Prostate-Specific Membrane Antigen-Positron Emission Tomography-Guided Radiomics and Machine Learning in Prostate Carcinoma

Aug 3, 2026

Positron emission tomography (PET) using prostate-specific membrane antigen (PSMA)-targeted radioligand imaging has expanded for prostate carcinoma staging and treatment guidance. Available evidence summarizes how PET/CT radiomics and machine learning can extract quantitative imaging markers and translate them into clinical value. Studies suggest improved non-invasive characterization of Gleason score compared with biopsy-based assessment, support for predicting biochemical recurrence, and the differentiation of benign versus malignant tracer uptake. Results for 177Lu-PSMA therapy outcome and overall survival remain limited, highlighting the need for larger datasets and external validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

1. Introduction

Radiomics feature extraction and quantitative parameters

Feature reduction and selection for machine learning

Supervised learning and data requirements

cancers Review Prostate-Specific Membrane Antigen-Positron Emission Tomography-Guided Radiomics and Machine Learning in Prostate Carcinoma Justine Maes 1, Simon Gesquière 2, Alex Maes 1,3, Mike Sathekge 4 and Christophe Van de Wiele 1,5, * Citation: Maes, J.; Gesquière, S.; Maes, A.; Sathekge, M.; Van de Wiele, C. Prostate-Specific Membrane Antigen-Positron Emission Tomography-Guided Radiomics and Machine Learning in Prostate Carcinoma. Cancers 2024, 16, 3369 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)cancers16193369 Academic Editor: Hideya Yamazaki Received: 9 September 2024 Revised: 16 September 2024 Accepted: 20 September 2024 Published: 1 October 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Nuclear Medicine, AZ Groeninge, 8500 Kortrijk, Belgium; [justinemaes@hotmail.com](justinemaes@hotmail.com) (J.M.); [alex.maes@azgroeninge.be](alex.maes@azgroeninge.be) (A.M.) 2 Department of Nuclear Medicine, University Hospital Ghent, 9000 Ghent, Belgium; [simon.gesquiere@uzgent.be](simon.gesquiere@uzgent.be) 3 Department of Morphology and Functional Imaging, University Hospital Leuven, 3000 Leuven, Belgium 4 Department of Nuclear Medicine, University of Pretoria, Pretoria 0002, South Africa; [mike.sathekge@up.ac.za](mike.sathekge@up.ac.za) 5 Department of Diagnostic Sciences, University Ghent, 9000 Ghent, Belgium * Correspondence: [christophe.vandewiele@ugent.be](christophe.vandewiele@ugent.be) Simple Summary: Available studies suggest that radiomics and machine learning applied to PSMAradioligand avid primary prostate carcinoma have potential to serve as an alternative for non-invasive Gleason score characterization, for the prediction of biochemical recurrence and to differentiate benign from malignant increased tracer uptake. However, prior to their implementation in clinical practice, additional, clinically relevant studies performed according to recently published guidelines and checklists, offering full transparency, including large enough datasets as well as external validation, are mandatory. Abstract: Positron emission tomography (PET) using radiolabeled prostate-specific membrane antigen targeting PET-imaging agents has been increasingly used over the past decade for imaging and directing prostate carcinoma treatment. Here, we summarize the available literature data on radiomics and machine learning using these imaging agents in prostate carcinoma. Gleason scores derived from biopsy and after resection are discordant in a large number of prostate carcinoma patients. Available studies suggest that radiomics and machine learning applied to PSMA-radioligand avid primary prostate carcinoma might be better performing than biopsy-based Gleason-scoring and could serve as an alternative for non-invasive GS characterization. Furthermore, it may allow for the prediction of biochemical recurrence with a net benefit for clinical utilization. Machine learning based on PET/CT radiomics features was also shown to be able to differentiate benign from malignant increased tracer uptake on PSMA-targeting radioligand PET/CT examinations, thus paving the way for a fully automated image reading in nuclear medicine. As for prediction to treatment outcome following 177Lu-PSMA therapy and overall survival, a limited number of studies have reported promising results on radiomics and machine learning applied to PSMA-targeting radioligand PET/CT images for this purpose. Its added value to clinical parameters warrants further exploration in larger datasets of patients. Keywords: PSMA; prostate carcinoma; radiomics 1. Introduction Radiomics allo

FAQs

What is the role of radiomics in PSMA PET for prostate carcinoma?

Radiomics extracts quantitative radiomic features from segmented tumor lesions that are not visually discernible, enabling computational analysis of imaging patterns.

How might machine learning improve Gleason score characterization?

Studies indicate radiomics and machine learning using PSMA-radioligand avid primary lesions may perform better than biopsy-based Gleason scoring and serve as a non-invasive alternative.

What evidence supports using these methods to predict treatment outcomes?

A limited number of studies report promising results for radiomics and machine learning applied to PSMA-targeting PET/CT images for predicting outcomes after 177Lu-PSMA therapy and overall survival, warranting further investigation in larger cohorts.

Aug 3, 2026

Upload by Theodore