An automatic entropy method to efficiently mask histology whole-slide images

Yipei Song; Francesco Cisternino; Joost M Mekke; Gert J de Borst; Dominique P V de Kleijn; Gerard Pasterkamp; Aryan Vink; Craig A Glastonbury; Sander W van der Laan; Clint L Miller

doi:10.1038/s41598-023-29638-1

An automatic entropy method to efficiently mask histology whole-slide images

Sci Rep. 2023 Mar 15;13(1):4321. doi: 10.1038/s41598-023-29638-1.

Authors

Yipei Song^{1

2}, Francesco Cisternino³, Joost M Mekke⁴, Gert J de Borst⁴, Dominique P V de Kleijn⁴, Gerard Pasterkamp⁵, Aryan Vink⁶, Craig A Glastonbury³, Sander W van der Laan^#⁷, Clint L Miller^#^{8

9}

Affiliations

¹ Department of Computer Engineering, University of Virginia, Charlottesville, VA, 22908, USA.
² Center for Public Health Genomics, University of Virginia, MSB 3231, PO Box 800717, Charlottesville, VA, 22908, USA.
³ Human Technopole, Viale Rita Levi-Montalcini, 1, 20157, Milano, Italy.
⁴ Department of Vascular Surgery, Division Surgical Specialties, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
⁵ Central Diagnostics Laboratory, Division Laboratories, Pharmacy, and Biomedical Genetics, University Medical Center Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands.
⁶ Department of Pathology, Division Laboratories, Pharmacy, and Biomedical Genetics, University Medical Center Utrecht, Utrecht University, Utrecht, The Netherlands.
⁷ Central Diagnostics Laboratory, Division Laboratories, Pharmacy, and Biomedical Genetics, University Medical Center Utrecht, Utrecht University, Heidelberglaan 100, 3584 CX, Utrecht, The Netherlands. s.w.vanderlaan-2@umcutrecht.nl.
⁸ Center for Public Health Genomics, University of Virginia, MSB 3231, PO Box 800717, Charlottesville, VA, 22908, USA. clintm@virginia.edu.
⁹ Department of Public Health Sciences, Department of Biochemistry and Molecular Genetics, University of Virginia, Charlottesville, VA, 22908, USA. clintm@virginia.edu.

^# Contributed equally.

Abstract

Tissue segmentation of histology whole-slide images (WSI) remains a critical task in automated digital pathology workflows for both accurate disease diagnosis and deep phenotyping for research purposes. This is especially challenging when the tissue structure of biospecimens is relatively porous and heterogeneous, such as for atherosclerotic plaques. In this study, we developed a unique approach called 'EntropyMasker' based on image entropy to tackle the fore- and background segmentation (masking) task in histology WSI. We evaluated our method on 97 high-resolution WSI of human carotid atherosclerotic plaques in the Athero-Express Biobank Study, constituting hematoxylin and eosin and 8 other staining types. Using multiple benchmarking metrics, we compared our method with four widely used segmentation methods: Otsu's method, Adaptive mean, Adaptive Gaussian and slideMask and observed that our method had the highest sensitivity and Jaccard similarity index. We envision EntropyMasker to fill an important gap in WSI preprocessing, machine learning image analysis pipelines, and enable disease phenotyping beyond the field of atherosclerosis.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Entropy
Histological Techniques
Humans
Image Processing, Computer-Assisted / methods
Machine Learning
Plaque, Atherosclerotic* / diagnostic imaging

Grants and funding

R00HL125912/NH/NIH HHS/United States