Classification of the Clinical Images for Benign and Malignant Cutaneous Tumors Using a Deep Learning Algorithm

We tested the use of a deep learning algorithm to classify the clinical images of 12 skin diseases-basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, actinic keratosis, seborrheic keratosis, malignant melanoma, melanocytic nevus, lentigo, pyogenic granuloma, hemangioma, dermat...

Full description

Saved in:
Bibliographic Details
Published in:Journal of investigative dermatology Vol. 138; no. 7; p. 1529
Main Authors: Han, Seung Seog, Kim, Myoung Shin, Lim, Woohyung, Park, Gyeong Hun, Park, Ilwoo, Chang, Sung Eun
Format: Journal Article
Language:English
Published: United States 01.07.2018
Subjects:
Adult
Aged
Aged, 80 and over
Area Under Curve
Biopsy
Datasets as Topic
Deep Learning
Diagnosis, Differential
False Positive Reactions
Female
Granuloma, Pyogenic - diagnostic imaging
Granuloma, Pyogenic - pathology
Humans
Image Processing, Computer-Assisted - methods
Keratosis, Actinic - diagnostic imaging
Keratosis, Actinic - pathology
Keratosis, Seborrheic - diagnostic imaging
Keratosis, Seborrheic - pathology
Lentigo - diagnostic imaging
Lentigo - pathology
Male
Middle Aged
Photography
Predictive Value of Tests
ROC Curve
Skin - diagnostic imaging
Skin - pathology
Skin Neoplasms - diagnostic imaging
Skin Neoplasms - pathology
Software
Warts - diagnostic imaging
Warts - pathology
Young Adult
ISSN:1523-1747, 1523-1747
Online Access:Get more information
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We tested the use of a deep learning algorithm to classify the clinical images of 12 skin diseases-basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, actinic keratosis, seborrheic keratosis, malignant melanoma, melanocytic nevus, lentigo, pyogenic granuloma, hemangioma, dermatofibroma, and wart. The convolutional neural network (Microsoft ResNet-152 model; Microsoft Research Asia, Beijing, China) was fine-tuned with images from the training portion of the Asan dataset, MED-NODE dataset, and atlas site images (19,398 images in total). The trained model was validated with the testing portion of the Asan, Hallym and Edinburgh datasets. With the Asan dataset, the area under the curve for the diagnosis of basal cell carcinoma, squamous cell carcinoma, intraepithelial carcinoma, and melanoma was 0.96 ± 0.01, 0.83 ± 0.01, 0.82 ± 0.02, and 0.96 ± 0.00, respectively. With the Edinburgh dataset, the area under the curve for the corresponding diseases was 0.90 ± 0.01, 0.91 ± 0.01, 0.83 ± 0.01, and 0.88 ± 0.01, respectively. With the Hallym dataset, the sensitivity for basal cell carcinoma diagnosis was 87.1% ± 6.0%. The tested algorithm performance with 480 Asan and Edinburgh images was comparable to that of 16 dermatologists. To improve the performance of convolutional neural network, additional images with a broader range of ages and ethnicities should be collected.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ObjectType-Undefined-3
ISSN:1523-1747
1523-1747
DOI:10.1016/j.jid.2018.01.028