Evaluation of Baseline and Interim-Therapy PET Features for Prognostication in High-Risk Pediatric Hodgkin Lymphoma: A Retrospective Analysis of the AHOD1331 Trial

This study aimed to evaluate the prognostic value of conventional and advanced PET metrics for predicting progression-free survival in high-risk pediatric Hodgkin lymphoma (HL), using data from the Children’s Oncology Group AHOD1331 trial. <b>Methods:</b> This retrospective analysis included 558 patients from 150 institutions. Conventional PET metrics and radiomics features were extracted from both baseline and interim-therapy PET images. Clinical variables, including demographic characteristics and common risk factors, were also considered. A standardized outcome-modeling pipeline was developed, comprising feature selection and penalized Cox regression with elastic net regularization (CoxNet). Models were trained and evaluated using nested cross-validation stratified by institution, ensuring consistent external testing. We investigated whether conventional PET metrics added prognostic value beyond clinical variables and whether radiomics or interim PET-derived features offered further benefit. Additionally, we compared the prognostic performance of features extracted from automated deep learning (DL) segmentations against those derived from physician annotations. Model performance was assessed using the concordance index (C-index). <b>Results:</b> Among all types of features, the CoxNet model using conventional baseline PET metrics achieved the highest performance (C-index, 0.72 ± 0.01), significantly outperforming the clinical model (C-index, 0.65 ± 0.01). Neither the inclusion of radiomics features nor interim PET-derived features improved performance. Models using DL-generated segmentations achieved comparable prognostic accuracy (C-index, 0.72 ± 0.01) to those using physician-based segmentations. <b>Conclusion:</b> Quantitative PET features provided significant prognostic improvements over clinical variables. Furthermore, DL-based segmentation offered a promising approach for automating feature extraction, supporting more effective risk stratification in pediatric HL.