Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition.

Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition.

Publication date: Aug 14, 2019

Deep learning convolutional neural networks (CNNs) have shown a performance at the level of dermatologists in the diagnosis of melanoma. Accordingly, further exploring the potential limitations of CNN technology before broadly applying it is of special interest.

To investigate the association between gentian violet surgical skin markings in dermoscopic images and the diagnostic performance of a CNN approved for use as a medical device in the European market.

A cross-sectional analysis was conducted from August 1, 2018, to November 30, 2018, using a CNN architecture trained with more than 120 000 dermoscopic images of skin neoplasms and corresponding diagnoses. The association of gentian violet skin markings in dermoscopic images with the performance of the CNN was investigated in 3 image sets of 130 melanocytic lesions each (107 benign nevi, 23 melanomas).

The same lesions were sequentially imaged with and without the application of a gentian violet surgical skin marker and then evaluated by the CNN for their probability of being a melanoma. In addition, the markings were removed by manually cropping the dermoscopic images to focus on the melanocytic lesion.

Sensitivity, specificity, and area under the curve (AUC) of the receiver operating characteristic (ROC) curve for the CNN’s diagnostic classification in unmarked, marked, and cropped images.

In all, 130 melanocytic lesions (107 benign nevi and 23 melanomas) were imaged. In unmarked lesions, the CNN achieved a sensitivity of 95.7% (95% CI, 79%-99.2%) and a specificity of 84.1% (95% CI, 76.0%-89.8%). The ROC AUC was 0.969. In marked lesions, an increase in melanoma probability scores was observed that resulted in a sensitivity of 100% (95% CI, 85.7%-100%) and a significantly reduced specificity of 45.8% (95% CI, 36.7%-55.2%, P 

Winkler, J.K., Fink, C., Toberer, F., Enk, A., Deinlein, T., Hofmann-Wellenhof, R., Thomas, L., Lallas, A., Blum, A., Stolz, W., and Haenssle, H.A. Association Between Surgical Skin Markings in Dermoscopic Images and Diagnostic Performance of a Deep Learning Convolutional Neural Network for Melanoma Recognition. 23743. 2019 JAMA Dermatol.

Concepts Keywords
AUC CNN probability melanoma
Benign Benign nevi melanomas
CNN Melanoma
Convolutional Neural Networks Medicine
Cross Organ systems
Deep Learning Dermatology
Gentian Violet Nevus
JAMA Neoplasm
Lesion Dermatoscopy
Melanoma Dysplastic nevus
Melanomas Neural Network
Nevi
Probability
Receiver Operating Characteristic
ROC
ROC Curve
Skin Neoplasms

Semantics

Type Source Name
drug DRUGBANK Saquinavir
disease MESH nevi
disease MESH skin neoplasms
disease MESH diagnosis
pathway BSID Melanoma
disease DOID Melanoma
disease MESH Melanoma

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *