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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jansen, Philipp (VerfasserIn) , Creosteanu, Adelaida (VerfasserIn) , Matyas, Viktor (VerfasserIn) , Dilling, Amrei (VerfasserIn) , Pina, Ana (VerfasserIn) , Saggini, Andrea (VerfasserIn) , Schimming, Tobias (VerfasserIn) , Landsberg, Jennifer (VerfasserIn) , Burgdorf, Birte (VerfasserIn) , Giaquinta, Sylvia (VerfasserIn) , Müller, Hansgeorg (VerfasserIn) , Emberger, Michael (VerfasserIn) , Rose, Christian (VerfasserIn) , Schmitz, Lutz (VerfasserIn) , Géraud, Cyrill (VerfasserIn) , Schadendorf, Dirk (VerfasserIn) , Schaller, Jörg (VerfasserIn) , Alber, Maximilian (VerfasserIn) , Klauschen, Frederick (VerfasserIn) , Griewank, Klaus G. (VerfasserIn)
Dokumenttyp: Article (Journal)
Sprache:Englisch
Veröffentlicht: 28 August 2022
In: Journal of Fungi
Year: 2022, Jahrgang: 8, Heft: 9, Pages: 1-13
ISSN:2309-608X
DOI:10.3390/jof8090912
Online-Zugang:Verlag, kostenfrei, Volltext: https://doi.org/10.3390/jof8090912
Verlag, kostenfrei, Volltext: https://www.mdpi.com/2309-608X/8/9/912
Volltext
Verfasserangaben:Philipp Jansen, Adelaida Creosteanu, Viktor Matyas, Amrei Dilling, Ana Pina, Andrea Saggini, Tobias Schimming, Jennifer Landsberg, Birte Burgdorf, Sylvia Giaquinta, Hansgeorg Müller, Michael Emberger, Christian Rose, Lutz Schmitz, Cyrill Geraud, Dirk Schadendorf, Jörg Schaller, Maximilian Alber, Frederick Klauschen and Klaus G. Griewank

MARC

LEADER 00000caa a2200000 c 4500
001 1860239064
003 DE-627
005 20250522232911.0
007 cr uuu---uuuuu
008 230925s2022 xx |||||o 00| ||eng c
024 7 |a 10.3390/jof8090912  |2 doi 
035 |a (DE-627)1860239064 
035 |a (DE-599)KXP1860239064 
035 |a (OCoLC)1425216643 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 33  |2 sdnb 
100 1 |a Jansen, Philipp  |e VerfasserIn  |0 (DE-588)1069849596  |0 (DE-627)822852616  |0 (DE-576)429543476  |4 aut 
245 1 0 |a Deep learning assisted diagnosis of onychomycosis on whole-slide images  |c Philipp Jansen, Adelaida Creosteanu, Viktor Matyas, Amrei Dilling, Ana Pina, Andrea Saggini, Tobias Schimming, Jennifer Landsberg, Birte Burgdorf, Sylvia Giaquinta, Hansgeorg Müller, Michael Emberger, Christian Rose, Lutz Schmitz, Cyrill Geraud, Dirk Schadendorf, Jörg Schaller, Maximilian Alber, Frederick Klauschen and Klaus G. Griewank 
264 1 |c 28 August 2022 
300 |a 13 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Dieser Artikel gehört zum Special issue: Dermatophytes and dermatophytoses 
500 |a Gesehen am 25.09.2023 
520 |a 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. 
