Advancing Ki67 hotspot detection in breast cancer: a comparative analysis of automated digital image analysis algorithms
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.
Authors
- Thomas W. Ramsing
- Jeppe Thagaard (ORCID: https://orcid.org/0000-0003-0201-2243)
- Bert van der Vegt (ORCID: https://orcid.org/0000-0002-2613-1506)
- Henk J. Buikema (ORCID: https://orcid.org/0009-0007-3234-4595)
- Mieke C. Zwager (ORCID: https://orcid.org/0000-0002-4470-7628)
- Shibo Yu (ORCID: https://orcid.org/0000-0001-5646-5710)
- Geertruida H. de Bock (ORCID: https://orcid.org/0000-0003-3104-4471)
- Timco Koopman (ORCID: https://orcid.org/0000-0001-5695-0126)
Institutions
- University Medical Center Groningen (NL)
- University of Groningen (NL)
- Friesland College (NL)
Publication Details
- Journal
- Histopathology
- Published
- 2024-08-05
- DOI
- https://doi.org/10.1111/his.15294
- Citations
- 7
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 2.83