18F FDG PET/CT baseline radiomics features are predictive of outcome in diffuse large B-cell lymphoma patients
Up to one third of diffuse large B-cell lymphoma (DLBCL) patients experience relapse or fail to achieve complete remission during first-line treatment. Identification of poor prognosis patients might be further improved by radiomics. Radiomics analysis of imaging data provides quantitative features of tumor characteristics such as intensity, shape, volume, texture and intra- and inter-lesion heterogeneity. The aim of this study is to develop a prediction model for 2-year time to progression (TTP) using baseline quantitative radiomics features.
296 newly diagnosed DLBCL patients with baseline 18F-FDG PET/CT scans from the HOVON84 trial (EudraCT: 2006-005174-42) were included. Lesions were delineated using a fully automated preselection of 18F-FDG avid structures defined by a SUV ≥ 4.0 and volume >3mL. Missed lesions were added and non-tumour regions were removed (accurate tool, https://petralymphoma.org). Next, 490 radiomics features were extracted from the total metabolic tumor volume (MTV) using RaCat (Pfaehler et al, 2019). To reduce feature space dimensions, we made a preselection of clinically most relevant radiomics features (SUVmax, SUVmean, SUVpeak, TLG, MTV, dissemination features and sphericity) and used logistic regression with backward feature selection to predict 2-year TTP, defined as time from baseline PET/CT to progression. Patients who died without progression were censored at date of death. Furthermore, we tested the predictive value of known clinical predictors (age, WHO performance status (WHO), Ann Arbor stage, extranodal involvement, lactate dehydrogenase (LDH) level and bulky disease) and of a model that combined radiomics and clinical parameters. Model performance was assessed using repeated cross-validation (5 folds, 2000 repeats) yielding the mean receiver-operator-characteristics curve integral (AUC).
The highest performance for the radiomics model was observed for MTV combined with SUVpeak and the maximal distance between the largest lesion and any other lesion (Dmaxbulk), which yielded in a cross-validated AUC (CV-AUC) of 0.75 ± 0.07, which was significantly higher than the MTV model (CV-AUC: 0.66 ± 0.08, p = 0.01). LDH, WHO and extranodal involvement showed the highest performance for the clinical prediction model with a CV-AUC of 0.71 ± 0.08. When combining radiomics features with clinical predictors, the highest performance was observed for MTV combined with SUVpeak, Dmaxbulk, WHO and age, with a CV-AUC of 0.77 ± 0.07.
Prediction models using quantitative radiomics features extracted from baseline 18F-FDG PET/CT scans are able to identify patients at risk of relapse at baseline and have added value compared to currently used clinical and PET predictors.