Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network

PLoS ONE

Volumn 13, Issue 1, 2018, Pages

  Han, Seung Seog ^a   Park, Gyeong Hun ^b   Lim, Woohyung ^c   Kim, Myoung Shin ^d   Na, Jung Im ^e   Park, Ilwoo ^f   Chang, Sung Eun ^g  

^a I Dermatology Clinic   (South Korea)

^b Hallym University   (South Korea)

^c SK Telecom   (South Korea)

^d Inje University College of Medicine   (South Korea)

^e Seoul National University   (South Korea)

^f Chonnam National University   (South Korea)

^g University of Ulsan College of Medicine   (South Korea)

Author keywords

[No Author keywords available]

Indexed keywords

ADULT; AREA UNDER THE CURVE; ARTICLE; ARTIFICIAL INTELLIGENCE; CONTROLLED STUDY; DERMATOLOGIST; DIAGNOSTIC ACCURACY; FEMALE; FUNGUS CULTURE; HUMAN; INGROWN NAIL; MAJOR CLINICAL STUDY; MALE; NAIL DYSTROPHY; NERVE CELL NETWORK; ONYCHOLYSIS; ONYCHOMYCOSIS; PARONYCHIA; REGION-BASED CONVOLUTIONAL NEURAL NETWORK; SENSITIVITY AND SPECIFICITY; SUBUNGUAL FIBROMA; SUBUNGUAL HEMORRHAGE; TRAINING; AGED; ALGORITHM; ARTIFICIAL NEURAL NETWORK; COMPUTER ASSISTED DIAGNOSIS; FACTUAL DATABASE; HAND DISEASE; MACHINE LEARNING; MIDDLE AGED; PATHOLOGY; SKIN DISEASE; YOUNG ADULT;

ADULT; AGED; ALGORITHMS; AREA UNDER CURVE; ARTIFICIAL INTELLIGENCE; DATABASES, FACTUAL; DERMATOLOGISTS; DIAGNOSIS, COMPUTER-ASSISTED; FEMALE; FOOT DERMATOSES; HAND DERMATOSES; HUMANS; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MACHINE LEARNING; MALE; MIDDLE AGED; NEURAL NETWORKS (COMPUTER); ONYCHOMYCOSIS; YOUNG ADULT;

EID: 85040794196     PISSN: None     EISSN: 19326203     Source Type: Journal    
DOI: 10.1371/journal.pone.0191493     Document Type: Article

References (20)

1. Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. Jama. 2016. https://doi.org/10.1001/jama.2016.17216 PMID: 27898976.
2. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017; 542(7639):115–8. https://doi.org/10.1038/ nature21056 PMID: 28117445.
3. Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. International Conference on Learning Representations. 2015.
4. He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. arXiv:151203385. 2015.
5. He K, Zhang X, Ren S, Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. arXiv:150201852. 2015.
6. Canziani A, Paszke A, Culurciello E. An analysis of deep neural network models for practical applications. arXiv preprint arXiv:160507678. 2016.
7. Girshick R, Donahue J, Darrell T, Malik J, editors. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition; 2014.
8. Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv:150601497. 2015.
9. Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, et al. Caffe: Convolutional Architecture for Fast Feature Embedding. arXiv:14085093. 2014.
10. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet Large Scale Visual Recognition Challenge. arXiv:14090575. 2014.
11. Binder M, Steiner A, Schwarz M, Knollmayer S, Wolff K, Pehamberger H. Application of an artificial neural network in epiluminescence microscopy pattern analysis of pigmented skin lesions: a pilot study. The British journal of dermatology. 1994; 130(4):460–5. PMID: 8186110.
12. Liao H. A deep learning approach to universal skin disease classification. University of Rochester Department of Computer Science, CSC. 2016.
13. Codella N, Nguyen Q-B, Pankanti S, Gutman D, Helba B, Halpern A, et al. Deep Learning Ensembles for Melanoma Recognition in Dermoscopy Images. IBM Journal of Research and Development. 2017; 61(arXiv:1610.04662).
14. Velasquez-Agudelo V, Cardona-Arias JA. Meta-analysis of the utility of culture, biopsy, and direct KOH examination for the diagnosis of onychomycosis. BMC infectious diseases. 2017; 17(1):166. https://doi.org/10.1186/s12879-017-2258-3 PMID: 28222676.
15. Zanardi D, Nunes DH, Pacheco AdS, Tubone MQ, Souza Filho JJd. Avaliação dos métodos diagnósti-cos para onicomicose. An bras dermatol. 2008; 83(2):119–24.
16. Karimzadegan-Nia M, Mir-Amin-Mohammadi A, Bouzari N, Firooz A. Comparison of direct smear, culture and histology for the diagnosis of onychomycosis. Australasian journal of dermatology. 2007; 48 (1):18–21. https://doi.org/10.1111/j.1440-0960.2007.00320.x PMID: 17222296
17. Jeelani S, Ahmed QM, Lanker AM, Hassan I, Jeelani N, Fazili T. Histopathological examination of nail clippings using PAS staining (HPE-PAS): gold standard in diagnosis of Onychomycosis. Mycoses. 2015; 58(1):27–32. https://doi.org/10.1111/myc.12251 PMID: 25346218
18. Lawry MA, Haneke E, Strobeck K, Martin S, Zimmer B, Romano PS. Methods for diagnosing onychomycosis: a comparative study and review of the literature. Archives of dermatology. 2000; 136(9):1112–6. PMID: 10987866.
19. Borkowski P, Williams M, Holewinski J, Bakotic B. Onychomycosis: an analysis of 50 cases and a comparison of diagnostic techniques. Journal of the American Podiatric Medical Association. 2001; 91 (7):351–5. PMID: 11466460
20. He K, Zhang X, Ren S, Sun J, editors. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.