The COVID-19 pandemic accelerated the adoption of digital technologies in many areas of medicine.
It includes art therapy [1], ushering in an era where AI [2] and virtual reality [3] could play significant roles despite existing biases against machine-generated visualization and art [4].
Melanoma accounts for the most deaths from any skin cancer [5] and develops from the pigment-producing cells known as melanocytes [6]. The incidence has been increasing over the past 30 years [7]. While suffering from physical pain, patients are also vulnerable to mental illnesses, as about 30% of all patients diagnosed with melanoma report psychological issues [8]. Follow-up research indicates that mental health problems can reduce the effectiveness of cancer medication [9,10]. Therefore, it is essential to care for the mental health of the patient during treatment. Even after successful treatment, melanoma survivors face psychological problems, as they may feel anxious or depressed due to fear of living with the disease or cancer recurrence [11]. In conclusion, adequate psychological help, such as art therapy, among others, is necessary to achieve better coping with the illness. Art therapy has already proven effective in various medical treatment approaches and shown to improve the patient’s expression, self-consciousness and resilience to pressure [12,13,14]. Visual art appreciation of famous paintings, such as Starry Night or Sunflowers by Vincent Van Gogh, is a common form of art therapy, and cancer patients feel relaxed in their emotional state through visual art appreciation, potentially leading to more in depth and long-standing healing [15,16].
In June 2014, a team led by Goodfellow introduced an advanced deep learning system called the Generative Adversarial Network (GAN) [17]. After that, other experts began creating different versions of GANs to solve a variety of challenges in many areas. For example, Zhu et al. proposed the CycleGAN model utilizing cycle consistency loss to constrain training and achieve cross-domain image transformation with unpaired datasets [18]. In this work, we propose the transformation of melanoma images into art paintings based on a CycleGAN variant. CycleGANs have been broadly applied in various scientific fields, including liver medical image generation [19], synthetic CT generation from MRI [20], road dataset generation for urban mobility [21], virtual immunohistochemical staining image generation [22], and CT synthesis from MRI for head-and-neck radiation therapy [23]. We aim to provide a tool based on generative artificial intelligence to be used in art therapy with melanoma patients. The tool can convert medical images of melanoma into artworks based on certain themes. In this work, a flower theme was used to show the concept. GANs are ideal for this concept since, following the initial network training, image production is safe, as the potential for glitches, such as the generation of unappealing images, is minimized. Digital art therapy has been shown to be effective in improving mental health and well-being by providing a dynamic and contemporary approach to therapeutic intervention. For instance, digital tools enable therapists to share and create images easily, which can be particularly beneficial in distance therapy or hybrid formats that combine in-person and online sessions [24]. Moreover, digital art therapy can address various therapeutic goals, such as emotional expression, stress reduction, and cognitive engagement. The incorporation of digital media allows for a broader range of expressive possibilities, helping clients to explore and process their emotions in innovative ways [24]. The survey conducted in this work, administered to a broad spectrum of art therapists, was designed to gather insights on the integration of AI-generated art, particularly derived from medical images, into therapeutic practice. It encapsulated themes ranging from ethical considerations, therapeutic applications, and challenges to the adaptability of this approach for patients across various medical conditions, offering a panoramic view of prevailing thoughts in the art therapy community.
References
Miller, G.; McDonald, A. Online art therapy during the COVID-19 pandemic. Int. J. Art Ther. 2020, 25, 159–160. [Google Scholar] [CrossRef]
Gao, T.; Zhang, D.; Hua, G.; Qiao, Y.; Zhou, H. Artificial Intelligence Painting Interactive Experience Discovers Possibilities for Emotional Healing in the Post-pandemic Era. In HCI International 2023 Posters; Stephanidis, C., Antona, M., Ntoa, S., Salvendy, G., Eds.; Springer Nature: Cham, Switzerland, 2023; pp. 415–425. ISBN 978-3-031-35997-2 . [Google Scholar]
Hadjipanayi, C.; Banakou, D.; Michael-Grigoriou, D. Art as therapy in virtual reality: A scoping review. Front. Virtual Real. 2023, 4, 1065863. [Google Scholar] [CrossRef]
