CellEcoNet: Decoding the Cellular Language of Pathology with Deep Learning for Invasive Lung Adenocarcinoma Recurrence Prediction

2025/08/22 by Akbar, Abdul Rehman, Sajjad, Usama, Su, Ziyu +5
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2508.16742

Abstract

Despite surgical resection, ~70% of invasive lung adenocarcinoma (ILA) patients recur within five years, and current tools fail to identify those needing adjuvant therapy. To address this unmet clinical need, we introduce CellEcoNet, a novel spatially aware deep learning framework that models whole slide images (WSIs) through natural language analogy, defining a "language of pathology," where cells act as words, cellular neighborhoods become phrases, and tissue architecture forms sentences. CellEcoNet learns these context-dependent meanings automatically, capturing how subtle variations and spatial interactions derive recurrence risk. On a dataset of 456 H&E-stained WSIs, CellEcoNet achieved superior predictive performance (AUC:77.8% HR:9.54), outperforming IASLC grading system (AUC:71.4% HR:2.36), AJCC Stage (AUC:64.0% HR:1.17) and state-of-the-art computational methods (AUCs:62.2-67.4%). CellEcoNet demonstrated fairness and consistent performance across diverse demographic and clinical subgroups. Beyond prognosis, CellEcoNet marks a paradigm shift by decoding the tumor microenvironment's cellular "language" to reveal how subtle cell variations encode recurrence risk.

Citations

• Morphology-Aware Prognostic model for Five-Year Survival Prediction in Colorectal Cancer from H&E Whole Slide Images
• Streamline pathology foundation model by cross-magnification distillation
• Multi-Modal Foundation Models for Computational Pathology: A Survey
• Accelerating Data Processing and Benchmarking of AI Models for Pathology
• Molecular-driven Foundation Model for Oncologic Pathology
• CellViT++: Energy-Efficient and Adaptive Cell Segmentation and Classification Using Foundation Models
• Cancer statistics, 2025
• Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-based Tool
• Phikon-v2, A large and public feature extractor for biomarker prediction
• Zero-Shot Whole Slide Image Retrieval in Histopathology Using Embeddings of Foundation Models
• Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries
• Cross-attention-based saliency inference for predicting cancer metastasis on whole slide images
• CellViT: Vision Transformers for Precise Cell Segmentation and Classification
• Micrograph segmentations for DDEVD
• Segment Anything
• TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification
• Emerging Properties in Self-Supervised Vision Transformers
• Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images
• Attention-based Deep Multiple Instance Learning
• Lung Adjuvant Cisplatin Evaluation: A Pooled Analysis by the LACE Collaborative Group

Related

• xCG: Explainable Cell Graphs for Survival Prediction in Non-Small Cell Lung Cancer
• Cell Maps Representation For Lung Adenocarcinoma Growth Patterns Classification In Whole Slide Images
• Doctor-in-the-Loop: An Explainable, Multi-View Deep Learning Framework for Predicting Pathological Response in Non-Small Cell Lung Cancer
• Cancer Cell Classification using Deep Learning
• ConvPath: A Software Tool for Lung Adenocarcinoma Digital Pathological Image Analysis Aided by Convolutional Neural Network