650 4 |a artificial intelligence 
650 4 |a deep learning 
650 4 |a dermatology 
650 4 |a onychomycosis 
650 4 |a U-NET 
700 1 |a Creosteanu, Adelaida  |e VerfasserIn  |4 aut 
700 1 |a Matyas, Viktor  |e VerfasserIn  |4 aut 
700 1 |a Dilling, Amrei  |e VerfasserIn  |4 aut 
700 1 |a Pina, Ana  |e VerfasserIn  |4 aut 
700 1 |a Saggini, Andrea  |e VerfasserIn  |4 aut 
700 1 |8 1\p  |a Schimming, Tobias  |d 1980-  |e VerfasserIn  |0 (DE-588)136477984  |0 (DE-627)584068360  |0 (DE-576)301040699  |4 aut 
700 1 |a Landsberg, Jennifer  |e VerfasserIn  |4 aut 
700 1 |a Burgdorf, Birte  |e VerfasserIn  |4 aut 
700 1 |a Giaquinta, Sylvia  |e VerfasserIn  |4 aut 
700 1 |a Müller, Hansgeorg  |e VerfasserIn  |4 aut 
700 1 |a Emberger, Michael  |e VerfasserIn  |4 aut 
700 1 |8 2\p  |a Rose, Christian  |d 1964-  |e VerfasserIn  |0 (DE-588)143761838  |0 (DE-627)704594951  |0 (DE-576)338777393  |4 aut 
700 1 |a Schmitz, Lutz  |e VerfasserIn  |4 aut 
700 1 |a Géraud, Cyrill  |d 1982-  |e VerfasserIn  |0 (DE-588)137867808  |0 (DE-627)696132583  |0 (DE-576)304908932  |4 aut 
700 1 |a Schadendorf, Dirk  |d 1960-  |e VerfasserIn  |0 (DE-588)11142576X  |0 (DE-627)499566076  |0 (DE-576)289702275  |4 aut 
700 1 |a Schaller, Jörg  |e VerfasserIn  |4 aut 
700 1 |a Alber, Maximilian  |e VerfasserIn  |4 aut 
700 1 |8 3\p  |a Klauschen, Frederick  |d 1974-  |e VerfasserIn  |0 (DE-588)129955779  |0 (DE-627)484980890  |0 (DE-576)297920766  |4 aut 
700 1 |a Griewank, Klaus G.  |e VerfasserIn  |4 aut 
773 0 8 |i Enthalten in  |t Journal of Fungi  |d Basel : MDPI, 2014  |g 8(2022), 9, Artikel-ID 912$m9, Seite 1-13  |h Online-Ressource  |w (DE-627)796588538  |w (DE-600)2784229-0  |w (DE-576)414229444  |x 2309-608X  |7 nnas  |a Deep learning assisted diagnosis of onychomycosis on whole-slide images 
773 1 8 |g volume:8  |g year:2022  |g number:9  |g elocationid:912$m9  |g pages:1-13  |g extent:13  |a Deep learning assisted diagnosis of onychomycosis on whole-slide images 
856 4 0 |u https://doi.org/10.3390/jof8090912  |x Verlag  |x Resolving-System  |z kostenfrei  |3 Volltext 
856 4 0 |u https://www.mdpi.com/2309-608X/8/9/912  |x Verlag  |z kostenfrei  |3 Volltext 
883 |8 1\p  |a cgwrk  |d 20250505  |q DE-101  |u https://d-nb.info/provenance/plan#cgwrk 
883 |8 2\p  |a cgwrk  |d 20250505  |q DE-101  |u https://d-nb.info/provenance/plan#cgwrk 
883 |8 3\p  |a cgwrk  |d 20250505  |q DE-101  |u https://d-nb.info/provenance/plan#cgwrk 
951 |a AR 
992 |a 20230925 
993 |a Article 
994 |a 2022 
998 |g 11142576X  |a Schadendorf, Dirk  |m 11142576X:Schadendorf, Dirk  |d 50000  |e 50000PS11142576X  |k 0/50000/  |p 16 
998 |g 137867808  |a Géraud, Cyrill  |m 137867808:Géraud, Cyrill  |d 60000  |d 61900  |e 60000PG137867808  |e 61900PG137867808  |k 0/60000/  |k 1/60000/61900/  |p 15 
999 |a KXP-PPN1860239064  |e 4378885026 
BIB |a Y 
SER |a journal 
