EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stain SAN: simultaneous augmentation and normalization for histopathology images

Taebin Kim iD, Yao Li iD, Benjamin C Calhoun iD, Aatish Thennavan, Lisa A Carey iD, W Fraser Symmans, Melissa A Troester, Charles M Perou, J S Marron iD

Journal of Medical Imaging · 23.08.2024 · 11 (04) · 1-14

DOI: 10.1117/1.jmi.11.4.044006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Imaging, erschienen am 23.08.2024. Verfasst von Taebin Kim und 8 weiteren Autor:innen. Beteiligte Einrichtung: University of North Carolina at Chapel Hill, Department of Statistics and Operations Research, Chapel Hill, North Carolina, United States. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIEHS NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PurposeWe address the need for effective stain domain adaptation methods in histopathology to enhance the performance of downstream computational tasks, particularly classification. Existing methods exhibit varying strengths and weaknesses, prompting the exploration of a different approach. The focus is on improving stain color consistency, expanding the stain domain scope, and minimizing the domain gap between image batches.ApproachWe introduce a new domain adaptation method, Stain simultaneous augmentation and normalization (SAN), designed to adjust the distribution of stain colors to align with a target distribution. Stain SAN combines the merits of established methods, such as stain normalization, stain augmentation, and stain mix-up, while mitigating their inherent limitations. Stain SAN adapts stain domains by resampling stain color matrices from a well-structured target distribution.ResultsExperimental evaluations of cross-dataset clinical estrogen receptor status classification demonstrate the efficacy of Stain SAN and its superior performance compared with existing stain adaptation methods. In one case, the area under the curve (AUC) increased by 11.4%. Overall, our results clearly show the improvements made over the history of the development of these methods culminating with substantial enhancement provided by Stain SAN. Furthermore, we show that Stain SAN achieves results comparable with the state-of-the-art generative adversarial network-based approach without requiring separate training for stain adaptation or access to the target domain during training. Stain SAN’s performance is on par with HistAuGAN, proving its effectiveness and computational efficiency.ConclusionsStain SAN emerges as a promising solution, addressing the potential shortcomings of contemporary stain adaptation methods. Its effectiveness is underscored by notable improvements in the context of clinical estrogen receptor status classification, where it achieves the best AUC performance. The findings endorse Stain SAN as a robust approach for stain domain adaptation in histopathology images, with implications for advancing computational tasks in the field.

Schlagwörter

Stichwörter der Autor:innen

batch adjustmentcolor transformationdomain adaptationhistopathologytissue staining

Autor:innen und Institutionen

  • University of North Carolina at Chapel Hill, Department of Statistics and Operations Research, Chapel Hill, North Carolina, United States.
  • University of North Carolina at Chapel Hill, Department of Pathology and Laboratory Medicine, Chapel Hill, North Carolina, United States.
  • University of North Carolina at Chapel Hill, UNC Lineberger Comprehensive Cancer Center, Chapel Hill, North Carolina, United States.
  • The University of Texas MD Anderson Cancer Center, Department of Systems Biology, Houston, Texas, United States.
  • University of North Carolina at Chapel Hill, Department of Medicine, Chapel Hill, North Carolina, United States.
  • The University of Texas MD Anderson Cancer Center, Department of Pathology, Houston, Texas, United States.

ORCID-Profile: Taebin Kim, Yao Li, Benjamin C Calhoun, Lisa A Carey, J S Marron

Förderung

  • NIEHS NIH HHS
  • NCI NIH HHS

Zitieren

APA

Kim, T., Li, Y., Calhoun, B. C., Thennavan, A., Carey, L. A., Symmans, W. F., Troester, M. A., Perou, C. M., & Marron, J. S. (2024). Stain SAN: simultaneous augmentation and normalization for histopathology images. Journal of Medical Imaging, 11(04), 1-14. https://doi.org/10.1117/1.jmi.11.4.044006

Vancouver

Kim T, Li Y, Calhoun BC, Thennavan A, Carey LA, Symmans WF, et al. Stain SAN: simultaneous augmentation and normalization for histopathology images. Journal of Medical Imaging. 2024;11(04):1-14. doi:10.1117/1.jmi.11.4.044006

BibTeX
@article{Kim2024,
  author = {Kim, Taebin and Li, Yao and Calhoun, Benjamin C and Thennavan, Aatish and Carey, Lisa A and Symmans, W Fraser and Troester, Melissa A and Perou, Charles M and Marron, J S},
  title = {Stain SAN: simultaneous augmentation and normalization for histopathology images},
  journal = {Journal of Medical Imaging},
  year = {2024},
  volume = {11},
  number = {04},
  pages = {1--14},
  doi = {10.1117/1.jmi.11.4.044006}
}
Kostenlos starten →