Elsevier

European Journal of Cancer

Volume 119, September 2019, Pages 11-17
European Journal of Cancer

Original Research
Deep neural networks are superior to dermatologists in melanoma image classification

https://doi.org/10.1016/j.ejca.2019.05.023Get rights and content
Under a Creative Commons license
open access

Highlights

  • Recent publications demonstrated that deep learning is capable to classify images of benign nevi and melanoma with dermatologist-level precision.

  • A systematic outperformance of dermatologists was not demonstrated to date.

  • This study shows the first systematic (p < 0.001) outperformance of board-certified dermatologists in dermoscopic melanoma image classification.

Abstract

Background

Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date.

Methods

For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes.

Findings

The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2% (95% confidence interval [CI]: 62.6%–71.7%) and 62.2% (95% CI: 57.6%–66.9%). In comparison, the trained CNN achieved a higher sensitivity of 82.3% (95% CI: 78.3%–85.7%) and a higher specificity of 77.9% (95% CI: 73.8%–81.8%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups.

Interpretation

For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001).

Keywords

Deep learning
Melanoma
Skin cancer
Artificial intelligence

Cited by (0)

1

These authors contributed equally to this work.