Next Article in Journal
Image Aesthetic Assessment Based on Image Classification and Region Segmentation
Next Article in Special Issue
Bayesian Learning of Shifted-Scaled Dirichlet Mixture Models and Its Application to Early COVID-19 Detection in Chest X-ray Images
Previous Article in Journal
Comparison of Thermal Neutron and Hard X-ray Dark-Field Tomography
Previous Article in Special Issue
A Survey of Deep Learning for Lung Disease Detection on Medical Images: State-of-the-Art, Taxonomy, Issues and Future Directions
Article

Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images

1
Fraunhofer Portugal AICOS, Rua Alfredo Allen, 4200-135 Porto, Portugal
2
Faculty of Engineering, University of Porto, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
3
INESC TEC, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
*
Author to whom correspondence should be addressed.
Received: 9 November 2020 / Revised: 4 December 2020 / Accepted: 16 December 2020 / Published: 24 December 2020
(This article belongs to the Special Issue Deep Learning in Medical Image Analysis)
Dermoscopic images allow the detailed examination of subsurface characteristics of the skin, which led to creating several substantial databases of diverse skin lesions. However, the dermoscope is not an easily accessible tool in some regions. A less expensive alternative could be acquiring medium resolution clinical macroscopic images of skin lesions. However, the limited volume of macroscopic images available, especially mobile-acquired, hinders developing a clinical mobile-based deep learning approach. In this work, we present a technique to efficiently utilize the sizable number of dermoscopic images to improve the segmentation capacity of macroscopic skin lesion images. A Cycle-Consistent Adversarial Network is used to translate the image between the two distinct domains created by the different image acquisition devices. A visual inspection was performed on several databases for qualitative evaluation of the results, based on the disappearance and appearance of intrinsic dermoscopic and macroscopic features. Moreover, the Fréchet Inception Distance was used as a quantitative metric. The quantitative segmentation results are demonstrated on the available macroscopic segmentation databases, SMARTSKINS and Dermofit Image Library, yielding test set thresholded Jaccard Index of 85.13% and 74.30%. These results establish a new state-of-the-art performance in the SMARTSKINS database. View Full-Text
Keywords: convolutional neural network; CycleGAN; data augmentation; dermoscopic images; domain transfer; macroscopic images; skin lesion segmentation convolutional neural network; CycleGAN; data augmentation; dermoscopic images; domain transfer; macroscopic images; skin lesion segmentation
Show Figures

Figure 1

MDPI and ACS Style

Andrade, C.; Teixeira, L.F.; Vasconcelos, M.J.M.; Rosado, L. Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images. J. Imaging 2021, 7, 2. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7010002

AMA Style

Andrade C, Teixeira LF, Vasconcelos MJM, Rosado L. Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images. Journal of Imaging. 2021; 7(1):2. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7010002

Chicago/Turabian Style

Andrade, Catarina; Teixeira, Luís F.; Vasconcelos, Maria J.M.; Rosado, Luís. 2021. "Data Augmentation Using Adversarial Image-to-Image Translation for the Segmentation of Mobile-Acquired Dermatological Images" J. Imaging 7, no. 1: 2. https://0-doi-org.brum.beds.ac.uk/10.3390/jimaging7010002

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop