Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms
Histopathology · 2025
DOI: 10.1111/his.15294 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Histopathology, 2025. Verfasst von Mieke C Zwager und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pathology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands. Hauptthemen laut MEDLINE: Ki-67 Antigen, Breast Neoplasms, Algorithms. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Aim
Manual detection and scoring of Ki67 hotspots is difficult and prone to variability, limiting its clinical utility. Automated hotspot detection and scoring by digital image analysis (DIA) could improve the assessment of the Ki67 hotspot proliferation index (PI). This study compared the clinical performance of Ki67 hotspot detection and scoring DIA algorithms based on virtual dual staining (VDS) and deep learning (DL) with manual Ki67 hotspot PI assessment.
Methods
Tissue sections of 135 consecutive invasive breast carcinomas were immunohistochemically stained for Ki67. Two DIA algorithms, based on VDS and DL, automatically determined the Ki67 hotspot PI. For manual assessment; two independent observers detected hotspots and calculated scores using a validated scoring protocol.
Results
Automated hotspot detection and assessment by VDS and DL could be performed in 73% and 100% of the cases, respectively. Automated hotspot detection by VDS and DL led to higher Ki67 hotspot PIs (mean 39.6% and 38.3%, respectively) compared to manual consensus Ki67 PIs (mean 28.8%). Comparing manual consensus Ki67 PIs with VDS Ki67 PIs revealed substantial correlation ( r = 0.90), while manual consensus versus DL Ki67 PIs demonstrated high correlation ( r = 0.95).
Conclusion
Automated Ki67 hotspot detection and analysis correlated strongly with manual Ki67 assessment and provided higher PIs compared to manual assessment. The DL‐based algorithm outperformed the VDS‐based algorithm in clinical applicability, because it did not depend on virtual alignment of slides and correlated stronger with manual scores. Use of a DL‐based algorithm may allow clearer Ki67 PI cutoff values, thereby improving the clinical usability of Ki67.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pathology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
- Department of Epidemiology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands.
- Visiopharm, Hørsholm, Denmark.
- Pathologie Friesland, Leeuwarden, The Netherlands.
ORCID-Profile: Mieke C Zwager, Shibo Yu, Henk J Buikema, Geertruida H de Bock, Jeppe Thagaard, Timco Koopman, Bert van der Vegt
Zitieren
APA
Zwager, M. C., Yu, S., Buikema, H. J., de Bock, G. H., Ramsing, T. W., Thagaard, J., Koopman, T., & van der Vegt, B. (2025). Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms. Histopathology. https://doi.org/10.1111/his.15294
Vancouver
Zwager MC, Yu S, Buikema HJ, de Bock GH, Ramsing TW, Thagaard J, et al. Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms. Histopathology. 2025. doi:10.1111/his.15294
BibTeX
@article{Zwager2025,
author = {Zwager, Mieke C and Yu, Shibo and Buikema, Henk J and de Bock, Geertruida H and Ramsing, Thomas W and Thagaard, Jeppe and Koopman, Timco and van der Vegt, Bert},
title = {Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms},
journal = {Histopathology},
year = {2025},
doi = {10.1111/his.15294}
}
EUVIMED