From Pixels to Predictions: Development of a multimodal-based deep learning algorithm for accurate and efficient erythema score assessment in radiation induced dermatitis

This study aims to develop advanced techniques that utilize a deep learning algorithm for the automatic classification of RISRs in accordance with the Common Terminology Criteria for Adverse Events (CTCAE) grading system. In terms of data, we propose a robust pipeline to collect a dedicated, diverse, and curated image dataset using Scarletred® Vision, a CE-certified medical device software platform. When it comes to models, we have trained a feedback-based deep learning multimodal system that incorporates Scarletred® Vision augmentation pipeline using 2192 distinct images. The results of our study indicate that the proposed model achieved high precision (92.51%), recall (91.21%), and F-score (91.83%), with a test accuracy of 92.02%. These results indicate a high level of precision and discriminatory power of the model across all three classes.