(Chemo)-radiotherapy is the gold standard therapeutic treatment for patients with locally advanced lung cancer non accessible or ineligible for surgery. While some progress occurred regarding progression free survival and overall survival thanks to recent advances (i.e., durvalumab), prediction of pulmonary and esophageal toxicity, remains insufficiently accurate. Current dose-volume histograms (DVH) do not account for spatial dose distribution and strict application of current dose constraints does not prevent toxicity events in some of the treated patients. The goal of this work was to investigate the added predictive value of the radiomics approach applied to dose maps regarding acute and late toxicity in both lungs and the esophagus.
Study Type
OBSERVATIONAL
Enrollment
167
CHRU Brest
Brest, Finistère, France
Prediction of Acute Pulmonary Toxicity
The model's performance will be evaluated based on the observed rate of Acute Pulmonary Toxicity using classification metrics (area Under the curve, balanced accuracy).
Time frame: Up to 6 months
Prediction of Late Pulmonary Toxicity
The model's performance will be evaluated based on the observed rate of Late Pulmonary Toxicity using classification metrics (area Under the curve, balanced accuracy).
Time frame: Between 6 months and 2 years after radiotherapy
Prediction of Acute Oesophageal Toxicity
The model's performance will be evaluated based on the observed rate of Acute Oesophageal Toxicity using classification metrics (area Under the curve, balanced accuracy).
Time frame: Up to 6 months
Prediction of Late Oesophageal Toxicity
The model's performance will be evaluated based on the observed rate of Late Oesophageal Toxicity using classification metrics (area Under the curve, balanced accuracy).
Time frame: Between 6 months and 2 years after radiotherapy
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.