Research ExplorerPublicationsA Deep Learning Approach for Histopathological Diagnosis of ...

A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists

Standard

A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists. / Decroos, Florence; Springenberg, Sebastian; Lang, Tobias; Päpper, Marc; Zapf, Antonia; Metze, Dieter; Steinkraus, Volker; Böer-Auer, Almut.

In: ACTA DERM-VENEREOL, Vol. 101, No. 8, 31.08.2021, p. adv00532.

Research output: SCORING: Contribution to journal › SCORING: Journal article › Research › peer-review

Harvard

Decroos, F, Springenberg, S, Lang, T, Päpper, M, Zapf, A, Metze, D, Steinkraus, V & Böer-Auer, A 2021, 'A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists', ACTA DERM-VENEREOL, vol. 101, no. 8, pp. adv00532. https://doi.org/10.2340/00015555-3893

APA

Decroos, F., Springenberg, S., Lang, T., Päpper, M., Zapf, A., Metze, D., Steinkraus, V., & Böer-Auer, A. (2021). A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists. ACTA DERM-VENEREOL, 101(8), adv00532. https://doi.org/10.2340/00015555-3893

Vancouver

Decroos F, Springenberg S, Lang T, Päpper M, Zapf A, Metze D et al. A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists. ACTA DERM-VENEREOL. 2021 Aug 31;101(8):adv00532. https://doi.org/10.2340/00015555-3893

Bibtex

@article{644cc72d5dbd4b8b836891f3549fa877,
title = "A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists",
abstract = "Onychomycosis is common. Diagnosis can be confirmed by various methods; a commonly used method is the histological examination of nail clippings. A deep learning system was developed and its diagnostic accuracy compared with that of human experts. A dataset with annotations for fungal elements was used to train an artificial intelligence (AI) model. In a second dataset (n=199) the diagnostic accuracy of the AI was compared with that of dermatopathologists. The results show a non-inferiority of the deep learning system to that of analogue diagnosis (non-inferiority margin 5%) with respect to specificity and the area under the receiver operating characteristic curve (AUC). The AI achieved an AUC of 0.981. One limitation of this system is the need for a large number of training images. The AI had difficulty recognizing spores and confused serum or aggregated bacteria with fungal elements. Use of this deep learning system in dermatopathology routine might help to diagnose onychomycosis more efficiently.",
author = "Florence Decroos and Sebastian Springenberg and Tobias Lang and Marc P{\"a}pper and Antonia Zapf and Dieter Metze and Volker Steinkraus and Almut B{\"o}er-Auer",
year = "2021",
month = aug,
day = "31",
doi = "10.2340/00015555-3893",
language = "English",
volume = "101",
pages = "adv00532",
journal = "ACTA DERM-VENEREOL",
issn = "0001-5555",
publisher = "Society for the Publication of Acta Dermato-Venereologica",
number = "8",

}

RIS

TY - JOUR

T1 - A Deep Learning Approach for Histopathological Diagnosis of Onychomycosis: Not Inferior to Analogue Diagnosis by Histopathologists

AU - Decroos, Florence

AU - Springenberg, Sebastian

AU - Lang, Tobias

AU - Päpper, Marc

AU - Zapf, Antonia

AU - Metze, Dieter

AU - Steinkraus, Volker

AU - Böer-Auer, Almut

PY - 2021/8/31

Y1 - 2021/8/31

N2 - Onychomycosis is common. Diagnosis can be confirmed by various methods; a commonly used method is the histological examination of nail clippings. A deep learning system was developed and its diagnostic accuracy compared with that of human experts. A dataset with annotations for fungal elements was used to train an artificial intelligence (AI) model. In a second dataset (n=199) the diagnostic accuracy of the AI was compared with that of dermatopathologists. The results show a non-inferiority of the deep learning system to that of analogue diagnosis (non-inferiority margin 5%) with respect to specificity and the area under the receiver operating characteristic curve (AUC). The AI achieved an AUC of 0.981. One limitation of this system is the need for a large number of training images. The AI had difficulty recognizing spores and confused serum or aggregated bacteria with fungal elements. Use of this deep learning system in dermatopathology routine might help to diagnose onychomycosis more efficiently.

AB - Onychomycosis is common. Diagnosis can be confirmed by various methods; a commonly used method is the histological examination of nail clippings. A deep learning system was developed and its diagnostic accuracy compared with that of human experts. A dataset with annotations for fungal elements was used to train an artificial intelligence (AI) model. In a second dataset (n=199) the diagnostic accuracy of the AI was compared with that of dermatopathologists. The results show a non-inferiority of the deep learning system to that of analogue diagnosis (non-inferiority margin 5%) with respect to specificity and the area under the receiver operating characteristic curve (AUC). The AI achieved an AUC of 0.981. One limitation of this system is the need for a large number of training images. The AI had difficulty recognizing spores and confused serum or aggregated bacteria with fungal elements. Use of this deep learning system in dermatopathology routine might help to diagnose onychomycosis more efficiently.

U2 - 10.2340/00015555-3893

DO - 10.2340/00015555-3893

M3 - SCORING: Journal article

C2 - 34405243

VL - 101

SP - adv00532

JO - ACTA DERM-VENEREOL

JF - ACTA DERM-VENEREOL

SN - 0001-5555

IS - 8

ER -