AI-Enabled Digital Pathology and Molecular Biomarker Assessment for Clinical Decision Support in Breast Cancer

Breast cancer diagnosis and management increasingly depend on the accurate assessment of tissue-based and molecular biomarkers that guide prognosis, therapeutic selection, and response evaluation. Today, digital pathology assessment of “classic” biomarkers, such as HR, HER2, PD-L1, Ki-67, tumor-infiltrating lymphocytes, and histologic grade, is no longer sufficient on its own to provide clinicians with the full range of prognostic and predictive information needed for optimal decision-making. Emerging biomarkers, including HER2 “low” and “ultralow” status, BRCA, PALB2, and PI3K/AKT/PTEN alterations, and ESR1 mutations, assessed on primary tumors, at the time of relapse, or via circulating tumor DNA (ctDNA), are increasingly mandatory considerations and warrant dedicated discussion. At the same time, the rapid adoption of whole-slide imaging, computational pathology, and artificial intelligence is reshaping how pathology and molecular data are generated, interpreted, and integrated into clinical care. These developments create important opportunities to improve reproducibility, scalability, and precision in biomarker assessment while also raising new questions regarding validation, interpretability, generalizability, and clinical utility.

This Research Topic aims to highlight emerging advances in AI-enabled digital pathology and molecular biomarker assessment for clinical decision support in breast cancer. In contrast to broader precision oncology frameworks, the focus here is specifically on the use of digitized histopathology, computational approaches, and molecular profiling to extract clinically meaningful information from breast tumor specimens, whether from primary tumors, relapse samples, or ctDNA, and to support pathology-led and multidisciplinary decision-making. Relevant areas include AI-assisted evaluation of established biomarkers such as ER, PR, HER2 (including low and ultralow expression), Ki-67, PD-L1, tumor-infiltrating lymphocytes, and histologic grade, alongside molecular alterations such as BRCA, PALB2, PI3K/AKT/PTEN, and ESR1 mutations, as well as the discovery of novel image-derived biomarkers, spatial phenotypes, and morphology-based signatures associated with prognosis, treatment response, and resistance.

We welcome contributions addressing algorithm development, analytical and clinical validation, workflow integration, and translational implementation across the breast cancer continuum. Topics of interest include multimodal models linking histopathology with molecular, radiologic, or clinical data; computational methods for subtype characterization and risk stratification; AI tools supporting treatment selection or response prediction, including at relapse; approaches for integrating ctDNA-based monitoring with digital pathology findings; and strategies to improve consistency in biomarker scoring across institutions and practice settings. Studies examining data quality, annotation strategies, interoperability, explainability, regulatory considerations, and fairness across diverse populations are also highly relevant, particularly where they address barriers to real-world deployment.

By bringing together work at the interface of pathology, oncology, molecular diagnostics, computer science, and translational research, this Research Topic seeks to provide a focused forum for advances that move AI-enabled digital pathology and biomarker assessment beyond proof-of-concept and toward robust, clinically meaningful application in breast cancer care.




Please note: Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent clinical or patient cohort, or biological validation in vitro or in vivo, which are not based on public databases) are not suitable for publication in this journal.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Case Report
• Clinical Trial
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Case Report
• Clinical Trial
• Editorial
• FAIR² Data
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review
• Study Protocol
• Systematic Review
• Technology and Code

Keywords: Digital pathology, Breast cancer biomarkers, Computational pathology, Whole-slide imaging, Clinical decision support, AI-derived biomarkers, Biomarker scoring reproducibility

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.