A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task

Collaborators

doi:10.1016/j.ejca.2019.02.005

A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task

Standard

A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. / Collaborators.

in: EUR J CANCER, Jahrgang 111, 04.2019, S. 148-154.

Publikationen: SCORING: Beitrag in Fachzeitschrift/Zeitung › SCORING: Zeitschriftenaufsatz › Forschung › Begutachtung

Harvard

Collaborators 2019, 'A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task', EUR J CANCER, Jg. 111, S. 148-154. https://doi.org/10.1016/j.ejca.2019.02.005

APA

Collaborators (2019). A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. EUR J CANCER, 111, 148-154. https://doi.org/10.1016/j.ejca.2019.02.005

Vancouver

Collaborators. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task. EUR J CANCER. 2019 Apr;111:148-154. https://doi.org/10.1016/j.ejca.2019.02.005

Bibtex

@article{aa3e80f0eea54ea2a9c2c1035cad9422,

title = "A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task",

abstract = "BACKGROUND: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.METHODS: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics.FINDINGS: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%.INTERPRETATION: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks.",

author = "Brinker, {Titus J} and Achim Hekler and Enk, {Alexander H} and Joachim Klode and Axel Hauschild and Carola Berking and Bastian Schilling and Sebastian Haferkamp and Dirk Schadendorf and Stefan Fr{\"o}hling and Utikal, {Jochen S} and {von Kalle}, Christof and Collaborators",

year = "2019",

month = apr,

doi = "10.1016/j.ejca.2019.02.005",

language = "English",

volume = "111",

pages = "148--154",

journal = "EUR J CANCER",

issn = "0959-8049",

publisher = "Elsevier Limited",

}

RIS

TY - JOUR

T1 - A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task

AU - Brinker, Titus J

AU - Hekler, Achim

AU - Enk, Alexander H

AU - Klode, Joachim

AU - Hauschild, Axel

AU - Berking, Carola

AU - Schilling, Bastian

AU - Haferkamp, Sebastian

AU - Schadendorf, Dirk

AU - Fröhling, Stefan

AU - Utikal, Jochen S

AU - von Kalle, Christof

AU - Collaborators

PY - 2019/4

Y1 - 2019/4

N2 - BACKGROUND: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.METHODS: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics.FINDINGS: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%.INTERPRETATION: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks.

AB - BACKGROUND: Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists.METHODS: We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics.FINDINGS: The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4% (range: 55.0%-100%) and 64.4% (range: 22.5%-92.5%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2% (range 47.5%-86.25%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8% at a mean specificity of 57.7%. With the same high sensitivity of 92.8%, the CNN had a mean specificity of 61.1%.INTERPRETATION: For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks.

U2 - 10.1016/j.ejca.2019.02.005

DO - 10.1016/j.ejca.2019.02.005

M3 - SCORING: Journal article

C2 - 30852421

VL - 111

SP - 148

EP - 154

JO - EUR J CANCER

JF - EUR J CANCER

SN - 0959-8049

ER -