Enhancing Breast Cancer Treatments Using Imaging Biomarkers.
Quantitative Thermal Imaging: Thermoradiomics.
Radiation-induced dermatitis is a common side effect of breast radiotherapy (RT). Current methods to evaluate breast skin toxicity include clinical examination, visual inspection, and patient-reported symptoms. Physiological changes associated with radiation-induced dermatitis, such as inflammation, may also increase body-surface temperature which can be detected by thermal imaging. Our team is investigating the use of quantitative thermal imaging markers as early signatures of radiation dermatitis.
Our results demonstrate that patients who presented with a CTCAE≥2, as evaluated at the time of their last RT fraction, exhibited higher skin-surface temperature values during treatment compared to those who demonstrated a CTCAE≤1 score. The temperature differences between patient groups were most evident at the 10th fraction of radiotherapy.
Our research team is studying pre-treatment diffuse optical spectroscopy (DOS)-based texture features and machine learning techniques to measure physiological characteristics of locally advanced breast tumours. These imaging and modelling techniques have been shown to predict breast cancer response to anthracycline- and taxane-based chemotherapy. The results demonstrate for the first time that textural heterogeneities in DOS measures of haemoglobin and oxygen content in breast tumours predicts NAC response with high accuracy. Volumetric tumour analysis indicated that tumour-specific ROI-data can yield highly sensitive and specific univariate and multivariate textural markers using various classifier models.