EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Artificial Intelligence in Prostate MRI: Comparison of an AI-Based Software and an Experienced Radiologist for Detecting Clinically Significant Prostate Cancer

Roberto Castellana, Simona Marzi iD, Andrea Russo, Maria Consiglia Ferriero, Irene Terrenato iD, Eugenia Papaleo, Giuseppe Navanteri, Davide Vitale, Giuseppe Pizzi, Antonello Vidiri iD, Luca Bertini

Current Oncology · 06.03.2026 · 33 (3) · 151

DOI: 10.3390/curroncol33030151 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Current Oncology, online erschienen am 06.03.2026. Verfasst von Roberto Castellana und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Artificial Intelligence, Magnetic Resonance Imaging, Software. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Multiparametric MRI is central to detecting clinically significant prostate cancer (csPCa), but diagnostic accuracy depends on reader experience. Artificial intelligence (AI) tools may support prostate MRI interpretation and reduce inter-reader variability. This study compared the detection rate of a trial, non-commercial version an AI-based software (PAROS) with that of an experienced radiologist.

Methods

This retrospective single-center study included 150 patients who underwent prostate MRI followed by combined systematic and MRI-targeted transperineal biopsy. MRI examinations were interpreted by an experienced radiologist according to PI-RADS v2.1 and independently analyzed using a precommercial trial version of PAROS operating on biparametric MRI. Histopathology served as the reference standard. Detection rate was evaluated using sensitivity, specificity, and positive and negative likelihood ratios (PLR and NLR) at PI-RADS thresholds ≥3 and ≥4.

Results

CsPCa was present in 63.3% of patients. At both PI-RADS thresholds, PAROS and the radiologist showed comparable sensitivity and specificity, wuth extremely low NLRs, indicating excellent rule-out capability. PLRs were modest and similar at PI-RADS ≥ 3 (1.26 vs. 1.42) and 1.88 for both at PI-RADS ≥ 4. PAROS detected more lesions, particularly in the transition zone.

Conclusions

PAROS achieved csPCa detection comparable to an experienced radiologist, supporting its role as a decision-support tool in prostate MRI interpretation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsArtificial IntelligenceMagnetic Resonance ImagingSoftwareHumansMaleRetrospective StudiesAgedRadiologistsMiddle AgedSensitivity and Specificity

Stichwörter der Autor:innen

AIMRIartificial intelligenceprostate cancer

Autor:innen und Institutionen

  • Department of Radiology, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.
  • Medical Physics Laboratory, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.
  • Department of Pathology, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.
  • Department of Urology, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.
  • Biostatistics-Scientific Direction, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.
  • Clinical Engineering and Technology and Informatic Systems, IRCCS Regina Elena National Cancer Institute, Via Elio Chianesi 53, 00144 Rome, Italy.

ORCID-Profile: Simona Marzi, Irene Terrenato, Antonello Vidiri

Zitieren

APA

Castellana, R., Marzi, S., Russo, A., Ferriero, M. C., Terrenato, I., Papaleo, E., Navanteri, G., Vitale, D., Pizzi, G., Vidiri, A., & Bertini, L. (2026). Artificial Intelligence in Prostate MRI: Comparison of an AI-Based Software and an Experienced Radiologist for Detecting Clinically Significant Prostate Cancer. Current Oncology, 33(3), 151. https://doi.org/10.3390/curroncol33030151

Vancouver

Castellana R, Marzi S, Russo A, Ferriero MC, Terrenato I, Papaleo E, et al. Artificial Intelligence in Prostate MRI: Comparison of an AI-Based Software and an Experienced Radiologist for Detecting Clinically Significant Prostate Cancer. Current Oncology. 2026;33(3):151. doi:10.3390/curroncol33030151

BibTeX
@article{Castellana2026,
  author = {Castellana, Roberto and Marzi, Simona and Russo, Andrea and Ferriero, Maria Consiglia and Terrenato, Irene and Papaleo, Eugenia and Navanteri, Giuseppe and Vitale, Davide and Pizzi, Giuseppe and Vidiri, Antonello and Bertini, Luca},
  title = {Artificial Intelligence in Prostate MRI: Comparison of an AI-Based Software and an Experienced Radiologist for Detecting Clinically Significant Prostate Cancer},
  journal = {Current Oncology},
  year = {2026},
  volume = {33},
  number = {3},
  pages = {151},
  doi = {10.3390/curroncol33030151}
}
Kostenlos starten →