# Contemporary Preoperative Detection of Extraprostatic Extension in Prostate Cancer

## TL;DR

This review explores current and emerging methods, including AI, for detecting prostate cancer spread beyond the prostate before surgery.

## Contribution

The paper provides a contemporary overview of AI-based techniques for improving preoperative detection of extraprostatic extension in prostate cancer.

## Key findings

- Deep-learning models show performance comparable to expert radiologists for EPE detection.
- Radiomics and machine learning models outperform traditional methods in some cases.
- Side-specific and graded EPE assessment is more clinically relevant than binary classification.

## Abstract

Extraprostatic extension occurs when prostate cancer grows beyond the prostate capsule and is an important factor influencing surgical strategy and complication rates. Standard tools, such as clinical parameters, risk calculators, and multiparametric MRI, help estimate this risk; however, their accuracy is limited and varies between observers. New artificial intelligence techniques are increasingly being explored to improve preoperative detection. Radiomics and deep-learning models can analyze subtle imaging patterns that are often invisible to the human eye and may support more personalized clinical decisions. This review provides a contemporary overview of current and emerging methods for detecting extraprostatic extension and discusses future directions of prostate cancer management.

Extraprostatic extension (EPE) is an important prognostic factor in prostate cancer and influences nerve-sparing decisions during radical prostatectomy. Multiparametric MRI (mpMRI) is the standard for local staging, but its sensitivity for EPE remains limited, and its interpretation is subject to inter-reader variability. In this narrative review, we aim to create an overview of contemporary strategies for the preoperative detection of EPE. We searched PubMed, Embase, Web of Science, and Google Scholar, focusing on studies published between 2015 and 2025 including articles evaluating clinical parameters, mpMRI features, nomograms, radiomics, machine learning, and deep learning models for EPE prediction. The analyzed literature was compared with respect to diagnostic performance, validation strategy, and clinical applicability of individual methods. Clinical parameters and traditional nomograms provide moderate accuracy for EPE detection. mpMRI improves staging, with tumor–capsule contact length as the most important single imaging marker. Radiomics-based and machine-learning models matched and occasionally outperform conventional approaches, achieving AUC values ranging from 0.75 to 0.85. Deep-learning models demonstrated similar performance by directly analyzing imaging data, although most lacked external validation and were sensitive to dataset heterogeneity. Several radiomics and deep learning models demonstrated performance comparable to, and in selected studies exceeding, expert radiologist assessment. Binary EPE classification has limited clinical value, while side-specific and graded EPE assessment offers a more clinically relevant approach. Translation of these tools into routine practice will require multimodal, side-specific, and externally validated models supported by automated segmentation and explainable artificial intelligence frameworks.