Pyramid-level training with stain normalization for breast cancer lymph-node metastasis segmentation in whole-slide images
PLOS One · 13.11.2026 · 21 (11) · e0362258
DOI: 10.1371/journal.pone.0362258 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 13.11.2026. Verfasst von Hamza Almobayed und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Engineering, Bolu Abant İzzet Baysal University, Bolu, Turkey. Hauptthemen laut MEDLINE: Breast Neoplasms, Lymphatic Metastasis, Image Processing, Computer-Assisted, Lymph Nodes. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Whole-slide histopathology images encode metastatic tissue information simultaneously at multiple spatial scales, from fine cellular morphology at high magnification to broad tissue architecture at low magnification. Existing segmentation models commonly operate at a single fixed resolution, leaving complementary information distributed across the whole-slide image pyramid underused. We present a multilevel segmentation framework with stain-normalization preprocessing that trains a unified model jointly across four study-defined WSI pyramid views (5 × –40 × ), integrating Vahadane stain normalization and structured class-balanced sampling stratified by pyramid level, dataset, and tissue class. Applied to a 280-slide CAMELYON16/CAMELYON17 study cohort under strict slide-level data separation (196 training, 42 validation, 42 held-out test slides), the framework achieves a Dice coefficient of 92.39% on the held-out test set. Relative to the single-scale U-Net baseline (89.00%), the paired slide-level improvement is 3.39 percentage points (95% bootstrap CI: 3.19–3.60 pp; Cohen’s d z = 4.98 ; two-sided permutation p < 0.00001). Per-level evaluation confirms that full pyramid fusion outperforms each individual scale, while a boundary-focused L1 audit yields a mean HD95 of 53.88 pixels (95% CI: 50.28–57.64). The contribution is therefore a training-sampling and evaluation pipeline rather than a new network layer or architecture. These results show that multiresolution training, stain normalization, structured sampling, and leakage-controlled evaluation can materially improve breast lymph-node metastasis segmentation on established WSI benchmarks. A supplementary external cross-dataset evaluation on 103 paired BCSS breast-histopathology ROIs, performed without retraining or fine-tuning, yielded a pooled Dice of 70.58%, IoU of 54.54%, precision of 55.95%, and recall of 95.57%; the mean per-ROI Dice was 67.89% (95% bootstrap CI: 65.00–70.76%). These external results demonstrate substantial sensitivity to tumor-like tissue under a different image source and semantic annotation scheme, while also exposing the expected effect of annotation granularity and class-definition mismatch on overlap and boundary metrics.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computer Engineering, Bolu Abant İzzet Baysal University, Bolu, Turkey.
- Department of Pathology, Bolu Abant Izzet Baysal University, Faculty of Medicine, Bolu, Turkey.
ORCID-Profile: Hamza Almobayed, Ali Yilmaz, Umit Senturk, Alperen Akgül
Zitieren
APA
Almobayed, H., Yilmaz, A., Senturk, U., Erdogan Duzcu, S., & Akgül, A. (2026). Pyramid-level training with stain normalization for breast cancer lymph-node metastasis segmentation in whole-slide images. PLOS One, 21(11), e0362258. https://doi.org/10.1371/journal.pone.0362258
Vancouver
Almobayed H, Yilmaz A, Senturk U, Erdogan Duzcu S, Akgül A. Pyramid-level training with stain normalization for breast cancer lymph-node metastasis segmentation in whole-slide images. PLOS One. 2026;21(11):e0362258. doi:10.1371/journal.pone.0362258
BibTeX
@article{Almobayed2026,
author = {Almobayed, Hamza and Yilmaz, Ali and Senturk, Umit and Erdogan Duzcu, Selma and Akgül, Alperen},
title = {Pyramid-level training with stain normalization for breast cancer lymph-node metastasis segmentation in whole-slide images},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0362258},
doi = {10.1371/journal.pone.0362258}
}
EUVIMED