Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists.

• Deep learning convolutional neural networks (CNN) may facilitate melanoma detection, but data comparing a CNN's diagnostic performance to larger groups of dermatologists are lacking.Google's Inception v4 CNN architecture was trained and validated using dermoscopic images and corresponding diagnoses. In a comparative cross-sectional reader study a 100-image test-set was used (level-I: dermoscopy only; level-II: dermoscopy plus clinical information and images). Main outcome measures were sensitivity, specificity and area under the curve (AUC) of receiver operating characteristics (ROC) for diagnostic classification (dichotomous) of lesions by the CNN versus an international group of 58 dermatologists during level-I or -II of the reader study. Secondary end points included the dermatologists' diagnostic performance in their management decisions and differences in the diagnostic performance of dermatologists during level-I and -II of the reader study. Additionally, the CNN's performance was compared with the top-five algorithms of the 2016 International Symposium on Biomedical Imaging (ISBI) challenge.In level-I dermatologists achieved a mean (±standard deviation) sensitivity and specificity for lesion classification of 86.6% (±9.3%) and 71.3% (±11.2%), respectively. More clinical information (level-II) improved the sensitivity to 88.9% (±9.6%, P=0.19) and specificity to 75.7% (±11.7%, P<0.05). The CNN ROC curve revealed a higher specificity of 82.5% when compared with dermatologists in level-I (71.3%, P<0.01) and level-II (75.7%, P<0.01) at their sensitivities of 86.6% and 88.9%, respectively. The CNN ROC AUC was greater than the mean ROC area of dermatologists (0.86 versus 0.79, P<0.01). The CNN scored results close to the top three algorithms of the ISBI 2016 challenge.For the first time we compared a CNN's diagnostic performance with a large international group of 58 dermatologists, including 30 experts. Most dermatologists were outperformed by the CNN. Irrespective of any physicians' experience, they may benefit from assistance by a CNN's image classification.This study was registered at the German Clinical Trial Register (DRKS-Study-ID: DRKS00013570; https://www.drks.de/drks_web/).

Subject headings

MEDICIN OCH HÄLSOVETENSKAP  -- Klinisk medicin -- Dermatologi och venereologi (hsv//swe)

MEDICAL AND HEALTH SCIENCES  -- Clinical Medicine -- Dermatology and Venereal Diseases (hsv//eng)

MEDICIN OCH HÄLSOVETENSKAP  -- Klinisk medicin -- Radiologi och bildbehandling (hsv//swe)

MEDICAL AND HEALTH SCIENCES  -- Clinical Medicine -- Radiology, Nuclear Medicine and Medical Imaging (hsv//eng)

MEDICIN OCH HÄLSOVETENSKAP  -- Klinisk medicin -- Cancer och onkologi (hsv//swe)

MEDICAL AND HEALTH SCIENCES  -- Clinical Medicine -- Cancer and Oncology (hsv//eng)

Keyword

Clinical Competence

Cross-Sectional Studies

Deep Learning

Dermatologists

statistics & numerical data

Dermoscopy

Humans

Image Processing

Computer-Assisted

methods

statistics & numerical data

International Cooperation

Melanoma

diagnostic imaging

ROC Curve

Retrospective Studies

Skin

diagnostic imaging

Skin Neoplasms

diagnostic imaging

melanoma

melanocytic nevi

dermoscopy

deep learning convolutional neural network

computer algorithm

automated melonoma detection

Publication and Content Type

ref (subject category)

art (subject category)