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

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

doi:10.3389/fonc.2022.820136

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

Front Oncol. 2022 Jun 8:12:820136. doi: 10.3389/fonc.2022.820136. eCollection 2022.

Authors

Affiliations

¹ Department of Medical Imaging, Medical School, University of Pécs, Pécs, Hungary.
² Medical University of Vienna, Center for Medical Physics and Biomedical Engineering, Vienna, Austria.
³ University of Kaposvár, PET Medicopus Nonprofit Ltd., Kaposvár, Hungary.
⁴ Department of Biophysics and Radiation Biology, Faculty of Medicine, Semmelweis University, Budapest, Hungary.
⁵ In Vivo Imaging Advanced Core Facility, Hungarian Centre of Excellence for Molecular Medicine, Budapest, Hungary.
⁶ Institute of Transdisciplinary Discoveries, Medical School, University of Pécs, Pécs, Hungary.
⁷ Institute of Physiology, Medical School, University of Pécs, Pécs, Hungary.
⁸ Department of Hematology, University of Kaposvár, Kaposvár, Hungary.
⁹ County Hospital Tolna, János Balassa Hospital, Szekszárd, Hungary.
¹⁰ Department of Pathology, Medical School, University of Pécs, Pécs, Hungary.
¹¹ 1st Department of Internal Medicine, Medical School, University of Pécs, Pécs, Hungary.

Abstract

Purpose: For the identification of high-risk patients in diffuse large B-cell lymphoma (DLBCL), 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 (EFS) was defined. After delineation of lymphoma lesions, conventional PET parameters and in vivo radiomics were extracted. For 2-year EFS prognosis assessment, the Center 1 dataset was utilized as the training set and underwent automated machine learning analysis. The dataset of Center 2 was utilized as an 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 that the most important features for building 2-year EFS are as follows: max diameter, neighbor gray tone difference matrix (NGTDM) busyness, total lesion glycolysis, total metabolic tumor volume, and NGTDM coarseness. The predictive model built on the Center 1 dataset yielded 79% sensitivity, 83% specificity, 69% positive predictive value, 89% negative predictive value, and 0.85 AUC by evaluating the Center 2 dataset.

Conclusion: Based on our dual-center retrospective analysis, predicting 2-year EFS built on imaging features is feasible by utilizing high-performance automated machine learning.

Keywords: DLBCL; [18F]FDG PET/CT; automated machine learning; radiomics; tumor imaging.