Study Status: RECRUITING
Recruit Status: RECRUITING
Study Type: OBSERVATIONAL
Official Title: Developing a Novel Artificial Intelligence Patient App to Recognize Squamous Cell Carcinoma (SCCs) in Recessive Dystrophic Epidermolysis Bullosa (RDEB): Image Collection
Brief Summary:
In this study, an artificial intelligence model to detect squamous cell carcinomas (SCC) on photos of recessive dystrophic epidermolysis bullosa (RDEB) skin is developed.
The ultimate goal is to integrate this model into an app for patients and physicians, to help detect SCCs in RDEB early.
SCCs which rapidly metastasize are the main cause of death in adults with RDEB.
The earlier an SCC is recognized, the easier it can be removed and the better the outcome.
AI leverages computer science to perform tasks that typically require human intelligence and has recently been used to identify skin cancers based on images.
We are currently developing an AI approach for early detection of SCC and distinction of malignancy from chronic wounds and other RDEB skin findings.
The aim is to create a web application for patients with RDEB to upload images of their skin and get an output as to SCC present/ no SCC.
This will be especially valuable for patients with difficult access to medical expertise and those who are hesitant to allow full skin examination at each visit, often because of fear of biopsies.
Thus, this project will directly benefit patients by allowing early recognition of SCCs and will empower patients and their families by providing a home use tool.
So far, the study team has mainly used professional images (photographs taken in hospital settings by physicians, nurses, and clinical photographers) of both SCCs in RDEB and images of RDEB skin without SCC to develop and train the AI model.
The images that are expected in a real-life setting will mostly be pictures taken by patients or family members with their phones or digital cameras.
These images have different properties regarding resolution, focus, lighting, and backgrounds.
Incorporating such images will be crucial in the upcoming phases of model development-testing and validation-for the web application be a success for patients.