A team of dermatologists from Tohoku University in Japan has developed an AI model that helps to detect complications from bacterial or viral infections in patients with atopic dermatitis. Moreover, it helps differentiate between eczema and skin lesions caused by a type of blood cancer.
The research team trained their convolutional neural network (CNN) model using non-standard images of AD, impetigo, mycosis fungoides, herpes simplex, and Kaposi varicelliform eruption. After this, they compared the AI’s diagnosis accuracy to a set of non-standard images manually cropped and diagnostically annotated by dermatologists. The model has achieved a diagnostic accuracy almost equal to the manually assessed image set.
Co-author Yuta Yanagisawa, a researcher with the Tohoku University School of Medicine, comments: “A dermatologist would of course be able to spot the difference, but it is incredibly impractical for an AD patient to visit a dermatologist every day. If only there were some handy, low-cost mechanism that replicated that dermatologist’s knowledge and could be used during a patient’s daily regimen of checking their skin.”
