ESTRO 2022 - Abstract Book

S319

Abstract book

ESTRO 2022

MO-0384 A CT-radiomics model to predict recurrence post curative-intent radiotherapy for stage I-III NSCLC

S. Hindocha 1 , T. Charlton 2 , K. Linton-Reid 3 , B. Hunter 1 , C. Chan 4 , M. Ahmed 1 , E. Robinson 5 , M. Orton 6 , J. Lunn 7 , S. Ahmed 8 , F. McDonald 1 , I. Locke 1 , D. Power 9 , S. Doran 7 , M. Blackledge 7 , R. Lee 1 , E. Aboagye 3 1 The Royal Marsden NHS Foundation Trust, Lung Unit, London, United Kingdom; 2 Guy's & St Thomas' NHS Foundation Trust, Lung Unit, London, United Kingdom; 3 Imperial College London, Department of Surgery & Cancer, London, United Kingdom; 4 The Royal Marsden NHS Foundation Trust, Clinical Oncology, London, United Kingdom; 5 Institute of Cancer Research, Clinical Trials Unit, London, United Kingdom; 6 Institute of Cancer Research, Artificial Intelligence Imaging Hub, London, United Kingdom; 7 Institute of Cancer Research, Radiotherapy & Imaging, London, United Kingdom; 8 Guy's & St Thomas' NHS Foundation Trust, Lung Unitq, London, United Kingdom; 9 Imperial College Healthcare NHS Trust, Clinical Oncology, London, United Kingdom Purpose or Objective Recurrence occurs in up to 36% of patients treated with radiotherapy for NSCLC. High-quality evidence to provide specific recommendations on the nature of post-treatment surveillance is lacking. Risk-stratification models are required to determine optimal follow-up. We present a radiomics model to predict recurrence and recurrence-free survival (RFS) 2 years post-treatment, using routinely available radiotherapy planning CTs and the gross tumour volume (GTV), contoured for radiotherapy purposes as the region of interest for feature extraction. Materials and Methods A retrospective multi-centre study of patients receiving stereotactic or conventional (chemo)radiotherapy for stage I-III NSCLC was undertaken. Cases with a GTV encompassing the primary tumour were included from 5 hospitals. Cases from 4 hospitals were divided into training and validation sets, stratified by outcome, with the 5 th hospital providing an external test set. Radiotherapy planning CTs were pre-processed and features extracted from GTVs using TexLAB 2.0. Time to recurrence/RFS data were binarized (yes/no) at 2 years from the first fraction of radiotherapy for classification purposes. We explored a combination of 9 feature reduction techniques with 11 machine learning classifiers, producing risk- stratification models for recurrence and RFS. The model with the highest validation set AUC was selected and deployed on the external test set. Models were compared with 10-fold cross validation and bench-marked against TNM stage. Youden index, calculated from validation set ROC curves, was used to define high and low risk groups. Kaplan-Meier curves were produced.