Pd42-02 Psma Pet/Ct Radiomics: Assessing Adverse Pathological Risk and Proteomic Biomarker Correlations in Prostate Cancer

You have accessJournal of UrologyProstate Cancer: Markers II (PD42)1 May 2024PD42-02 PSMA PET/CT RADIOMICS: ASSESSING ADVERSE PATHOLOGICAL RISK AND PROTEOMIC BIOMARKER CORRELATIONS IN PROSTATE CANCER Wenhao Zhu, Yongxiang Tang, Xiaomei Gao, Minfeng Chen, Shuo Hu, and Yi Cai Wenhao ZhuWenhao Zhu , Yongxiang TangYongxiang Tang , Xiaomei GaoXiaomei Gao , Minfeng ChenMinfeng Chen , Shuo HuShuo Hu , and Yi CaiYi Cai View All Author Informationhttps://doi.org/10.1097/01.JU.0001008560.54103.65.02AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Prostate cancer (PCa) is a highly heterogeneous malignancy. The early identification of adverse pathological characteristics in PCa during a controllable stage of the tumor is a critical factor in improving patient prognosis. This study employed radiomics machine learning models to predict the aggressiveness of PCa and identify quantitative radiomic features and protein biomarkers associated with adverse pathological traits. Consequently, the goal was to construct a multi-omics marker that enhances risk stratification. METHODS: In this retrospective study, 191 patients diagnosed with prostate cancer (PCa) or benign prostatic hyperplasia (BPH) at the time of diagnosis and confirmed via pathology after undergoing a 68Ga-PSMA-11 PET/CT scan were included. Under the guidance of PSMA-PET, CT images were utilized for anatomical localization, with prostate contours manually delineated and radiomic features extracted. Six machine learning algorithms were employed to construct radiomics models for predicting malignancies and combinations of adverse pathological features (Gleason score (GS), ISUP group, pathological stage (pT), lymph node infiltration (LNI), and perineural invasion (PNI)). Feature selection was conducted using two methods, minimum redundancy maximum relevance (mRMR) and LASSO, to identify the quantitative radiomic features with optimal predictive capacity. Additionally, proteomics was performed on 39 patients to identify protein biomarkers of adverse pathological features at the molecular level in PCa. Correlation analysis was used to refine the associations between quantitative radiomic features and protein biomarkers. RESULTS: The optimal radiomics model based on machine learning methods achieved an area under the curve (AUC) of 0.938 (95% CI: 0.893 to 0.983) for predicting malignant prostate lesions and an AUC of 0.916 (95% CI: 0.854 to 0.977) for adverse pathological feature combinations in the test set. The validation set yielded AUC values of 0.918 (95% CI: 0.848 to 0.989) for malignancy prediction and 0.855 (95% CI: 0.728 to 0.983) for adverse feature combinations. Three quantitative radiomic features and ten protein molecules associated with adverse pathological characteristics were identified. Moreover, the study revealed a significant correlation between quantitative radiomic features and protein biomarkers, with radioproteomic analysis highlighting the potential impact of molecular changes in protein molecules on imaging biomarkers. CONCLUSIONS: The machine learning models developed from 68Ga-PSMA-11 PET/CT radiomic features can stratify patients with clinically meaningful insights, guiding risk stratification, and revealing potential links between quantitative radiomic characteristics and protein biomarkers. Source of Funding: His research was supported by the key Research and Development program of Hunan Province (2021SK2014, 2023SK2017), the Science and Technology Innovation Team Talent Project of Hunan Province (2021 RC4056), the National Natural Science Foundation of China (82272907, 81974397, 91859207, 81771873), the clinical research foundation of the National Clinical Research Center for Geriatric Diseases (XIANGYA; 2020LNJJ01), and the Fundamental Research Funds for the Central Universities of Central South university © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e892 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Wenhao Zhu More articles by this author Yongxiang Tang More articles by this author Xiaomei Gao More articles by this author Minfeng Chen More articles by this author Shuo Hu More articles by this author Yi Cai More articles by this author Expand All Advertisement PDF downloadLoading ...