Radiomics vs radiologist in prostate cancer. Results from a systematic review

Giuseppe Chiacchio, Daniele Castellani*, Carlotta Nedbal, Virgilio De Stefano, Carlo Brocca, Pietro Tramanzoli, Andrea Benedetto Galosi, Rodrigo Donalisio da Silva, Jeremy Yuen Chun Teoh, Ho Yee Tiong, Nithesh Naik, Bhaskar K. Somani, Axel S. Merseburger, Vineet Gauhar

*Corresponding author for this work
2 Citations (Scopus)

Abstract

Purpose: Radiomics in uro-oncology is a rapidly evolving science proving to be a novel approach for optimizing the analysis of massive data from medical images to provide auxiliary guidance in clinical issues. This scoping review aimed to identify key aspects wherein radiomics can potentially improve the accuracy of diagnosis, staging, and extraprostatic extension in prostate cancer (PCa). Methods: The literature search was performed on June 2022 using PubMed, Embase, and Cochrane Central Controlled Register of Trials. Studies were included if radiomics were compared with radiological reports only. Results: Seventeen papers were included. The combination of PIRADS and radiomics score models improves the PIRADS score reporting of 2 and 3 lesions even in the peripheral zone. Multiparametric MRI-based radiomics models suggest that by simply omitting diffusion contrast enhancement imaging in radiomics models can simplify the process of analysis of clinically significant PCa by PIRADS. Radiomics features correlated with the Gleason grade with excellent discriminative ability. Radiomics has higher accuracy in predicting not only the presence but also the side of extraprostatic extension. Conclusions: Radiomics research on PCa mainly uses MRI as an imaging modality and is focused on diagnosis and risk stratification and has the best future possibility of improving PIRADS reporting. Radiomics has established its superiority over radiologist-reported outcomes but the variability has to be taken into consideration before translating it to clinical practice.

Original languageEnglish
JournalWorld Journal of Urology
Volume41
Issue number3
Pages (from-to)709-724
Number of pages16
ISSN0724-4983
DOIs
Publication statusPublished - 03.2023

Research Areas and Centers

  • Research Area: Luebeck Integrated Oncology Network (LION)
  • Centers: University Cancer Center Schleswig-Holstein (UCCSH)

DFG Research Classification Scheme

  • 2.22-14 Hematology, Oncology
  • 2.22-23 Reproductive Medicine, Urology

Fingerprint

Dive into the research topics of 'Radiomics vs radiologist in prostate cancer. Results from a systematic review'. Together they form a unique fingerprint.

Cite this