CellOMaps: A Compact Representation for Robust Classification of Lung Adenocarcinoma Growth Patterns

2025-01-14

AI Summary

Current classification of lung adenocarcinoma (LUAD) into five histologic growth patterns suffers from high subjectivity, substantial inter-observer variability, and suboptimal accuracy. Method: We propose a weakly supervised learning framework based on cell-oriented tissue graphs (cellOMaps), the first to explicitly model cellular spatial arrangements. Our approach integrates H&E whole-slide image tissue segmentation, cell instance localization, and a spatial graph neural network, enabling multi-region fine-grained pattern recognition and extrapolation to tumor mutational burden (TMB) prediction. Contribution/Results: Evaluated on internal and multiple external cohorts, our method achieves robust, state-of-the-art classification of all five LUAD growth patterns plus non-neoplastic tissue, significantly outperforming existing methods in accuracy and generalizability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Computer Vision: Adversarial Attacks & Robustness
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Lung adenocarcinoma (LUAD) is a morphologically heterogeneous disease, characterized by five primary histological growth patterns. The classification of such patterns is crucial due to their direct relation to prognosis but the high subjectivity and observer variability pose a major challenge. Although several studies have developed machine learning methods for growth pattern classification, they either only report the predominant pattern per slide or lack proper evaluation. We propose a generalizable machine learning pipeline capable of classifying lung tissue into one of the five patterns or as non-tumor. The proposed pipeline's strength lies in a novel compact Cell Organization Maps (cellOMaps) representation that captures the cellular spatial patterns from Hematoxylin and Eosin whole slide images (WSIs). The proposed pipeline provides state-of-the-art performance on LUAD growth pattern classification when evaluated on both internal unseen slides and external datasets, significantly outperforming the current approaches. In addition, our preliminary results show that the model's outputs can be used to predict patients Tumor Mutational Burden (TMB) levels.

Problem

• Lung Adenocarcinoma Classification
• Machine Learning Shortcomings
• Interpretation Variability

Innovation

• cellOMaps
• LUAD growth pattern recognition
• Tumor Mutation Burden prediction