AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study

Nikita Sushentsev; Zobair Arya; Jobie Budd; Amy Frary; Nadia Moreira  da Silva; Mirjana Ferrer Rodriguez; Paul Burn; Richard Hindley; Nikhil Vasdev; Mohamed Ibrahim; Alison Bradley; Adrian Andreou; Sidath Liyanage; Raj Persad; Jonathan Aning; Alexander B C D Ng; Aqua Asif; Veeru Kasivisvanathan; Tristan Barrett; Mark Hinton; Anwar Roshanali Padhani; Aarti Shah; Lucy Davies; Antony Rix; Evis Sala

doi:10.1007/s00330-026-12361-6

AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study

Nikita Sushentsev
, Zobair Arya
, Jobie Budd
, Amy Frary
, Nadia Moreira da Silva
, Mirjana Ferrer Rodriguez
, Paul Burn
, Richard Hindley
, Nikhil Vasdev
, Mohamed Ibrahim
, Alison Bradley
, Adrian Andreou
, Sidath Liyanage
, Raj Persad
, Jonathan Aning
, Alexander B C D Ng
, Aqua Asif
, Veeru Kasivisvanathan
, Tristan Barrett
, Mark Hinton

Anwar Roshanali Padhani, Aarti Shah, Lucy Davies, Antony Rix, Evis Sala

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

1 Downloads (Pure)

Abstract

Objectives To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios.
Materials and methods This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores
was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard.
Results In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31%) harboured ≥ GG2 disease. Compared to the reference standard, the AI-DSS at the 31% cancer detection rate (CDR) would have avoided 28 biopsies while missing one ≥ GG2 cancer. This corresponded to a 70% increase in grade selectivity (from 4.6 to 7.8), 79% increase in biopsy efficiency (from 1.4 to 2.5), and a 143% increase in selective biopsy
avoidance (from 2.8 to 6.8). At the reduced CDR of 30%, grade selectivity, biopsy efficiency, and selective biopsy avoidance increased by 172%, 236%, and 475%, with four ≥ GG2 cancers missed.
Conclusion An AI-DSS that integrates clinical and advanced imaging data improves the benefit-to-harm ratio of
prostate biopsy decisions in a retrospective setting. Future prospective validation as part of real-world clinical workflow
is required to enable clinical implementation.
Key Points
Question Current prostate cancer diagnostic pathways result in fewer unnecessary biopsies. Can an AI decision support
system (AI-DSS) further improve biopsy efficiency for detecting significant cancer?

Original language	English
Number of pages	9
Journal	European Radiology
Early online date	20 Feb 2026
DOIs	https://doi.org/10.1007/s00330-026-12361-6
Publication status	E-pub ahead of print - 20 Feb 2026

Access to Document

10.1007/s00330-026-12361-6Licence: CC BY

Final_versionFinal published version, 3.64 MBLicence: CC BY

Cite this

Sushentsev, N., Arya, Z., Budd, J., Frary, A., da Silva, N. M., Rodriguez, M. F., Burn, P., Hindley, R., Vasdev, N., Ibrahim, M., Bradley, A., Andreou, A., Liyanage, S., Persad, R., Aning, J., Ng, A. B. C. D., Asif, A., Kasivisvanathan, V., Barrett, T., ... Sala, E. (2026). AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study. European Radiology. Advance online publication. https://doi.org/10.1007/s00330-026-12361-6

@article{cff0b9db0137418f898e78c07ceeea75,

title = "AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study",

abstract = "Objectives To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios. Materials and methods This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard. Results In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31\%) harboured ≥ GG2 disease. Compared to the reference standard, the AI-DSS at the 31\% cancer detection rate (CDR) would have avoided 28 biopsies while missing one ≥ GG2 cancer. This corresponded to a 70\% increase in grade selectivity (from 4.6 to 7.8), 79\% increase in biopsy efficiency (from 1.4 to 2.5), and a 143\% increase in selective biopsy avoidance (from 2.8 to 6.8). At the reduced CDR of 30\%, grade selectivity, biopsy efficiency, and selective biopsy avoidance increased by 172\%, 236\%, and 475\%, with four ≥ GG2 cancers missed. Conclusion An AI-DSS that integrates clinical and advanced imaging data improves the benefit-to-harm ratio of prostate biopsy decisions in a retrospective setting. Future prospective validation as part of real-world clinical workflow is required to enable clinical implementation. Key Points Question Current prostate cancer diagnostic pathways result in fewer unnecessary biopsies. Can an AI decision support system (AI-DSS) further improve biopsy efficiency for detecting significant cancer?",

author = "Nikita Sushentsev and Zobair Arya and Jobie Budd and Amy Frary and \{da Silva\}, \{Nadia Moreira\} and Rodriguez, \{Mirjana Ferrer\} and Paul Burn and Richard Hindley and Nikhil Vasdev and Mohamed Ibrahim and Alison Bradley and Adrian Andreou and Sidath Liyanage and Raj Persad and Jonathan Aning and Ng, \{Alexander B C D\} and Aqua Asif and Veeru Kasivisvanathan and Tristan Barrett and Mark Hinton and Padhani, \{Anwar Roshanali\} and Aarti Shah and Lucy Davies and Antony Rix and Evis Sala",

