Corinne Johnson1, Gareth Price2, Jonathan Khalifa3, Corinne Faivre-Finn2, Andre Dekker4, Christopher Moore2, Marcel van Herk2. 1. Manchester Cancer Research Centre, Division of Molecular and Clinical Cancer Science, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester Academic Health Sciences Centre, UK; The Christie NHS Foundation Trust, Manchester Academic Health Sciences Centre, UK. Electronic address: corinne.johnson@physics.cr.man.ac.uk. 2. Manchester Cancer Research Centre, Division of Molecular and Clinical Cancer Science, School of Medical Sciences, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester Academic Health Sciences Centre, UK; The Christie NHS Foundation Trust, Manchester Academic Health Sciences Centre, UK. 3. The Christie NHS Foundation Trust, Manchester Academic Health Sciences Centre, UK; Department of Radiation Oncology, Institut Universitaire du Cancer de Toulouse - Oncopole, France. 4. The MAASTRO Clinic, Maastricht University Medical Centre+, The Netherlands.
Abstract
BACKGROUND AND PURPOSE: The gross tumour volume (GTV) is predictive of clinical outcome and consequently features in many machine-learned models. 4D-planning, however, has prompted substitution of the GTV with the internal gross target volume (iGTV). We present and validate a method to synthesise GTV data from the iGTV, allowing the combination of 3D and 4D planned patient cohorts for modelling. MATERIAL AND METHODS: Expert delineations in 40 non-small cell lung cancer patients were used to develop linear fit and erosion methods to synthesise the GTV volume and shape. Quality was assessed using Dice Similarity Coefficients (DSC) and closest point measurements; by calculating dosimetric features; and by assessing the quality of random forest models built on patient populations with and without synthetic GTVs. RESULTS: Volume estimates were within the magnitudes of inter-observer delineation variability. Shape comparisons produced mean DSCs of 0.8817 and 0.8584 for upper and lower lobe cases, respectively. A model trained on combined true and synthetic data performed significantly better than models trained on GTV alone, or combined GTV and iGTV data. CONCLUSIONS: Accurate synthesis of GTV size from the iGTV permits the combination of lung cancer patient cohorts, facilitating machine learning applications in thoracic radiotherapy.
RCT Entities:
BACKGROUND AND PURPOSE: The gross tumour volume (GTV) is predictive of clinical outcome and consequently features in many machine-learned models. 4D-planning, however, has prompted substitution of the GTV with the internal gross target volume (iGTV). We present and validate a method to synthesise GTV data from the iGTV, allowing the combination of 3D and 4D planned patient cohorts for modelling. MATERIAL AND METHODS: Expert delineations in 40 non-small cell lung cancerpatients were used to develop linear fit and erosion methods to synthesise the GTV volume and shape. Quality was assessed using Dice Similarity Coefficients (DSC) and closest point measurements; by calculating dosimetric features; and by assessing the quality of random forest models built on patient populations with and without synthetic GTVs. RESULTS: Volume estimates were within the magnitudes of inter-observer delineation variability. Shape comparisons produced mean DSCs of 0.8817 and 0.8584 for upper and lower lobe cases, respectively. A model trained on combined true and synthetic data performed significantly better than models trained on GTV alone, or combined GTV and iGTV data. CONCLUSIONS: Accurate synthesis of GTV size from the iGTV permits the combination of lung cancerpatient cohorts, facilitating machine learning applications in thoracic radiotherapy.
Authors: Isabella Fornacon-Wood; Clara Chan; Neil Bayman; Kathryn Banfill; Joanna Coote; Alex Garbett; Margaret Harris; Andrew Hudson; Jason Kennedy; Laura Pemberton; Ahmed Salem; Hamid Sheikh; Philip Whitehurst; David Woolf; Gareth Price; Corinne Faivre-Finn Journal: Front Oncol Date: 2022-05-31 Impact factor: 5.738