Computer-Assisted Annotation of Digital H&E/SOX10 Dual Stains Generates High-Performing Convolutional Neural Network for Calculating Tumor Burden in H&E-Stained Cutaneous Melanoma

Patricia Switten Nielsen (), Jeanette Baehr Georgsen, Mads Sloth Vinding, Lasse Riis Østergaard and Torben Steiniche
Additional contact information
Patricia Switten Nielsen: Department of Pathology, Aarhus University Hospital, Palle Juul-Jensens Boulevard 35, DK-8200 Aarhus, Denmark
Jeanette Baehr Georgsen: Department of Pathology, Aarhus University Hospital, Palle Juul-Jensens Boulevard 35, DK-8200 Aarhus, Denmark
Mads Sloth Vinding: Department of Clinical Medicine, Aarhus University, Palle Juul-Jensens Boulevard 82, DK-8200 Aarhus, Denmark
Lasse Riis Østergaard: Department of Health Science and Technology, Aalborg University, Fredrik Bajers Vej 7E, DK-9220 Aalborg, Denmark
Torben Steiniche: Department of Pathology, Aarhus University Hospital, Palle Juul-Jensens Boulevard 35, DK-8200 Aarhus, Denmark

IJERPH, 2022, vol. 19, issue 21, 1-19

Abstract: Deep learning for the analysis of H&E stains requires a large annotated training set. This may form a labor-intensive task involving highly skilled pathologists. We aimed to optimize and evaluate computer-assisted annotation based on digital dual stains of the same tissue section. H&E stains of primary and metastatic melanoma ( N = 77) were digitized, re-stained with SOX10, and re-scanned. Because images were aligned, annotations of SOX10 image analysis were directly transferred to H&E stains of the training set. Based on 1,221,367 annotated nuclei, a convolutional neural network for calculating tumor burden (CNN TB ) was developed. For primary melanomas, precision of annotation was 100% (95%CI, 99% to 100%) for tumor cells and 99% (95%CI, 98% to 100%) for normal cells. Due to low or missing tumor-cell SOX10 positivity, precision for normal cells was markedly reduced in lymph-node and organ metastases compared with primary melanomas ( p < 0.001). Compared with stereological counts within skin lesions, mean difference in tumor burden was 6% (95%CI, −1% to 13%, p = 0.10) for CNN TB and 16% (95%CI, 4% to 28%, p = 0.02) for pathologists. Conclusively, the technique produced a large annotated H&E training set with high quality within a reasonable timeframe for primary melanomas and subcutaneous metastases. For these lesion types, the training set generated a high-performing CNN TB , which was superior to the routine assessments of pathologists.

Keywords: deep learning; artificial intelligence; digital pathology; melanoma; immunohistochemistry; H&E; SOX10; IHC-supervised annotation; digital multiple stains; tumor burden (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1660-4601/19/21/14327/pdf (application/pdf)
https://www.mdpi.com/1660-4601/19/21/14327/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:19:y:2022:i:21:p:14327-:d:961032

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().