EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Scalable Nuclei Detection in HER2-SISH Whole Slide Images via Fine-Tuned Stardist with Expert-Annotated Regions of Interest

Zaka Ur Rehman iD, Mohammad Faizal Ahmad Fauzi iD, Wan Siti Halimatul Munirah Wan Ahmad iD, Fazly Salleh Abas iD, Phaik-Leng Cheah, Seow-Fan Chiew, Lai-Meng Looi

Diagnostics · 22.06.2025 · 15 (13) · 1584

DOI: 10.3390/diagnostics15131584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 22.06.2025. Verfasst von Zaka Ur Rehman und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Image and Vision Computing, CoE for Artificial Intelligence, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malay…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Multimedia University, TMR&D Research Grant, Multimedia University’s Postdoctoral Research Scheme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Breast cancer remains a critical health concern worldwide, with histopathological analysis of tissue biopsies serving as the clinical gold standard for diagnosis. Manual evaluation of histopathology images is time-intensive and requires specialized expertise, often resulting in variability in diagnostic outcomes. In silver in situ hybridization (SISH) images, accurate nuclei detection is essential for precise histo-scoring of HER2 gene expression, directly impacting treatment decisions.

Methods

This study presents a scalable and automated deep learning framework for nuclei detection in HER2-SISH whole slide images (WSIs), utilizing a novel dataset of 100 expert-marked regions extracted from 20 WSIs collected at the University of Malaya Medical Center (UMMC). The proposed two-stage approach combines a pretrained Stardist model with image processing-based annotations, followed by fine tuning on our domain-specific dataset to improve generalization.

Results

The fine-tuned model achieved substantial improvements over both the pretrained Stardist model and a conventional watershed segmentation baseline. Quantitatively, the proposed method attained an average F1-score of 98.1% for visual assessments and 97.4% for expert-marked nuclei, outperforming baseline methods across all metrics. Additionally, training and validation performance curves demonstrate stable model convergence over 100 epochs.

Conclusions

These results highlight the robustness of our approach in handling the complex morphological characteristics of SISH-stained nuclei. Our framework supports pathologists by offering reliable, automated nuclei detection in HER2 scoring workflows, contributing to diagnostic consistency and efficiency in clinical pathology.

Schlagwörter

Stichwörter der Autor:innen

deep learningdigital pathologyhuman epidermal growth factor receptor 2 (HER2)silver-enhanced in situ hybridization (SISH)

Autor:innen und Institutionen

  • Centre for Image and Vision Computing, CoE for Artificial Intelligence, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malaysia.
  • Faculty of Artificial Intelligence and Engineering, Multimedia University, Persiaran Multimedia, Cyberjaya 63100, Selangor, Malaysia.
  • Institute for Research, Development and Innovation, IMU University, Bukit Jalil, Kuala Lumpur 57000, Malaysia.
  • Faculty of Engineering and Technology, Multimedia University, Bukit Beruang 75450, Melaka, Malaysia.
  • Department of Pathology, University Malaya-Medical Center, Kuala Lumpur 59100, Malaysia.

ORCID-Profile: Zaka Ur Rehman, Mohammad Faizal Ahmad Fauzi, Wan Siti Halimatul Munirah Wan Ahmad, Fazly Salleh Abas

Förderung

  • Multimedia University
  • TMR&D Research Grant
  • Multimedia University’s Postdoctoral Research Scheme

Zitieren

APA

Rehman, Z. U., Ahmad Fauzi, M. F., Wan Ahmad, W. S. H. M., Abas, F. S., Cheah, P. L., Chiew, S. F., & Looi, L. M. (2025). Scalable Nuclei Detection in HER2-SISH Whole Slide Images via Fine-Tuned Stardist with Expert-Annotated Regions of Interest. Diagnostics, 15(13), 1584. https://doi.org/10.3390/diagnostics15131584

Vancouver

Rehman ZU, Ahmad Fauzi MF, Wan Ahmad WSHM, Abas FS, Cheah PL, Chiew SF, et al. Scalable Nuclei Detection in HER2-SISH Whole Slide Images via Fine-Tuned Stardist with Expert-Annotated Regions of Interest. Diagnostics. 2025;15(13):1584. doi:10.3390/diagnostics15131584

BibTeX
@article{Rehman2025,
  author = {Rehman, Zaka Ur and Ahmad Fauzi, Mohammad Faizal and Wan Ahmad, Wan Siti Halimatul Munirah and Abas, Fazly Salleh and Cheah, Phaik-Leng and Chiew, Seow-Fan and Looi, Lai-Meng},
  title = {Scalable Nuclei Detection in HER2-SISH Whole Slide Images via Fine-Tuned Stardist with Expert-Annotated Regions of Interest},
  journal = {Diagnostics},
  year = {2025},
  volume = {15},
  number = {13},
  pages = {1584},
  doi = {10.3390/diagnostics15131584}
}
Kostenlos starten →