AUTHOR=Ritter Zsombor , Papp László , Zámbó Katalin , Tóth Zoltán , Dezső Dániel , Veres Dániel Sándor , Máthé Domokos , Budán Ferenc , Karádi Éva , Balikó Anett , Pajor László , Szomor Árpád , Schmidt Erzsébet , Alizadeh Hussain 

TITLE=Two-Year Event-Free Survival Prediction in DLBCL Patients Based on In Vivo Radiomics and Clinical Parameters

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.820136

DOI=10.3389/fonc.2022.820136

ISSN=2234-943X

ABSTRACT=Purpose: For the identification of high risk patients in diffuse large B-cell lymphoma we investigated the prognostic significance of in vivo radiomics derived from baseline [18F]FDG PET/CT and clinical parameters. 
Methods: Pre-treatment [18F]FDG PET/CT scans of 85 patients diagnosed with DLBCL were assessed. The scans were carried out in two clinical centers. Two-year event-free survival was defined. After delineation of lymphoma lesions conventional PET parameters and in vivo radiomics were extracted. For 2-year EFS prognosis assessment, Center 1 dataset was utilized as training set and underwent automated machine learning analysis. The dataset of Center 2 was utilized as independent test set to validate the established predictive model built by the dataset of Center 1.
Results: The automated machine learning analysis of the Center 1 dataset revealed the most important features for building 2-years event free survival are: max diameter, neighbor gray tone difference matrix (NGTDM) busyness, Total lesion glycolysis, Total metabolic tumor volume and NGTDM Coarseness. The predictive model built on Center 1 dataset yielded 79% sensitivity, 83% specificity, 69% positive predictive value, 89% negative predictive value and 0.85 AUC in by evaluating the Center 2 dataset. 
Conclusion: Based on our dual-center retrospective analysis, predicting 2-year event-free survival built on imaging features is feasible with a high-performance utilizing automated machine learning.