Estimating the Potential of Radiomics Features and Radiomics Signature from Pretherapeutic PSMA-PET-CT Scans and Clinical Data for Prediction of Overall Survival When Treated with 177Lu-PSMA.

Abstract

Prostate-specific membrane antigen (PSMA) positron emission tomography/computed tomography (PSMA-PET/CT) scans can facilitate diagnosis and treatment of prostate disease. Radiomics signature (RS) is widely used for the analysis of overall survival (OS) in cancer diseases. This study aims at investigating the role of radiomics features (RFs) and RS from pretherapeutic gallium-68 (68Ga)-PSMA-PET/CT findings and patient-specific clinical parameters to analyze overall survival of prostate cancer (PC) patients when treated with lutethium-177 (177Lu)-PSMA. A cohort of 83 patients with advanced PC was retrospectively analyzed. Average values of 73 RFs of 2070 malignant hotspots as well as 22 clinical parameters were analyzed for each patient. From the Cox proportional hazard model, the least absolute shrinkage and selection operator (LASSO) regularization method is used to select most relevant features (standardized uptake value (SUV)Min and kurtosis with the coefficients of 0.984 and -0.118, respectively) and to calculate the RS from the RFs. Kaplan-Meier (KM) estimator was used to analyze the potential of RFs and conventional clinical parameters, such as metabolic tumor volume (MTV) and standardized uptake value (SUV) for the prediction of survival. As a result, SUVMin, kurtosis, the calculated RS, SUVMean, as well as Hemoglobin (Hb)1, C-reactive protein (CRP)1, and ECOG1 (clinical parameters) achieved p-values less than 0.05, which suggest the potential of findings from 68Ga-PSMA-PET/CT scans as well as patient-specific clinical parameters for the prediction of OS for patients with advanced PC treated with 177Lu-PSMA therapy.

• Authors: Sobhan Moazemi, Annette Erle, Susanne Lütje, Florian C Gaertner, Markus Essler, Ralph A Bundschuh
• Journal: Diagnostics (Basel, Switzerland) (Diagnostics (Basel)) Vol. 11 Issue 2 (Jan 28 2021) ISSN: 2075-4418 [Print] Switzerland
• PMID: 33525456 (Publication Type: Journal Article)