note = "{\textcopyright} The Author(s) 2026. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.",

year = "2026",

month = feb,

day = "20",

doi = "10.1007/s00330-026-12361-6",

language = "English",

journal = "European Radiology",

issn = "0938-7994",

publisher = "Springer Nature ",

}

Sushentsev, N, Arya, Z, Budd, J, Frary, A, da Silva, NM, Rodriguez, MF, Burn, P, Hindley, R, Vasdev, N, Ibrahim, M, Bradley, A, Andreou, A, Liyanage, S, Persad, R, Aning, J, Ng, ABCD, Asif, A, Kasivisvanathan, V, Barrett, T, Hinton, M, Padhani, AR, Shah, A, Davies, L, Rix, A & Sala, E 2026, 'AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study', European Radiology. https://doi.org/10.1007/s00330-026-12361-6

TY - JOUR

T1 - AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study

AU - Sushentsev, Nikita

AU - Arya, Zobair

AU - Budd, Jobie

AU - Frary, Amy

AU - da Silva, Nadia Moreira

AU - Rodriguez, Mirjana Ferrer

AU - Burn, Paul

AU - Hindley, Richard

AU - Vasdev, Nikhil

AU - Ibrahim, Mohamed

AU - Bradley, Alison

AU - Andreou, Adrian

AU - Liyanage, Sidath

AU - Persad, Raj

AU - Aning, Jonathan

AU - Ng, Alexander B C D

AU - Asif, Aqua

AU - Kasivisvanathan, Veeru

AU - Barrett, Tristan

AU - Hinton, Mark

AU - Padhani, Anwar Roshanali

AU - Shah, Aarti

AU - Davies, Lucy

AU - Rix, Antony

AU - Sala, Evis

N1 - © The Author(s) 2026. Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.

PY - 2026/2/20

Y1 - 2026/2/20

N2 - Objectives To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios. Materials and methods This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard. Results In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31%) harboured ≥ GG2 disease. Compared to the reference standard, the AI-DSS at the 31% cancer detection rate (CDR) would have avoided 28 biopsies while missing one ≥ GG2 cancer. This corresponded to a 70% increase in grade selectivity (from 4.6 to 7.8), 79% increase in biopsy efficiency (from 1.4 to 2.5), and a 143% increase in selective biopsy avoidance (from 2.8 to 6.8). At the reduced CDR of 30%, grade selectivity, biopsy efficiency, and selective biopsy avoidance increased by 172%, 236%, and 475%, with four ≥ GG2 cancers missed. Conclusion An AI-DSS that integrates clinical and advanced imaging data improves the benefit-to-harm ratio of prostate biopsy decisions in a retrospective setting. Future prospective validation as part of real-world clinical workflow is required to enable clinical implementation. Key Points Question Current prostate cancer diagnostic pathways result in fewer unnecessary biopsies. Can an AI decision support system (AI-DSS) further improve biopsy efficiency for detecting significant cancer?

AB - Objectives To develop and retrospectively validate an artificial intelligence-based decision support system (AI-DSS) for optimising prostate biopsy decisions and improving benefit-to-harm ratios. Materials and methods This retrospective, multicentre, multiscanner study used data from 1022 patients. An AI-DSS integrating PI-RADS scores, automated prostate-specific antigen density (PSAd), and deep-learning imaging risk scores was developed on 770 cases and validated on an independent cohort of 252 men from six UK centres. The AI-DSS performance was benchmarked against the real-world clinical decisions (reference standard) using grade selectivity, biopsy efficiency, and selective biopsy avoidance as outcome measures. Biopsy-proven detection of grade group (GG) ≥ 2 disease was the reference standard. Results In the validation cohort of 252 patients (mean age, 67.3 years), 137 underwent biopsy and 79 (31%) harboured ≥ GG2 disease. Compared to the reference standard, the AI-DSS at the 31% cancer detection rate (CDR) would have avoided 28 biopsies while missing one ≥ GG2 cancer. This corresponded to a 70% increase in grade selectivity (from 4.6 to 7.8), 79% increase in biopsy efficiency (from 1.4 to 2.5), and a 143% increase in selective biopsy avoidance (from 2.8 to 6.8). At the reduced CDR of 30%, grade selectivity, biopsy efficiency, and selective biopsy avoidance increased by 172%, 236%, and 475%, with four ≥ GG2 cancers missed. Conclusion An AI-DSS that integrates clinical and advanced imaging data improves the benefit-to-harm ratio of prostate biopsy decisions in a retrospective setting. Future prospective validation as part of real-world clinical workflow is required to enable clinical implementation. Key Points Question Current prostate cancer diagnostic pathways result in fewer unnecessary biopsies. Can an AI decision support system (AI-DSS) further improve biopsy efficiency for detecting significant cancer?

U2 - 10.1007/s00330-026-12361-6

DO - 10.1007/s00330-026-12361-6

M3 - Article

SN - 0938-7994

JO - European Radiology

JF - European Radiology

ER -

AI decision support for increasing prostate biopsy efficiency: a retrospective multicentre, multiscanner study

Abstract

Access to Document

Fingerprint

Cite this