Machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer histopathology: a systematic review and evidence-gap analysis of translational readiness
9 affiliations
- 1Khoja Akhmet Yassawi International Kazakh-Turkish University
- 2School of Digital Technologies, Almaty Management University
- 3Office of the Vice Rector for Science and Strategic Development, Khoja Akhmet Yassawi International Kazakh-Turkish University
- 4Center for Strategic Development, Ranking, and Quality, Khoja Akhmet Yassawi International Kazakh-Turkish University
- 5Health Research Institute, Al-Farabi Kazakh National University
- 6Faculty of Medicine, Khoja Akhmet Yassawi International Kazakh-Turkish University
- 7Department of Epidemiology, Biostatistics and Evidence-Based Medicine, Al-Farabi Kazakh National University
- 8Faculty of Medicine and Health Care, Al-Farabi Kazakh National University
- 9Postgraduate Faculty of Medicine, Khoja Akhmet Yassawi International Kazakh-Turkish University
Abstract
Background: Machine learning-based assessment of tumor-infiltrating lymphocytes (TILs) has been proposed to improve the reproducibility and clinical utility of immune-contexture evaluation in breast cancer histopathology. However, existing studies differ substantially in task definition, annotation strategy, model architecture, validation design, and clinical endpoint. This systematic review and evidence-gap analysis aimed to map the translational readiness of TIL-related machine learning studies in breast cancer histopathology and to identify cluster-specific methodological gaps.
Methods: A systematic search of PubMed, Web of Science, Scopus, ScienceDirect, and Google Scholar was conducted up to 20 April 2026, supplemented by backward citation tracing and a targeted Google search of the 30 most relevant additional results. Eligible studies included breast cancer histopathology-based machine learning, deep learning, artificial intelligence, or computational image-analysis studies evaluating TILs or TIL-related immune-cell features. Studies were grouped by principal application into detection/classification, outcome prognostication, and treatment-response prediction. Extracted variables included data source, specimen type, model family, annotation strategy, validation design, clinical comparator use, calibration, decision-curve analysis, incremental value, reproducibility, and methodological challenges. Because of heterogeneity in endpoints and performance metrics, synthesis was descriptive and evidence-map based.
Results: The primary evidence map included 51 histopathology-image studies: 19 detection/classification, 18 outcome prognostication, and 14 treatment-response prediction studies. External validation was reported in 31.6% of detection/classification studies, 61.1% of prognostication studies, and 57.1% of treatment-response prediction studies. Clinical comparator reporting increased across the same continuum, from 63.2% to 94.4% and 92.9%, respectively. However, calibration was reported in only one prognostication study (5.6%) and in no detection/classification or treatment-response prediction studies. Decision-curve analysis was similarly limited to one prognostication study. Class imbalance was near-universal (94.7–100% across clusters). Scanner/stain robustness was addressed in a majority of studies (63.2–83.3%), but fairness or subgroup analyses remained inconsistently reported (27.8–57.1%).
Conclusions: TIL machine learning in breast cancer is technically active but clinically under-validated. Future studies should move beyond model development toward externally validated, calibrated, clinically benchmarked, reproducible, and decision-relevant evidence, using cluster-specific planning standards for detection, prognostication, and treatment-response prediction.
Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42024574566 , identifier CRD42024574566.
