Russell Frood1,2,3, Matthew Clark2, Cathy Burton4, Charalampos Tsoumpas5,6, Alejandro F Frangi6,7,8, Fergus Gleeson7,9, Chirag Patel1,2, Andrew F Scarsbrook1,2,3. 1. Department of Nuclear Medicine, Leeds Teaching Hospitals NHS Trust, Leeds LS2 9JT, UK. 2. Department of Radiology, Leeds Teaching Hospitals NHS Trust, Leeds LS2 9JT, UK. 3. Leeds Institute of Health Research, University of Leeds, Leeds LS9 7TF, UK. 4. Department of Haematology, Leeds Teaching Hospitals NHS Trust, Leeds LS2 9JT, UK. 5. Department of Nuclear Medicine and Molecular Imaging, University Medical Center of Groningen, University of Groningen, 9713 AV Groningen, The Netherlands. 6. Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds LS2 9JT, UK. 7. Centre for Computational Imaging and Simulation Technologies in Biomedicine (CISTIB), School of Computing and School of Medicine, University of Leeds, Leeds LS2 9JT, UK. 8. Medical Imaging Research Center (MIRC), University Hospital Gasthuisberg, Katholieke Universiteit Leuven, 3000 Leuven, Belgium. 9. Department of Radiology, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK.
Abstract
BACKGROUND: Approximately 30% of patients with diffuse large B-cell lymphoma (DLBCL) will have recurrence. The aim of this study was to develop a radiomic based model derived from baseline PET/CT to predict 2-year event free survival (2-EFS). METHODS: Patients with DLBCL treated with R-CHOP chemotherapy undergoing pre-treatment PET/CT between January 2008 and January 2018 were included. The dataset was split into training and internal unseen test sets (ratio 80:20). A logistic regression model using metabolic tumour volume (MTV) and six different machine learning classifiers created from clinical and radiomic features derived from the baseline PET/CT were trained and tuned using four-fold cross validation. The model with the highest mean validation receiver operator characteristic (ROC) curve area under the curve (AUC) was tested on the unseen test set. RESULTS: 229 DLBCL patients met the inclusion criteria with 62 (27%) having 2-EFS events. The training cohort had 183 patients with 46 patients in the unseen test cohort. The model with the highest mean validation AUC combined clinical and radiomic features in a ridge regression model with a mean validation AUC of 0.75 ± 0.06 and a test AUC of 0.73. CONCLUSIONS: Radiomics based models demonstrate promise in predicting outcomes in DLBCL patients.
BACKGROUND: Approximately 30% of patients with diffuse large B-cell lymphoma (DLBCL) will have recurrence. The aim of this study was to develop a radiomic based model derived from baseline PET/CT to predict 2-year event free survival (2-EFS). METHODS: Patients with DLBCL treated with R-CHOP chemotherapy undergoing pre-treatment PET/CT between January 2008 and January 2018 were included. The dataset was split into training and internal unseen test sets (ratio 80:20). A logistic regression model using metabolic tumour volume (MTV) and six different machine learning classifiers created from clinical and radiomic features derived from the baseline PET/CT were trained and tuned using four-fold cross validation. The model with the highest mean validation receiver operator characteristic (ROC) curve area under the curve (AUC) was tested on the unseen test set. RESULTS: 229 DLBCL patients met the inclusion criteria with 62 (27%) having 2-EFS events. The training cohort had 183 patients with 46 patients in the unseen test cohort. The model with the highest mean validation AUC combined clinical and radiomic features in a ridge regression model with a mean validation AUC of 0.75 ± 0.06 and a test AUC of 0.73. CONCLUSIONS: Radiomics based models demonstrate promise in predicting outcomes in DLBCL patients.
Authors: Hugo J A Adams; John M H de Klerk; Rob Fijnheer; Ben G F Heggelman; Stefan V Dubois; Rutger A J Nievelstein; Thomas C Kwee Journal: Eur J Haematol Date: 2015-03-13 Impact factor: 2.997
Authors: Bruce D Cheson; Richard I Fisher; Sally F Barrington; Franco Cavalli; Lawrence H Schwartz; Emanuele Zucca; T Andrew Lister Journal: J Clin Oncol Date: 2014-09-20 Impact factor: 44.544
Authors: J Zhong; R Frood; P Brown; H Nelstrop; R Prestwich; G McDermott; S Currie; S Vaidyanathan; A F Scarsbrook Journal: Clin Radiol Date: 2020-10-06 Impact factor: 2.350
Authors: Mathieu Nessim Toledano; P Desbordes; A Banjar; I Gardin; P Vera; P Ruminy; F Jardin; H Tilly; S Becker Journal: Eur J Nucl Med Mol Imaging Date: 2018-01-17 Impact factor: 9.236
Authors: N George Mikhaeel; Daniel Smith; Joel T Dunn; Michael Phillips; Henrik Møller; Paul A Fields; David Wrench; Sally F Barrington Journal: Eur J Nucl Med Mol Imaging Date: 2016-02-23 Impact factor: 9.236
Authors: P J Brown; J Zhong; R Frood; S Currie; A Gilbert; A L Appelt; D Sebag-Montefiore; A Scarsbrook Journal: Eur J Nucl Med Mol Imaging Date: 2019-09-04 Impact factor: 9.236