Next Article in Journal
Biosynthesis of Sesquiterpenes in Basidiomycetes: A Review
Next Article in Special Issue
Identification of Dermatophyte and Non-Dermatophyte Agents in Onychomycosis by PCR and DNA Sequencing—A Retrospective Comparison of Diagnostic Tools
Previous Article in Journal
Antifungal Activity of Copper Oxide Nanoparticles against Root Rot Disease in Cucumber
Previous Article in Special Issue
Alternative Splicing in Trichophyton rubrum Occurs in Efflux Pump Transcripts in Response to Antifungal Drugs
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JoF
Volume 8
Issue 9
10.3390/jof8090912
jof-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images

by
Philipp Jansen
1,2,†,
Adelaida Creosteanu
3,†,
Viktor Matyas
3,
Amrei Dilling
4,
Ana Pina
5,
Andrea Saggini
5,
Tobias Schimming
6,
Jennifer Landsberg
2,
Birte Burgdorf
1,
Sylvia Giaquinta
7,
Hansgeorg Müller
8,
Michael Emberger
9,
Christian Rose
10,
Lutz Schmitz
11,
Cyrill Geraud
12,
Dirk Schadendorf
1,
Jörg Schaller
13,
Maximilian Alber
3,14,
Frederick Klauschen
14,15,16,17,18,‡ and
Klaus G. Griewank
1,7,*,‡
1
Department of Dermatology, University Hospital Essen, Hufelandstraße 55, 45122 Essen, Germany
2
Department of Dermatology, University Hospital Bonn, Venusberg-Campus 1, 53127 Bonn, Germany
3
Aignostics GmbH, 10555 Berlin, Germany
4
Department of Dermatology, Charité Berlin, 10117 Berlin, Germany
5
Center for Dermatopathology, 79106 Freiburg, Germany
6
Department of Dermatology Hornheide, 48157 Münster, Germany
7
Dermatopathology Near Mainz, 55268 Nieder-Olm, Germany
8
Dermatohistology am Stachus, 80331 München, Germany
9
Patholab, 5020 Salzburg, Austria
10
Institute for Dermatohistology, 23562 Lübeck, Germany
11
Institute for Dermatopathology, 53115 Bonn, Germany
12
Department of Dermatology, University Hospital Mannheim, 68167 Mannheim, Germany
13
MVZ Dermatopathology Duisburg Essen GmbH, 45329 Essen, Germany
14
Institute of Pathology, Charité Berlin, 10117 Berlin, Germany
15
Institute of Pathology, Ludwig-Maximilians University Munich, 80337 München, Germany
16
German Cancer Research Center (DKFZ) and German Cancer Consortium (DKTK), Munich Partner Site, 80336 München, Germany
17
BIFOLD—Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany
18
BIH—Berlin Institute of Health, Anna-Louisa-Karsch-Straße 2, 10178 Berlin, Germany
 
add Show full affiliation list
 
remove Hide full affiliation list
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
‡
These authors contributed equally to this work.
J. Fungi 2022, 8(9), 912; https://doi.org/10.3390/jof8090912
Submission received: 17 July 2022 / Revised: 18 August 2022 / Accepted: 25 August 2022 / Published: 28 August 2022
(This article belongs to the Special Issue Dermatophytes and Dermatophytoses)
Browse Figures
Review Reports Versions Notes

Abstract

Background: Onychomycosis numbers among the most common fungal infections in humans affecting finger- or toenails. Histology remains a frequently applied screening technique to diagnose onychomycosis. Screening slides for fungal elements can be time-consuming for pathologists, and sensitivity in cases with low amounts of fungi remains a concern. Convolutional neural networks (CNNs) have revolutionized image classification in recent years. The goal of our project was to evaluate if a U-NET-based segmentation approach as a subcategory of CNNs can be applied to detect fungal elements on digitized histologic sections of human nail specimens and to compare it with the performance of 11 board-certified dermatopathologists. Methods: In total, 664 corresponding H&E- and PAS-stained histologic whole-slide images (WSIs) of human nail plates from four different laboratories were digitized. Histologic structures were manually annotated. A U-NET image segmentation model was trained for binary segmentation on the dataset generated by annotated slides. Results: The U-NET algorithm detected 90.5% of WSIs with fungi, demonstrating a comparable sensitivity with that of the 11 board-certified dermatopathologists (sensitivity of 89.2%). Conclusions: Our results demonstrate that machine-learning-based algorithms applied to real-world clinical cases can produce comparable sensitivities to human pathologists. Our established U-NET may be used as a supportive diagnostic tool to preselect possible slides with fungal elements. Slides where fungal elements are indicated by our U-NET should be reevaluated by the pathologist to confirm or refute the diagnosis of onychomycosis.
Keywords: deep learning; artificial intelligence; U-NET; onychomycosis; dermatology deep learning; artificial intelligence; U-NET; onychomycosis; dermatology

Share and Cite

MDPI and ACS Style

Jansen, P.; Creosteanu, A.; Matyas, V.; Dilling, A.; Pina, A.; Saggini, A.; Schimming, T.; Landsberg, J.; Burgdorf, B.; Giaquinta, S.; et al. Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images. J. Fungi 2022, 8, 912. https://doi.org/10.3390/jof8090912

AMA Style

Jansen P, Creosteanu A, Matyas V, Dilling A, Pina A, Saggini A, Schimming T, Landsberg J, Burgdorf B, Giaquinta S, et al. Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images. Journal of Fungi. 2022; 8(9):912. https://doi.org/10.3390/jof8090912

Chicago/Turabian Style

Jansen, Philipp, Adelaida Creosteanu, Viktor Matyas, Amrei Dilling, Ana Pina, Andrea Saggini, Tobias Schimming, Jennifer Landsberg, Birte Burgdorf, Sylvia Giaquinta, and et al. 2022. "Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images" Journal of Fungi 8, no. 9: 912. https://doi.org/10.3390/jof8090912

APA Style

Jansen, P., Creosteanu, A., Matyas, V., Dilling, A., Pina, A., Saggini, A., Schimming, T., Landsberg, J., Burgdorf, B., Giaquinta, S., Müller, H., Emberger, M., Rose, C., Schmitz, L., Geraud, C., Schadendorf, D., Schaller, J., Alber, M., Klauschen, F., & Griewank, K. G. (2022). Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images. Journal of Fungi, 8(9), 912. https://doi.org/10.3390/jof8090912

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop