Artificial intelligence modelling in grading breast phyllodes tumours
Histopathology · 2026
DOI: 10.1111/his.70144 ↗Kurz gefasst
Fachartikel in der Zeitschrift Histopathology, 2026. Verfasst von Jessica Ee Ting Koong und 9 weiteren Autor:innen. Beteiligte Einrichtung: Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore. Hauptthemen laut MEDLINE: Phyllodes Tumor, Breast Neoplasms, Artificial Intelligence, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 11 Literaturangaben.
Abstract (Originalsprache)
Background
Breast phyllodes tumours (PT) are rare biphasic neoplasms consisting of epithelial and stromal components. They are classified into benign, borderline and malignant categories. Diagnosing and grading PTs present a challenge for pathologists, as there are multiple histological parameters and their own tiers. We aim to investigate the potential role of artificial intelligence (AI) as a diagnostic aid in determining PT grade. Materials and methods We investigated 15 PT whole slide images (WSIs), comprising 5 benign, 5 borderline and 5 malignant cases. We sought to classify and retrieve the most relevant WSIs by matching histological features at different patch sizes, using the Yottixel framework for WSI processing. Patches were extracted at a 20× magnification level. We then used the KimiaNet to extract feature vectors and transformed these into barcode representations. Barcodes of a query WSI were compared with those of others in the archive, allowing us to identify the most similar WSI and determine the PT grades from histological similarities.
Results
We utilized ‘majority‐n accuracy’ as a measure of correctness, that is when the majority of the top‐n search results have the correct diagnosis as the query patient. We achieved a maximum reported accuracy of 67%, with a 3000 × 3000 patch size when grading PT at majority voting with n = 4.
Conclusion
Despite the small sample size and absence of fine‐tuning, our study demonstrated the potential of AI‐based PT grade stratification using various patch sizes through histological matching. This serves as a preliminary proof of concept, with the prospect of refinement for potential routine clinical application.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
- Kimia Lab, Department of AI&I, Mayo Clinic, Rochester, Minnesota, USA.
- Singapore Breast Surgery Center, Singapore, Singapore.
- Loyola University Stritch School of Medicine, Maywood, Illinois, USA.
- Department of Clinical Pathology, Hokuto Hospital, Obihiro, Hokkaido, Japan.
- School of Medicine, Western Sydney University, Sydney, New South Wales, Australia.
ORCID-Profile: Jessica Ee Ting Koong, Abubakr Shafique, Nur Diyana Md Nasir, Aaron Han, Oi Harada, Soon Lee, Rieko Nishimura, Yasuyo Ohi, Hamid R Tizhoosh, Puay Hoon Tan
Zitieren
APA
Koong, J. E. T., Shafique, A., Md Nasir, N. D., Han, A., Harada, O., Lee, S., Nishimura, R., Ohi, Y., Tizhoosh, H. R., & Tan, P. H. (2026). Artificial intelligence modelling in grading breast phyllodes tumours. Histopathology. https://doi.org/10.1111/his.70144
Vancouver
Koong JET, Shafique A, Md Nasir ND, Han A, Harada O, Lee S, et al. Artificial intelligence modelling in grading breast phyllodes tumours. Histopathology. 2026. doi:10.1111/his.70144
BibTeX
@article{Koong2026,
author = {Koong, Jessica Ee Ting and Shafique, Abubakr and Md Nasir, Nur Diyana and Han, Aaron and Harada, Oi and Lee, Soon and Nishimura, Rieko and Ohi, Yasuyo and Tizhoosh, Hamid R and Tan, Puay Hoon},
title = {Artificial intelligence modelling in grading breast phyllodes tumours},
journal = {Histopathology},
year = {2026},
doi = {10.1111/his.70144}
}
EUVIMED