Facial skin disease prediction using StarGAN v2 and transfer learning

Article type: Research Article

Authors: Holmes, Kristen^{a; *} | Sharma, Poonam^b | Fernandes, Steven^a

Affiliations: [a] Department of Computer Science, Design and Journalism, Creighton University, Omaha, NE, USA | [b] Department of Pathology, Creighton University, Omaha, NE, USA

Correspondence: [*] Corresponding author: Kristen Holmes, Department of Computer Science, Design and Journalism, Creighton University, NE, USA. E-mail: [email protected].

Abstract: Deep learning algorithms have become the most prominent methods for medical image analysis over the past years, leading to enhanced performances in various medical applications. In this paper, we focus on applying intelligent skin disease detection to face images, where the crucial challenge is the low availability of training data. To achieve high disease detection and classification success rates, we adapt the state-of-the-art StarGAN v2 network to augment images of faces and combine it with a transfer learning approach. The experimental results show that the classification accuracies of transfer learning models are in the range of 77.46–99.80% when trained on datasets that are extended with StarGAN v2 augmented data.

DOI: 10.3233/IDT-228046

Journal: Intelligent Decision Technologies, vol. 17, no. 1, pp. 55-66, 2023