A Prospective Study Demonstrating Early Prediction of Skin Toxicity From Radiation Therapy Using Radiomic Features From Optical and Infrared Images

Abstract

Purpose: Approximately 90% of patients undergoing breast cancer radiation therapy experience skin toxicities that are difficult to classify and predict ahead of time. A prediction of toxicity at the early stages of the treatment would provide clinicians with a prompt to intervene. The objectives of this study were to evaluate the correlation between skin toxicity and radiomic features extracted from optical and infrared (thermal) images of skin, and to develop a model for predicting a patient's skin response to radiation.

Methods and materials: Optical and infrared breast and chest-wall images were acquired daily during the course of radiation therapy, as well as weekly for 3 weeks after the end of treatment for 20 patients with breast cancer. Skin-toxicity assessments were conducted weekly until the patients' final visit. Skin color and temperature trends from histogram-based and texture-based radiomic features, extracted from the treatment area, were analyzed, reduced, and used in a cross-validation machine learning model to predict the patients' skin toxicity grades.

Results: A set of 9 independent color and temperature features with significant correlation to skin toxicity were identified from 108 features. The cross-validation accuracy of a cubic Support Vector Machine remained >85% and area under the receiver operating characteristic curve remained >0.75, when reducing the input imaging data to include only the sessions with a biologically effective dose not exceeding 30 Gy (approximately the first third to first half of the total treatment dose).

Conclusions: The quantitative analysis of radiomic features extracted from optical and infrared (thermal) images of skin was shown to be promising for predicting skin toxicities.