Semantic modeling of cell damage prediction: a machine learning approach at human-level performance in dermatology

Abstract

Machine learning is transforming the field of histopathology. Especially in classification related tasks, there have been many successful applications of deep learning already. Yet, in tasks that rely on regression and many niche applications, the domain lacks cohesive procedures that are adapted to the learning processes of neural networks. In this work, we investigate cell damage in whole slide images of the epidermis. A common way for pathologists to annotate a score, characterizing the degree of damage for these samples, is the ratio between healthy and unhealthy nuclei. The annotation procedure of these scores, however, is expensive and prone to be noisy among pathologists. We propose a new measure of damage, that is the total area of damage, relative to the total area of the epidermis. In this work, we present results of regression and segmentation models, predicting both scores on a curated and public dataset. We have acquired the dataset in collaborative efforts with medical professionals. Our study resulted in a comprehensive evaluation of the proposed damage metrics in the epidermis, with recommendations, emphasizing practical relevance for real world applications.

Far‐UVC‐ and UVB‐induced DNA damage depending on skin type

“…Furthermore, the area score of CPD + cells representative for the distribution of DNA damage in the epidermis was calculated using a semantic machine learning model as previously described elsewhere 25 . The area score S area was calculated as the ratio of the area of the epidermis and the area of semantic segmentation maps of damaged cells in the epidermis.…”

Redefine photoprotection: Sun protection beyond sunburn

“…Thus, a semantic model for the prediction of DNA damage in the epidermis of histological slides stained for CPD + and 6-4 PP DNA damage was used as previously described elsewhere. 31 For data augmentation, the epidermis was additionally masked with a separate segmentation model based on the U-Net/64 convolutional network typically used in biomedical image segmentation. This ensures that only information from the epidermis was considered.…”