Baseline PET radiomics outperform the IPI risk score for prediction of outcome in diffuse large B-cell lymphoma

Abstract

The objective of this study was to externally validate the clinicalPET model developed in the HOVON-84 trial and to compare the model performance of our clinicalPET model to the international prognostic index (IPI). In total, 1195 Diffuse large B-cell lymphoma patients were included. 887 patients from 6 studies were used as external validation datasets. Primary outcomes were 2-year progression free survival (PFS) and 2-year time to progression (TTP). Metabolic tumor volume (MTV), the maximum distance between the largest lesion and another lesion (Dmaxbulk) and the peak standardized uptake value (SUVpeak) were extracted. The predictive value of the IPI and the HOVON-84 clinicalPET model (MTV, Dmaxbulk, SUVpeak, performance status and age) were tested. Model performance was assessed using the area under the curve (AUC), and diagnostic performance with the positive predictive value (PPV). Using 2-year PFS as outcome, the IPI yielded an AUC of 0.62 (range:0.51-0.65). The clinicalPET model yielded a significantly higher AUC of 0.71 (range:0.59-0.75, p<0.001). Comparable results were found using 2-year TTP. High-risk IPI patients had a 2-year PFS of 61.4%, versus 51.9% for the high-risk clinicalPET patients, with an increase in PPV from 35.5% to 49.1%, respectively. 66.4% of high-risk IPI patients were free from progression or relapse versus 55.5% for high-risk clinicalPET patients, with an increased PPV from 33.7% to 44.6%, respectively. The clinicalPET model that was developed in the HOVON-84 dataset remained predictive of outcome in 6 independent first-line DLBCL studies, and had higher model performance than the currently used IPI in all studies.

Comprehensive scientometrics and visualization study profiles lymphoma metabolism and identifies its significant research signatures

“…The recent demonstration by Eertink et al. that baseline PET radiomics is superior to traditional IPI risk scores in predicting outcome in diffuse large B-cell lymphoma provides a wonderful example ( 51 ).…”

An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients

“…From these, 279 were classified as TTP0 and 61 as TTP1. The exact same data were used as in Eertink et al 4 , 19 , so that our results can be compared with recently published segmentation based approaches.…”

“…To better understand the CNN predictions, we further investigated the output of the model by exploring the association between P(TTP1) and two PET extracted features: MTV and Dmax bulk since both have shown potential as prognostic markers in DLBCL 4 , 5 , 19 , 23 . The process to extract PET features has been explained in previous studies 4 .…”

Real-world applicability of the International Metabolic Prognostic Index in DLBCL: a validation cohort study

“… 1 The IMPI incorporates the total metabolic tumor volume (TMTV) with age and stage as continuous variables rather than in a dichotomized manner, which is less influenced by data-driven optimal cutoffs, thereby increasing generalizability. 2 , 3 However, the applicability of IMPI to real-world cohorts remains uncertain due to its model construction using hybrid data sets that largely depend on clinical trials. Furthermore, a model performance comparison of IMPI and the National Comprehensive Cancer Network IPI (NCCN-IPI) remains unreported.…”