Augmented Intelligence in EB: Using deep learning for early detection of squamous cell carcinoma in EB

Project: Research project

Project Details


Abstract of Research Squamous cell carcinoma (SCC) is the most common cause of death in adults with recessive dystrophic EB. However, even for experts, distinguishing SCCs from “normal” EB wounds is difficult. Biopsy is critical for diagnosing malignancy, but choosing the right locations for biopsy is equally challenging. EB patients also tend to avoid biopsies, including postponing a clinica visit when cancer-suspicious lesions occur. Recently, the high potential of deep learning in recognizing melanoma and non-melanoma skin cancer has been demonstrated, with a detection rate comparable to expert dermatologists. Well-trained artificial intelligence could provide a low-threshold tool for early detection of RDEB-SCCs, possibly finding patterns in large datasets that are invisible to the individual physician. With the long-term goal of creating an app for photography and interpretation of EB skin to be used by both physicians and patients, we strive to improve clinical management and potentially prolong lives.
Effective start/end date12/1/2111/30/22


  • EB Research Partnership Inc. (Agmt 1/12/22)


Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.