This website requires JavaScript.

Generative Adversarial Network for Personalized Art Therapy in Melanoma Disease Management

Lennart J\"utteNing WandBernhard Roth
Mar 2023
Melanoma is the most lethal type of skin cancer. Patients are vulnerable tomental health illnesses which can reduce the effectiveness of the cancertreatment and the patients adherence to drug plans. It is crucial to preservethe mental health of patients while they are receiving treatment. However,current art therapy approaches are not personal and unique to the patient. Weaim to provide a well-trained image style transfer model that can quicklygenerate unique art from personal dermoscopic melanoma images as an additionaltool for art therapy in disease management of melanoma. Visual art appreciationas a common form of art therapy in disease management that measurably reducesthe degree of psychological distress. We developed a network based on thecycle-consistent generative adversarial network for style transfer thatgenerates personalized and unique artworks from dermoscopic melanoma images. Wedeveloped a model that converts melanoma images into unique flower-themedartworks that relate to the shape of the lesion and are therefore personal tothe patient. Further, we altered the initial framework and made comparisons andevaluations of the results. With this, we increased the options in the toolboxfor art therapy in disease management of melanoma. The development of aneasy-to-use user interface ensures the availability of the approach tostakeholders. The transformation of melanoma into flower-themed artworks isachieved by the proposed model and the graphical user interface. Thiscontribution opens a new field of GANs in art therapy and could lead to morepersonalized disease management.