It appears you don't have support to open PDFs in this web browser. To view this file, Open with your PDF reader
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 18F-fluorodeoxyglucose (18F-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 18F-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 Dmaxbulk 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.
You have requested "on-the-fly" machine translation of selected content from our databases. This functionality is provided solely for your convenience and is in no way intended to replace human translation. Show full disclaimer
Neither ProQuest nor its licensors make any representations or warranties with respect to the translations. The translations are automatically generated "AS IS" and "AS AVAILABLE" and are not retained in our systems. PROQUEST AND ITS LICENSORS SPECIFICALLY DISCLAIM ANY AND ALL EXPRESS OR IMPLIED WARRANTIES, INCLUDING WITHOUT LIMITATION, ANY WARRANTIES FOR AVAILABILITY, ACCURACY, TIMELINESS, COMPLETENESS, NON-INFRINGMENT, MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE. Your use of the translations is subject to all use restrictions contained in your Electronic Products License Agreement and by using the translation functionality you agree to forgo any and all claims against ProQuest or its licensors for your use of the translation functionality and any output derived there from. Hide full disclaimer
Details
1 Vrije Universiteit Amsterdam, Amsterdam UMC, Cancer Center Amsterdam, Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227); Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, The Netherlands (GRID:grid.12380.38)
2 Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, The Netherlands (GRID:grid.12380.38); Amsterdam UMC, Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Department of Hematology, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227)
3 University Medical Center Rotterdam, Department of Hematology, Erasmus MC Cancer Institute, Rotterdam, The Netherlands (GRID:grid.508717.c) (ISNI:0000 0004 0637 3764)
4 University of Leipzig, Department of Nuclear Medicine, Clinic and Polyclinic for Nuclear Medicine, Leipzig, Germany (GRID:grid.9647.c) (ISNI:0000 0004 7669 9786)
5 University Hospital Essen, University of Duisburg-Essen, Department of Hematology, West German Cancer Center, Essen, Germany (GRID:grid.5718.b) (ISNI:0000 0001 2187 5445)
6 Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Epidemiology and Data Science, Amsterdam Public Health Research Institute, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227); Amsterdam Public Health Research Institute, Methodology, Department of Methodology, Amsterdam, The Netherlands (GRID:grid.16872.3a) (ISNI:0000 0004 0435 165X)
7 Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, The Netherlands (GRID:grid.16872.3a); Amsterdam UMC, Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Department of Hematology, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227)
8 Amsterdam UMC, Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Department of Hematology, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227)
9 King’s Health Partners, King’s College London, King’s College London and Guy’s and St Thomas’ PET Centre, School of Biomedical Engineering and Imaging Sciences, London, UK (GRID:grid.467480.9) (ISNI:0000 0004 0449 5311)
10 King’s College London University, Department of Clinical Oncology, Guy’s Cancer Centre and School of Cancer and Pharmaceutical Sciences, London, UK (GRID:grid.13097.3c) (ISNI:0000 0001 2322 6764)
11 SAKK Swiss Group for Clinical Cancer Research, Bern, Switzerland (GRID:grid.476782.8) (ISNI:0000 0001 1955 3199); Universita’ Della Svizzera Italiana, Department of Oncology, IOSI - Oncology Institute of Southern Switzerland, Bellinzona, Switzerland (GRID:grid.29078.34) (ISNI:0000 0001 2203 2861)
12 SAKK Swiss Group for Clinical Cancer Research, Bern, Switzerland (GRID:grid.476782.8) (ISNI:0000 0001 1955 3199); Universita’ Della Svizzera Italiana, Department of Nuclear Medicine and PET/CT Centre, Imaging Institute of Southern Switzerland, Bellinzona, Switzerland (GRID:grid.29078.34) (ISNI:0000 0001 2203 2861)
13 King’s College, Guy’s and St. Thomas’ Hospital, London, UK (GRID:grid.13097.3c) (ISNI:0000 0001 2322 6764)
14 Semmelweis University, Department of Nuclear Medicine, Budapest, Hungary (GRID:grid.11804.3c) (ISNI:0000 0001 0942 9821); ScanoMed Medical Diagnostic Research and Training Ltd., Budapest, Hungary (GRID:grid.11804.3c)
15 Semmelweis University, Medical Imaging Centre, Department of Nuclear Medicine, Budapest, Hungary (GRID:grid.11804.3c) (ISNI:0000 0001 0942 9821)
16 IRCCS Azienda Ospedaliero-Universitaria di Bologna, Nuclear Medicine Unit, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758); IRCCS Azienda Ospedaliero-Universitaria di Bologna, Radiology Unit, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758); University of Bologna, Nuclear Medicine, Alma Mater Studiorum, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758)
17 University of Virginia, Department of Radiology and Medical Imaging, Charlottesville, USA (GRID:grid.27755.32) (ISNI:0000 0000 9136 933X)
18 Rigshospitalet, Department of Clinical Physiology and Nuclear Medicine, Copenhagen, Denmark (GRID:grid.475435.4)
19 Rigshospitalet, Department of Haematology, Copenhagen, Denmark (GRID:grid.475435.4)
20 Australasian Association of Nuclear Medicine Specialists, Balmain, Australia (GRID:grid.475435.4)
21 Cancer Center Amsterdam, Imaging and Biomarkers, Amsterdam, The Netherlands (GRID:grid.475435.4); Amsterdam UMC, Vrije Universiteit Amsterdam, Cancer Center Amsterdam, Department of Hematology, Amsterdam, The Netherlands (GRID:grid.12380.38) (ISNI:0000 0004 1754 9227)