Related
- Human platelet lysate enables robust expansion of tumor infiltrating lymphocytes from endometrial cancer
- Quantifying Localized Tumor-Infiltrating Lymphocytes by Deep Learning on H&E Images: Analytical Validation and Prognostic Value in Lung Adenocarcinoma
- [18F]FDG PET/CT-Derived Metabolic Characteristics and Tumour-Infiltrating Lymphocytes for Predicting Axillary Response to Neoadjuvant Chemo-(Immuno)Therapy in Clinically Node-Positive Breast Cancer
- Parity, breastfeeding, and reproductive timing are associated with tumour-infiltrating lymphocytes in hormone receptor-negative breast cancer: a population-based cohort study
- Platform-based manufacturing of tumor-infiltrating lymphocytes derived from different solid tumor types
BibTeX
@article{dunenova2026machine,
title = {{Machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer histopathology: a systematic review and evidence-gap analysis of translational readiness}},
author = {Gauhar Dunenova and Aidos Sarsembayev and Ainash Oshibayeva and Saltanat Kyrykbayeva and Zinat Abdrakhmanova and Balnur Omarova and Alexandr Ivankov and Aliya Ualiyeva and Balzhan Zhakypova and Zhanar Zhagiparova and Gulnaz Nuskabayeva and Meruyert Suleimenova and Natalya Glushkova},
journal = {Frontiers in Oncology},
year = {2026},
month = oct,
doi = {10.3389/fonc.2026.1908349},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1908349/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning-based assessment of tumor-infiltrating lymphocytes in breast cancer histopathology: a systematic review and evidence-gap analysis of translational readiness
AU - Gauhar Dunenova
AU - Aidos Sarsembayev
AU - Ainash Oshibayeva
AU - Saltanat Kyrykbayeva
AU - Zinat Abdrakhmanova
AU - Balnur Omarova
AU - Alexandr Ivankov
AU - Aliya Ualiyeva
AU - Balzhan Zhakypova
AU - Zhanar Zhagiparova
AU - Gulnaz Nuskabayeva
AU - Meruyert Suleimenova
AU - Natalya Glushkova
PY - 2026
DA - 2026/10/26
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1908349
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1908349/full
AB - Background: Machine learning-based assessment of tumor-infiltrating lymphocytes (TILs) has been proposed to improve the reproducibility and clinical utility of immune-contexture evaluation in breast cancer histopathology. However, existing studies differ substantially in task definition, annotation strategy, model architecture, validation design, and clinical endpoint. This systematic review and evidence-gap analysis aimed to map the translational readiness of TIL-related machine learning studies in breast cancer histopathology and to identify cluster-specific methodological gaps. Methods: A systematic search of PubMed, Web of Science, Scopus, ScienceDirect, and Google Scholar was conducted up to 20 April 2026, supplemented by backward citation tracing and a targeted Google search of the 30 most relevant additional results. Eligible studies included breast cancer histopathology-based machine learning, deep learning, artificial intelligence, or computational image-analysis studies evaluating TILs or TIL-related immune-cell features. Studies were grouped by principal application into detection/classification, outcome prognostication, and treatment-response prediction. Extracted variables included data source, specimen type, model family, annotation strategy, validation design, clinical comparator use, calibration, decision-curve analysis, incremental value, reproducibility, and methodological challenges. Because of heterogeneity in endpoints and performance metrics, synthesis was descriptive and evidence-map based. Results: The primary evidence map included 51 histopathology-image studies: 19 detection/classification, 18 outcome prognostication, and 14 treatment-response prediction studies. External validation was reported in 31.6% of detection/classification studies, 61.1% of prognostication studies, and 57.1% of treatment-response prediction studies. Clinical comparator reporting increased across the same continuum, from 63.2% to 94.4% and 92.9%, respectively. However, calibration was reported in only one prognostication study (5.6%) and in no detection/classification or treatment-response prediction studies. Decision-curve analysis was similarly limited to one prognostication study. Class imbalance was near-universal (94.7–100% across clusters). Scanner/stain robustness was addressed in a majority of studies (63.2–83.3%), but fairness or subgroup analyses remained inconsistently reported (27.8–57.1%). Conclusions: TIL machine learning in breast cancer is technically active but clinically under-validated. Future studies should move beyond model development toward externally validated, calibrated, clinically benchmarked, reproducible, and decision-relevant evidence, using cluster-specific planning standards for detection, prognostication, and treatment-response prediction. Systematic review registration: https://www.crd.york.ac.uk/PROSPERO/view/CRD42024574566 , identifier CRD42024574566.
SN - 2234-943X
ER -