Topic: Explainable Genomic AI for Breast Cancer Screening

Breast cancer remains one of the most prevalent and heterogeneous malignancies worldwide. While early detection significantly improves prognosis, current screening methods often face limitations in sensitivity, specificity, and population stratification. With the increasing availability of large-scale genomic and multi-omics datasets, artificial intelligence (AI) has emerged as a powerful tool for identifying risk patterns and improving screening strategies.

However, many existing AI approaches operate as “black boxes,” limiting their trust and applicability in clinical settings. To bridge this gap, explainable AI (XAI) methods are gaining traction for their ability to make model decisions transparent, interpretable, and clinically actionable—particularly in genomics, where understanding feature contribution and biological relevance is essential.

This special issue aims to bring together cutting-edge research at the intersection of genomics, AI, and explainability, with a focus on breast cancer screening. We welcome both original research and review articles that explore interpretable models, real-world clinical validation, and novel algorithmic frameworks that prioritize transparency and trust.

Suggested Subtopics:

● Explainable machine learning models for breast cancer genomic risk prediction;

● Integration of multi-omics data using interpretable AI approaches;

● Biology-informed neural networks for early breast cancer detection;

● Feature attribution methods (e.g., SHAP, LIME, attention) applied to genomic datasets;

● Explainable AI-enhanced polygenic risk scores (PRS);

● Human-in-the-loop systems for genomic interpretation;

● Ethical and regulatory challenges in explainable AI applications;

● Comparative analyses of interpretable vs. black-box models in genomic oncology;

● Applications in high-risk populations, including BRCA mutation carriers.

Explainable Artificial Intelligence (XAI), Genomic Risk Prediction, Breast Cancer Screening, Multi-Omics Integration, Interpretable Machine Learning