The ReIMAGINE consortium – establishing an infrastructure for the external validation of prostate MRI lesion classification models
Motivation: Multiparametric MRI is highly sensitive for identifying clinically significant prostate cancer (csPCa), but has a poorer specificity, meaning many men undergo unnecessary prostate biopsies. Goal(s): To evaluate whether artificial intelligence (AI) could improve the diagnostic accuracy of MRI compared to current clinical methods, including Likert score and PSA density (PSAd). Approach: We carried out independent evaluation of a prostate MRI lesion classifier model using a large multisite and multivendor prostate MRI dataset (1,039 patients). Results: The AI model matched the sensitivity and specificity of Likert score plus PSAd cut-offs on data similar to the training set, but did not generalise to other data. Impact: An infrastructure has been successfully established to allow robust and independent evaluation of prostate MRI lesion classification models to accelerate the development of such tools and to ensure adequate testing pre-deployment.
Authors
- Chris Brew‐Graves (ORCID: https://orcid.org/0000-0002-0266-0315)
- Simon Rodney
- Aida Santaolalla
- Rosemary Clow
- Jimmy Antunes (ORCID: https://orcid.org/0009-0008-7232-0464)
- Yipeng Hu (ORCID: https://orcid.org/0000-0003-4902-0486)
- Zhe Min (ORCID: https://orcid.org/0000-0002-8903-1561)
- Mrishta Brizmohun Appayya (ORCID: https://orcid.org/0000-0003-1173-4846)
- Giorgio Brembilla (ORCID: https://orcid.org/0000-0002-9690-8624)
- Teresa Marsden (ORCID: https://orcid.org/0000-0002-1800-3547)
- Paul Jacobs
- David Atkinson (ORCID: https://orcid.org/0000-0002-9956-2454)
- Tom Syer (ORCID: https://orcid.org/0000-0001-9594-9638)
- Mark Emberton (ORCID: https://orcid.org/0000-0003-4230-0338)
- Susan Mallett (ORCID: https://orcid.org/0000-0002-0596-8200)
- Natasha Thorley
- Thomas Parry
- Jonathan Piper
- Hashim U. Ahmed
- Shonit Punwani
- Swetha Srikanthan
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/3504
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00