Beyond diagnosis: is there a role for radiomics in prostate cancer management?

Abstract

The role of imaging in pretreatment staging and management of prostate cancer (PCa) is constantly evolving. In the last decade, there has been an ever-growing interest in radiomics as an image analysis approach able to extract objective quantitative features that are missed by human eye. However, most of PCa radiomics studies have been focused on cancer detection and characterisation. With this narrative review we aimed to provide a synopsis of the recently proposed potential applications of radiomics for PCa with a management-based approach, focusing on primary treatments with curative intent and active surveillance as well as highlighting on recurrent disease after primary treatment. Current evidence is encouraging, with radiomics and artificial intelligence appearing as feasible tools to aid physicians in planning PCa management. However, the lack of external independent datasets for validation and prospectively designed studies casts a shadow on the reliability and generalisability of radiomics models, delaying their translation into clinical practice.Key points• Artificial intelligence solutions have been proposed to streamline prostate cancer radiotherapy planning.• Radiomics models could improve risk assessment for radical prostatectomy patient selection.• Delta-radiomics appears promising for the management of patients under active surveillance.• Radiomics might outperform current nomograms for prostate cancer recurrence risk assessment.• Reproducibility of results, methodological and ethical issues must still be faced before clinical implementation.

Keywords: Artificial intelligence; Clinical decision-making; Prostatic neoplasms; Radiomics; Reproducibility of results.

Fig. 1

Graphic representation of radiomics and artificial intelligence main applications in the setting of prostate cancer management

Fig. 2

Sixty-nine-years old patient treated with external beam radiotherapy after MRI targeted biopsy revealed 3+4 Gleason score prostate cancer. Images from pre-biopsy (a−c) as well as post-treatment (d−f) MRI scans are presented. The index lesion (PI-RADS 5) can be appreciated on the T2-weighted images (a, lesion epicentre marked with a white star) as a homogeneous, moderately hypointense area with obscured margins in the right anterior transition zone. Corresponding marked and focal hypointensity on ADC map (b, red region of interest) and hyperintensity on high b value DWI (c, white arrow) are present. On the corresponding post-treatment sequences (d−f), no abnormalities can be detected, suggesting a good treatment response. DWI Diffusion-weighted imaging, MRI Magnetic resonance imaging, PI-RADS Prostate Imaging-Reporting and Data System

Fig. 3

Prebiopsy MRI scan of a 58-year-old patient (PSA value of 6.12 ng/mL at the time of imaging) showing a PI-RADS 4 lesion in the posterior-lateral peripheral zone (right lobe) appearing hypointense on T2-weighted images (a) and exhibiting markedly restricted diffusion (b, high b value DWI; c, ADC map with red region of interest). Target biopsy confirmed the presence of prostatic adenocarcinoma (Gleason score 3 + 4). While a moderate capsule-tumour contact length can be appreciated on the T2-weighted images (a, white arrow), no bulging nor definitive signs of extracapsular extension are present and the radiologist staged the disease as locally confined. Based on the MRI report and considering the young age, the patient underwent nerve-sparing radical prostatectomy. Unfortunately, the pathology report on the surgical specimen revealed the presence of extracapsular disease extension and upgraded the Gleason score to 4 + 4. ADC Apparent diffusion coefficient, DWI Diffusion-weighted imaging, MRI Magnetic resonance imaging, PI-RADS Prostate Imaging-Reporting and Data System, PSA Prostate-specific antigen

Fig. 4

Seventy-two-year-old patient who underwent radical prostatectomy for prostate cancer (at pathology, Gleason score 3 + 4). Staging MRI shows a large peripheral zone (left posteromedial) lesion with intermediate signal on T2-weighted images (a, lesion epicentre marked with white star), focal and marked hypointensity on the ADC map (b, red region of interest) and corresponding hyperintensity on high b value DWI (c, white arrowhead). Three years after treatment, rise of PSA value determines biochemical recurrence. [⁶⁸Ga]Ga-PSMA-11 PET/CT (d and e) shows a small but concerning right external iliac lymph node. ADC Apparent diffusion coefficient, DWI Diffusion-weighted imaging, MRI Magnetic resonance imaging, PET/TC Positron emission tomography/computed tomography, PMSA Prostate-specific membrane antigen, PSA Prostate-specific antigen