Ragot, M.; Martin, N.; Cojean, S. AI-generated vs. Human Artworks. A Perception Bias Towards Artificial Intelligence? In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems, Proceedings of the CHI‘20: CHI Conference on Human Factors in Computing Systems, Honolulu, HI, USA, 25–30 April 2020; Bernhaupt, R., Mueller, F., Verweij, D., Andres, J., McGrenere, J., Cockburn, A., Avellino, I., Goguey, A., Bjørn, P., Zhao, S., et al., Eds.; ACM: New York, NY, USA, 2020; pp. 1–10. ISBN 9781450368193 . [Google Scholar]
Siegel, R.L.; Miller, K.D.; Fuchs, H.E.; Jemal, A. Cancer statistics, 2022. CA Cancer J. Clin. 2022, 72, 7–33. [Google Scholar] [CrossRef] [PubMed]
Uong, A.; Zon, L.I. Melanocytes in development and cancer. J. Cell. Physiol. 2010, 222, 38–41. [Google Scholar] [CrossRef]
Guy, G.P.; Thomas, C.C.; Thompson, T.; Watson, M.; Massetti, G.M.; Richardson, L.C. Vital signs: Melanoma incidence and mortality trends and projections—United States, 1982–2030. MMWR Morb. Mortal. Wkly. Rep. 2015, 64, 591–596. [Google Scholar]
Kasparian, N.A. Psychological care for people with melanoma: What, when, why and how? Semin. Oncol. Nurs. 2013, 29, 214–222. [Google Scholar] [CrossRef]
Yang, H.; Xia, L.; Chen, J.; Zhang, S.; Martin, V.; Li, Q.; Lin, S.; Chen, J.; Calmette, J.; Lu, M.; et al. Stress-glucocorticoid-TSC22D3 axis compromises therapy-induced antitumor immunity. Nat. Med. 2019, 25, 1428–1441. [Google Scholar] [CrossRef] [PubMed]
Schoemaker, M.J.; Jones, M.E.; Wright, L.B.; Griffin, J.; McFadden, E.; Ashworth, A.; Swerdlow, A.J. Psychological stress, adverse life events and breast cancer incidence: A cohort investigation in 106,000 women in the United Kingdom. Breast Cancer Res. 2016, 18, 72. [Google Scholar] [CrossRef]
Blum, A.; Blum, D.; Stroebel, W.; Rassner, G.; Garbe, C.; Hautzinger, M. Psychosoziale Belastung und subjektives Erleben von Melanompatienten in der ambulanten Nachsorge. Psychother. Psychosom. Med. Psychol. 2003, 53, 258–266. [Google Scholar] [CrossRef]
Kim, K.S.; Loring, S.; Kwekkeboom, K. Use of Art-Making Intervention for Pain and Quality of Life Among Cancer Patients: A Systematic Review. J. Holist. Nurs. 2018, 36, 341–353. [Google Scholar] [CrossRef]
Tang, Y.; Fu, F.; Gao, H.; Shen, L.; Chi, I.; Bai, Z. Art therapy for anxiety, depression, and fatigue in females with breast cancer: A systematic review. J. Psychosoc. Oncol. 2019, 37, 79–95. [Google Scholar] [CrossRef]
Boehm, K.; Cramer, H.; Staroszynski, T.; Ostermann, T. Arts therapies for anxiety, depression, and quality of life in breast cancer patients: A systematic review and meta-analysis. Evid. Based Complement. Alternat. Med. 2014, 2014, 103297. [Google Scholar] [CrossRef] [PubMed]
Lin, M.-H.; Moh, S.-L.; Kuo, Y.-C.; Wu, P.-Y.; Lin, C.-L.; Tsai, M.-H.; Chen, T.-J.; Hwang, S.-J. Art therapy for terminal cancer patients in a hospice palliative care unit in Taiwan. Palliat. Support. Care 2012, 10, 51–57. [Google Scholar] [CrossRef] [PubMed]
Lee, J.; Choi, M.Y.; Kim, Y.B.; Sun, J.; Park, E.J.; Kim, J.H.; Kang, M.; Koom, W.S. Art therapy based on appreciation of famous paintings and its effect on distress among cancer patients. Qual. Life Res. 2017, 26, 707–715. [Google Scholar] [CrossRef] [PubMed]
Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative adversarial networks. Commun. ACM 2020, 63, 139–144. [Google Scholar] [CrossRef]
Zhu, J.-Y.; Park, T.; Isola, P.; Efros, A.A. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, France, 22–29 October 2017; pp. 2242–2251, ISBN 978-1-5386-1032-9 . [Google Scholar]
Chen, Y.; Lin, H.; Zhang, W.; Chen, W.; Zhou, Z.; Heidari, A.A.; Chen, H.; Xu, G. ICycle-GAN: Improved cycle generative adversarial networks for liver medical image generation. Biomed. Signal Process. Control. 2024, 92, 106100. [Google Scholar] [CrossRef]
Lei, Y.; Harms, J.; Wang, T.; Liu, Y.; Shu, H.-K.; Jani, A.B.; Curran, W.J.; Mao, H.; Liu, T.; Yang, X. MRI-only based synthetic CT generation using dense cycle consistent generative adversarial networks. Med. Phys. 2019, 46, 3565–3581. [Google Scholar] [CrossRef]
Rajagopal, B.G.; Kumar, M.; Alshehri, A.H.; Alanazi, F.; Deifalla, A.F.; Yosri, A.M.; Azam, A. A hybrid Cycle GAN-based lightweight road perception pipeline for road dataset generation for Urban mobility. PLoS ONE 2023, 18, e0293978. [Google Scholar] [CrossRef]
Liu, S.; Li, X.; Zheng, A.; Yang, F.; Liu, Y.; Guan, T.; He, Y. The Generation of Virtual Immunohistochemical Staining Images Based on an Improved Cycle-GAN. In Proceedings of the Machine Learning and Intelligent Communications; Guan, M., Na, Z., Eds.; Springer International Publishing: Cham, Switzerland, 2021; pp. 137–147, ISBN 978-3-030-66784-9 . [Google Scholar]
Liu, Y.; Chen, A.; Shi, H.; Huang, S.; Zheng, W.; Liu, Z.; Zhang, Q.; Yang, X. CT synthesis from MRI using multi-cycle GAN for head-and-neck radiation therapy. Comput. Med. Imaging Graph. 2021, 91, 101953. [Google Scholar] [CrossRef]
Zubala, A.; Kennell, N.; Hackett, S. Art Therapy in the Digital World: An Integrative Review of Current Practice and Future Directions. Front. Psychol. 2021, 12, 595536. [Google Scholar] [CrossRef]