Detecting Skin Reactions in Epicutaneous Patch Testing with Deep Learning: An Evaluation of Pre-Processing and Modality Performance

Epicutaneous patch testing is a well-established diagnostic method for identifying substances that may cause Allergic Contact Dermatitis (ACD), common skin condition caused by exposure to environmental allergens. While the test remains gold standard allergens, it prone observer bias and consumes valuable human resources. Deep learning models can be employed address this challenge. In study, we collected dataset of 1579 multi-modal images from 200 patients using Antera 3D® camera. We then investigated feasibility deep classifier automating identification allergens causing ACD. propose approach utilizes context-retaining pre-processing technique improve accuracy classifier. addition, find promise in combination color image false-color map hemoglobin concentration accuracy. Our results showed potentially achieve more than 86% recall 94% specificity reactions, contribute faster accurate diagnosis while reducing clinician workload.