Counterfactual bidirectional co-attention transformer for integrative histology-genomic cancer risk stratification Journal Article


Authors: Ji, Z.; Ge, Y.; Chukwudi, C.; U, K.; Zhang, S. M.; Peng, Y.; Zhu, J.; Zaki, H.; Zhang, X.; Yang, S.; Wang, X.; Chen, Y.; Zhao, J.
Article Title: Counterfactual bidirectional co-attention transformer for integrative histology-genomic cancer risk stratification
Abstract: Applying deep learning to predict patient prognostic survival outcomes using histological whole-slide images (WSIs) and genomic data is challenging due to the morphological and transcriptomic heterogeneity present in the tumor microenvironment. Existing deep learning-enabled methods often exhibit learning biases, primarily because the genomic knowledge used to guide directional feature extraction from WSIs may be irrelevant or incomplete. This results in a suboptimal and sometimes myopic understanding of the overall pathological landscape, potentially overlooking crucial histological insights. To tackle these challenges, we propose the CounterFactual Bidirectional Co-Attention Transformer framework. By integrating a bidirectional co-attention layer, our framework fosters effective feature interactions between the genomic and histology modalities and ensures consistent identification of prognostic features from WSIs. Using counterfactual reasoning, our model utilizes causality to model unimodal and multimodal knowledge for cancer risk stratification. This approach directly addresses and reduces bias, enables the exploration of 'what-if' scenarios, and offers a deeper understanding of how different features influence survival outcomes. Our framework, validated across eight diverse cancer benchmark datasets from The Cancer Genome Atlas (TCGA), represents a major improvement over current histology-genomic model learning methods. It shows an average 2.5% improvement in c-index performance over 18 state-of-the-art models in predicting patient prognoses across eight cancer types. Our code is released at https://github.com/BusyJzy599/CFBCT-main. © 2013 IEEE.
Keywords: cancer risk; genes; lung cancer; risk assessment; diagnosis; risk stratification; genomics; diseases; multi-modal; digital pathology; deep learning; digital pathologies; whole slide images; contrastive learning; multimodal data integration; cancer risk stratification; counterfactual reasoning; counterfactuals
Journal Title: IEEE Journal of Biomedical and Health Informatics
Volume: 29
Issue: 8
ISSN: 2168-2194
Publisher: IEEE  
Publication status: Published
Date Published: 2025-08-01
Start Page: 5862
End Page: 5874
Language: English
DOI: 10.1109/jbhi.2025.3548048
PUBMED: 40042950
PROVIDER: scopus
DOI/URL:
Notes: Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Kai Cheng U
    4 U