymphoid Structures / immunology
  • Tertiary Lymphoid Structures / pathology