Machine learning in the differentiation of follicular lymphoma from diffuse large B-cell lymphoma with radiomic [18F]FDG PET/CT features
- 1 December 2021
- journal article
- research article
- Published by Springer Nature in European Journal of Nuclear Medicine and Molecular Imaging
- Vol. 49 (5) , 1535-1543
Abstract
Background One of the challenges in the management of patients with follicular lymphoma (FL) is the identification of individuals with histological transformation, most commonly into diffuse large B-cell lymphoma (DLBCL). [18F]FDG-PET/CT is used for staging of patients with lymphoma, but visual interpretation cannot reliably discern FL from DLBCL. This study evaluated whether radiomic features extracted from clinical baseline [18F]FDG PET/CT and analyzed by machine learning algorithms may help discriminate FL from DLBCL. Materials and methods Patients were selected based on confirmed histopathological diagnosis of primary FL (n=44) or DLBCL (n=76) and available [18F]FDG PET/CT with EARL reconstruction parameters within 6 months of diagnosis. Radiomic features were extracted from the volume of interest on co-registered [18F]FDG PET and CT images. Analysis of selected radiomic features was performed with machine learning classifiers based on logistic regression and tree-based ensemble classifiers (AdaBoosting, Gradient Boosting, and XG Boosting). The performance of radiomic features was compared with a SUVmax-based logistic regression model. Results From the segmented lesions, 121 FL and 227 DLBCL lesions were included for radiomic feature extraction. In total, 79 radiomic features were extracted from the SUVmap, 51 from CT, and 6 shape features. Machine learning classifier Gradient Boosting achieved the best discrimination performance using 136 radiomic features (AUC of 0.86 and accuracy of 80%). SUVmax-based logistic regression model achieved an AUC of 0.79 and an accuracy of 70%. Gradient Boosting classifier had a significantly greater AUC and accuracy compared to the SUVmax-based logistic regression (p≤0.01). Conclusion Machine learning analysis of radiomic features may be of diagnostic value for discriminating FL from DLBCL tumor lesions, beyond that of the SUVmax alone.Keywords
This publication has 45 references indexed in Scilit:
- Rates and Outcomes of Follicular Lymphoma Transformation in the Immunochemotherapy Era: A Report From the University of Iowa/Mayo Clinic Specialized Program of Research Excellence Molecular Epidemiology ResourceJournal of Clinical Oncology, 2013
- Noise Considerations for PET Quantification Using Maximum and Peak Standardized Uptake ValueJournal of Nuclear Medicine, 2012
- Radiomics: Extracting more information from medical images using advanced feature analysisEuropean Journal of Cancer, 2012
- pROC: an open-source package for R and S+ to analyze and compare ROC curvesBMC Bioinformatics, 2011
- Features of large cell transformation of indolent lymphomas as observed on sequential PET/CTNuclear Medicine Communications, 2011
- Standardised uptake value of 18F-FDG on staging PET/CT in newly diagnosed patients with different subtypes of non-Hodgkin’s lymphomaEuropean Journal of Haematology, 2010
- High SUV uptake on FDG–PET/CT predicts for an aggressive B-cell lymphoma in a prospective study of primary FDG–PET/CT staging in lymphomaAnnals of Oncology, 2009
- From RECIST to PERCIST: Evolving Considerations for PET Response Criteria in Solid TumorsJournal of Nuclear Medicine, 2009
- Risk and Clinical Implications of Transformation of Follicular Lymphoma to Diffuse Large B-Cell LymphomaJournal of Clinical Oncology, 2007
- Intensity of18Fluorodeoxyglucose Uptake in Positron Emission Tomography Distinguishes Between Indolent and Aggressive Non-Hodgkin’s LymphomaJournal of Clinical Oncology, 2005