Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases. / Thomsen, Kenneth; Christensen, Anja Liljedahl; Iversen, Lars; Lomholt, Hans Bredsted; Winther, Ole.
In: Frontiers in Medicine, Vol. 7, 574329, 2020.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep Learning for Diagnostic Binary Classification of Multiple-Lesion Skin Diseases
AU - Thomsen, Kenneth
AU - Christensen, Anja Liljedahl
AU - Iversen, Lars
AU - Lomholt, Hans Bredsted
AU - Winther, Ole
PY - 2020
Y1 - 2020
N2 - Background:Diagnosis of skin diseases is often challenging and computer-aided diagnostic tools are urgently needed to underpin decision making. Objective:To develop a convolutional neural network model to classify clinically relevant selected multiple-lesion skin diseases, this in accordance to the STARD guidelines. Methods:This was an image-based retrospective study using multi-task learning for binary classification. A VGG-16 model was trained on 16,543 non-standardized images. Image data was distributed in training set (80%), validation set (10%), and test set (10%). All images were collected from a clinical database of a Danish population attending one dermatological department. Included was patients categorized with ICD-10 codes related to acne, rosacea, psoriasis, eczema, and cutaneous t-cell lymphoma. Results:Acne was distinguished from rosacea with a sensitivity of 85.42% CI 72.24-93.93% and a specificity of 89.53% CI 83.97-93.68%, cutaneous t-cell lymphoma was distinguished from eczema with a sensitivity of 74.29% CI 67.82-80.05% and a specificity of 84.09% CI 80.83-86.99%, and psoriasis from eczema with a sensitivity of 81.79% CI 78.51-84.76% and a specificity of 73.57% CI 69.76-77.13%. All results were based on the test set. Conclusion:The performance rates reported were equal or superior to those reported for general practitioners with dermatological training, indicating that computer-aided diagnostic models based on convolutional neural network may potentially be employed for diagnosing multiple-lesion skin diseases.
AB - Background:Diagnosis of skin diseases is often challenging and computer-aided diagnostic tools are urgently needed to underpin decision making. Objective:To develop a convolutional neural network model to classify clinically relevant selected multiple-lesion skin diseases, this in accordance to the STARD guidelines. Methods:This was an image-based retrospective study using multi-task learning for binary classification. A VGG-16 model was trained on 16,543 non-standardized images. Image data was distributed in training set (80%), validation set (10%), and test set (10%). All images were collected from a clinical database of a Danish population attending one dermatological department. Included was patients categorized with ICD-10 codes related to acne, rosacea, psoriasis, eczema, and cutaneous t-cell lymphoma. Results:Acne was distinguished from rosacea with a sensitivity of 85.42% CI 72.24-93.93% and a specificity of 89.53% CI 83.97-93.68%, cutaneous t-cell lymphoma was distinguished from eczema with a sensitivity of 74.29% CI 67.82-80.05% and a specificity of 84.09% CI 80.83-86.99%, and psoriasis from eczema with a sensitivity of 81.79% CI 78.51-84.76% and a specificity of 73.57% CI 69.76-77.13%. All results were based on the test set. Conclusion:The performance rates reported were equal or superior to those reported for general practitioners with dermatological training, indicating that computer-aided diagnostic models based on convolutional neural network may potentially be employed for diagnosing multiple-lesion skin diseases.
KW - deep neural network (DNN)
KW - dermatology
KW - skin disease
KW - acne
KW - rosacea
KW - psoriasis
KW - cutaneous T cell lymphoma (CTCL)
KW - ezcema
KW - DERMATOLOGISTS
KW - PREVALENCE
KW - MEDICINE
KW - CANCER
KW - CARE
U2 - 10.3389/fmed.2020.574329
DO - 10.3389/fmed.2020.574329
M3 - Journal article
C2 - 33072786
VL - 7
JO - Frontiers in Medicine
JF - Frontiers in Medicine
SN - 2296-858X
M1 - 574329
ER -
ID: 250206422