Using artificial intelligence on skin photos to study melanoma and immunotherapy response

Trial details

Who runs it

Nantes University Hospital

Trial code

NCT05856565

Record updated

15 April 2026

Original description

In the last decade, the advent of immunotherapies with inhibitors of immune checkpoints, such as anti-PD-1 and anti-CTLA-4, has revolutionized the treatment of advanced or metastatic melanoma. However, the clinical benefit remains limited to a subset of patients. Identifying the patients most likely to benefit from these novel therapies (and avoiding unnecessary toxicity in non-responding patients) is therefore critical. Previous studies found a significant link between the high mutational load of a tumor (TMB) and its response to anti-PD-1 monotherapy, regardless of the histological type of cancer. Unfortunately, TMB measurement is expensive, and requires extensive sequencing approaches difficult to implement in clinical practice. I have shown that melanomas known to be secondary to mutagenic ultraviolet rays (UVR) often carry a high TMB. The cumulative UVR damage translates into visible stigmas termed "dermatoheliosis" on patients' skin, easy to recognize with the naked eye of the clinician around the scar of the primary melanoma. My project proposes to establish, for the first time, dermatoheliosis as a novel predictive factor of response to anti-PD-1 immunotherapy, to be used within multidisciplinary tumor boards as a powerful decision-support tool to select the best treatment option. Specifically, I will 1) develop, validate and test in a prospective manner, an artificial intelligence (AI)-based algorithm, to assess features of pericicatricial dermatoheliosis based on a collection of photographs obtained from patients with unresectable locally advanced or metastatic melanoma 2) demonstrate the link between dermatoheliosis, TMB, immune and treatment response by characterizing pericicatricial skin single cell transcriptomics, as well as tumor DNA, RNA and host immunological profiles of the patients. This directly accessible, non-invasive, surrogate marker for TMB will be a game changer in clinical practice and will subsequently be translated to other skin cancers.Read full original descriptionShow less

Generation of an Artificial Intelligence Algorithm Based on the Analysis of Melanoma Peri-scar Dermatoheliosis, as a Predictive Factor of Response to Anti-PD-1

In the last decade, the advent of immunotherapies with inhibitors of immune checkpoints, such as anti-PD-1 and anti-CTLA-4, has revolutionized the treatment of advanced or metastatic melanoma. However, the clinical benefit remains limited to a subset of patients. Identifying the patients most likely to benefit from these novel therapies (and avoiding unnecessary toxicity in non-responding patients) is therefore critical. Previous studies found a significant link between the high mutational load of a tumor (TMB) and its response to anti-PD-1 monotherapy, regardless of the histological type of cancer. Unfortunately, TMB measurement is expensive, and requires extensive sequencing approaches difficult to implement in clinical practice. I have shown that melanomas known to be secondary to mutagenic ultraviolet rays (UVR) often carry a high TMB. The cumulative UVR damage translates into visible stigmas termed "dermatoheliosis" on patients' skin, easy to recognize with the naked eye of the clinician around the scar of the primary melanoma. My project proposes to establish, for the first time, dermatoheliosis as a novel predictive factor of response to anti-PD-1 immunotherapy, to be used within multidisciplinary tumor boards as a powerful decision-support tool to select the best treatment option. Specifically, I will 1) develop, validate and test in a prospective manner, an artificial intelligence (AI)-based algorithm, to assess features of pericicatricial dermatoheliosis based on a collection of photographs obtained from patients with unresectable locally advanced or metastatic melanoma 2) demonstrate the link between dermatoheliosis, TMB, immune and treatment response by characterizing pericicatricial skin single cell transcriptomics, as well as tumor DNA, RNA and host immunological profiles of the patients. This directly accessible, non-invasive, surrogate marker for TMB will be a game changer in clinical practice and will subsequently be translated to other skin cancers.

Inclusion: ▪ Adult patients with inoperable stage III or IV melanoma, or inoperable skin carcinoma (squamous cell carcinoma or basal cell carcinoma); Retrospective cohort: patients who have received curative treatment with anti-PD1, +/- anti-CTLA-4 or anti-LAG-3 for their skin cancer for at least 90 days, with at least 6 months of follow-up, without immunosuppression and whose primary tumour site is not altered by concomitant dermatosis. Adjuvant immunotherapy is tolerated if it was stopped at least 6 months before the start of curative treatment. Interferon is also tolerated if it was stopped at least 6 months before the start of curative treatment. Radiotherapy is tolerated if it did not take place at the site of the primary melanoma scar. For squamous cell carcinomas, prior radiotherapy on the scar is acceptable (it must simply not have been administered during the period of anti-PD-1 treatment in order to be able to reliably assess the response); Inoperable primary tumours are eligible. Targeted therapy is accepted before the start of curative treatment with immunotherapy; Chemotherapy is not accepted prior to the initiation of curative treatment with immunotherapy; ▪ Prospective cohort: Patients who have not received immunotherapy for the management of their skin cancer at the start of curative treatment with anti-PD-1, +/- anti-CTLA-4 or anti-LAG-3; Adjuvant immunotherapy is tolerated if it has been discontinued for at least 6 months prior to the start of curative treatment. Interferon is also tolerated if it has been discontinued for at least 6 months prior to the start of curative treatment. Radiotherapy is tolerated if it has not been administered at the site of the primary cancer scar; Targeted therapy is accepted before starting curative treatment with anti-PD-1, +/- anti-CTLA-4 or anti-LAG-3; Chemotherapy is not accepted before the start of curative treatment with anti-PD-1, +/- anti-CTLA-4 or anti-LAG-3; ▪ Patients who have agreed to participate in the research and have signed an image rights authorisation form.

Exclusion: Retrospective cohort: Patients who have received curative treatment with anti-PD-1, +/- anti-CTLA-4 or anti-LAG-3 for skin cancer for less than 90 days; Patients who received adjuvant immunotherapy within 6 months prior to curative treatment; Patients who received chemotherapy prior to curative treatment; Patients treated with systemic corticosteroids (dose greater than 10 mg/day) at the start of the immunotherapy in question,; Patients whose primary skin cancer site cannot be photographed (e.g. choroidal melanomas, mucosal melanomas, with the exception of vulvar or penile melanomas, etc.); Patients who are immunocompromised (associated blood disorder, human immunodeficiency virus infection, transplant patients, etc.) at the start of immunotherapy,; Patients with iatrogenic peri-scar vitiligo,; Patients who have refused to participate in the research,; Adults protected by law.

ClinicalTrials.gov NCT05856565