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

• Type: Article in International Scientific Journal
• Date: 2021

Authors

Catarina Andrade (Author) Other; Luís F. Teixeira (Author) FEUP; Maria João M. Vasconcelos (Author) Other; Luís Rosado (Author) Other

Journal

Title: Journal of Imaging

Vol. 20

Pages: 1-2

Publisher: MDPI

Indexing

ISI Web of Knowledge - 9 Citations

Other information

Authenticus ID: P-00T-6YW

DOI: 10.3390/jimaging7010002

Abstract (EN): 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 Frechet 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.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 15