An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients
Maria C. Ferrández, Sandeep S.V. Golla, Jakoba J. Eertink, Bart M. de Vries, Pieternella J. Lugtenburg, Sanne E. Wiegers, Gerben J.C. Zwezerijnen, Simone Pieplenbosch, Lars Kurch, Andreas Hüttmann, Christine Hanoun, Ulrich Dührsen, Henrica C. W. de Vet, PETRA, Otto S. Hoekstra, Coreline N. Burggraaff, Annelies Bes, Martijn W. Heymans, Yvonne W. S. Jauw, Martine E.D. Chamuleau, Sally F. Barrington, G. Mikhaeel, Emanuele Zucca, Luca Ceriani, Robert Carr, Tamás Györke, Sándor Czibor, Stefano Fanti, Lale Kostakoğlu, Annika Loft, Martin Hutchings, Sze Ting Lee, Josée M. Zijlstra, Ronald Boellaard
Abstract
Abstract Convolutional neural networks (CNNs) may improve response prediction in diffuse large B-cell lymphoma (DLBCL). The aim of this study was to investigate the feasibility of a CNN using maximum intensity projection (MIP) images from 18 F-fluorodeoxyglucose ( 18 F-FDG) positron emission tomography (PET) baseline scans to predict the probability of time-to-progression (TTP) within 2 years and compare it with the International Prognostic Index (IPI), i.e. a clinically used score. 296 DLBCL 18 F-FDG PET/CT baseline scans collected from a prospective clinical trial (HOVON-84) were analysed. Cross-validation was performed using coronal and sagittal MIPs. An external dataset (340 DLBCL patients) was used to validate the model. Association between the probabilities, metabolic tumour volume and Dmax bulk was assessed. Probabilities for PET scans with synthetically removed tumors were also assessed. The CNN provided a 2-year TTP prediction with an area under the curve (AUC) of 0.74, outperforming the IPI-based model (AUC = 0.68). Furthermore, high probabilities (> 0.6) of the original MIPs were considerably decreased after removing the tumours (< 0.4, generally). These findings suggest that MIP-based CNNs are able to predict treatment outcome in DLBCL.