JSO |a {"name":{"displayForm":["Philipp Jansen, Adelaida Creosteanu, Viktor Matyas, Amrei Dilling, Ana Pina, Andrea Saggini, Tobias Schimming, Jennifer Landsberg, Birte Burgdorf, Sylvia Giaquinta, Hansgeorg Müller, Michael Emberger, Christian Rose, Lutz Schmitz, Cyrill Geraud, Dirk Schadendorf, Jörg Schaller, Maximilian Alber, Frederick Klauschen and Klaus G. Griewank"]},"language":["eng"],"note":["Dieser Artikel gehört zum Special issue: Dermatophytes and dermatophytoses","Gesehen am 25.09.2023"],"recId":"1860239064","person":[{"family":"Jansen","role":"aut","display":"Jansen, Philipp","given":"Philipp"},{"display":"Creosteanu, Adelaida","given":"Adelaida","role":"aut","family":"Creosteanu"},{"display":"Matyas, Viktor","given":"Viktor","family":"Matyas","role":"aut"},{"role":"aut","family":"Dilling","display":"Dilling, Amrei","given":"Amrei"},{"given":"Ana","display":"Pina, Ana","role":"aut","family":"Pina"},{"display":"Saggini, Andrea","given":"Andrea","family":"Saggini","role":"aut"},{"family":"Schimming","role":"aut","display":"Schimming, Tobias","given":"Tobias"},{"given":"Jennifer","display":"Landsberg, Jennifer","role":"aut","family":"Landsberg"},{"given":"Birte","display":"Burgdorf, Birte","role":"aut","family":"Burgdorf"},{"given":"Sylvia","display":"Giaquinta, Sylvia","role":"aut","family":"Giaquinta"},{"family":"Müller","role":"aut","display":"Müller, Hansgeorg","given":"Hansgeorg"},{"given":"Michael","display":"Emberger, Michael","role":"aut","family":"Emberger"},{"given":"Christian","display":"Rose, Christian","role":"aut","family":"Rose"},{"family":"Schmitz","role":"aut","display":"Schmitz, Lutz","given":"Lutz"},{"display":"Géraud, Cyrill","given":"Cyrill","role":"aut","family":"Géraud"},{"role":"aut","family":"Schadendorf","given":"Dirk","display":"Schadendorf, Dirk"},{"role":"aut","family":"Schaller","given":"Jörg","display":"Schaller, Jörg"},{"family":"Alber","role":"aut","display":"Alber, Maximilian","given":"Maximilian"},{"role":"aut","family":"Klauschen","given":"Frederick","display":"Klauschen, Frederick"},{"given":"Klaus G.","display":"Griewank, Klaus G.","family":"Griewank","role":"aut"}],"id":{"eki":["1860239064"],"doi":["10.3390/jof8090912"]},"physDesc":[{"extent":"13 S."}],"title":[{"title":"Deep learning assisted diagnosis of onychomycosis on whole-slide images","title_sort":"Deep learning assisted diagnosis of onychomycosis on whole-slide images"}],"type":{"bibl":"article-journal","media":"Online-Ressource"},"origin":[{"dateIssuedKey":"2022","dateIssuedDisp":"28 August 2022"}],"relHost":[{"recId":"796588538","title":[{"title_sort":"Journal of Fungi","title":"Journal of Fungi"}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"eki":["796588538"],"issn":["2309-608X"],"zdb":["2784229-0"]},"origin":[{"dateIssuedKey":"2014","publisherPlace":"Basel","publisher":"MDPI","dateIssuedDisp":"2014-"}],"language":["eng"],"part":{"issue":"9","extent":"13","pages":"1-13","text":"8(2022), 9, Artikel-ID 912$m9, Seite 1-13","year":"2022","volume":"8"},"note":["Gesehen am 26.03.2021"],"pubHistory":["1.2014 -"],"disp":"Deep learning assisted diagnosis of onychomycosis on whole-slide imagesJournal of Fungi","type":{"bibl":"periodical","media":"Online-Ressource"}}]} 
SRT |a JANSENPHILDEEPLEARNI2820