Cargando…
Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images
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 cas...
Autores principales: | , , , , , , , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9504700/ https://www.ncbi.nlm.nih.gov/pubmed/36135637 http://dx.doi.org/10.3390/jof8090912 |
_version_ | 1784796282817085440 |
---|---|
author | Jansen, Philipp Creosteanu, Adelaida Matyas, Viktor Dilling, Amrei Pina, Ana Saggini, Andrea Schimming, Tobias Landsberg, Jennifer Burgdorf, Birte Giaquinta, Sylvia Müller, Hansgeorg Emberger, Michael Rose, Christian Schmitz, Lutz Geraud, Cyrill Schadendorf, Dirk Schaller, Jörg Alber, Maximilian Klauschen, Frederick Griewank, Klaus G. |
author_facet | Jansen, Philipp Creosteanu, Adelaida Matyas, Viktor Dilling, Amrei Pina, Ana Saggini, Andrea Schimming, Tobias Landsberg, Jennifer Burgdorf, Birte Giaquinta, Sylvia Müller, Hansgeorg Emberger, Michael Rose, Christian Schmitz, Lutz Geraud, Cyrill Schadendorf, Dirk Schaller, Jörg Alber, Maximilian Klauschen, Frederick Griewank, Klaus G. |
author_sort | Jansen, Philipp |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9504700 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-95047002022-09-24 Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images Jansen, Philipp Creosteanu, Adelaida Matyas, Viktor Dilling, Amrei Pina, Ana Saggini, Andrea Schimming, Tobias Landsberg, Jennifer Burgdorf, Birte Giaquinta, Sylvia Müller, Hansgeorg Emberger, Michael Rose, Christian Schmitz, Lutz Geraud, Cyrill Schadendorf, Dirk Schaller, Jörg Alber, Maximilian Klauschen, Frederick Griewank, Klaus G. J Fungi (Basel) Article 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. MDPI 2022-08-28 /pmc/articles/PMC9504700/ /pubmed/36135637 http://dx.doi.org/10.3390/jof8090912 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Jansen, Philipp Creosteanu, Adelaida Matyas, Viktor Dilling, Amrei Pina, Ana Saggini, Andrea Schimming, Tobias Landsberg, Jennifer Burgdorf, Birte Giaquinta, Sylvia Müller, Hansgeorg Emberger, Michael Rose, Christian Schmitz, Lutz Geraud, Cyrill Schadendorf, Dirk Schaller, Jörg Alber, Maximilian Klauschen, Frederick Griewank, Klaus G. Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title | Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title_full | Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title_fullStr | Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title_full_unstemmed | Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title_short | Deep Learning Assisted Diagnosis of Onychomycosis on Whole-Slide Images |
title_sort | deep learning assisted diagnosis of onychomycosis on whole-slide images |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9504700/ https://www.ncbi.nlm.nih.gov/pubmed/36135637 http://dx.doi.org/10.3390/jof8090912 |
work_keys_str_mv | AT jansenphilipp deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT creosteanuadelaida deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT matyasviktor deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT dillingamrei deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT pinaana deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT sagginiandrea deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT schimmingtobias deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT landsbergjennifer deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT burgdorfbirte deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT giaquintasylvia deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT mullerhansgeorg deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT embergermichael deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT rosechristian deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT schmitzlutz deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT geraudcyrill deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT schadendorfdirk deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT schallerjorg deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT albermaximilian deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT klauschenfrederick deeplearningassisteddiagnosisofonychomycosisonwholeslideimages AT griewankklausg deeplearningassisteddiagnosisofonychomycosisonwholeslideimages |