Pi ™ – Applied Artificial Intelligence for diagnosing prostate cancer from MRI
Example outputs from Pi for a patient with biopsy-verified Gleason Grade Group 4 & 5 cancer at the highlighted locations.
Top row left to right
- T2 axial series overlaid with editable AI-generated RTSTRUCT segmentations of prostate and lesions
- AI prostate segmentation and volume as DICOM-SC overlaid to T2 axial
- AI lesion identification and risk scores as DICOM-SC overlaid to T2 axial
Bottom row left to right: axial ADC, DWI and DCE images.
Images from Litjens G et al, The Cancer Imaging Archive (2017). DOI: 10.7937/K9TCIA.2017.MURS5CL.
Publications
Sushentsev, N. et al. Comparative performance of fully-automated and semi-automated artificial intelligence methods for the detection of clinically significant prostate cancer on MRI: a systematic review. Insights into Imaging, 2022 13:59, https://doi.org/10.1186/s13244-022-01199-3
Conference presentations and posters
Accepted/upcoming
Shah, A. et al. Multiple centre external validation of an AI solution for prostate cancer diagnostic imaging. RSNA 2023, 26 November (oral presentation)
Rix, A. et al. Integrating clinical data with AI to optimise decision-making in prostate MRI. RSNA 2023, 26-30 November (poster presentation)
2023
Shah, A. et al. AI for prostate MRI: results from a large multi-centre, multi-vendor external validation study. ICIS 2023, 25-27 September (poster)
Rix, A. et al. Integrating clinical data with AI to optimise biopsy decisions after prostate MRI. ICIS 2023, 25-27 September (poster)
Shah, A. et al. AI for prostate MRI: results from a large multi-centre, multi-vendor external validation study. ESUR 2023, 21-24 September (oral presentation)
Ward, P. et al. The use of an AI software tool for prostate volume measurement on MRI. ESUR 2023, 21-24 September (poster), https://www.esur2023.com/the-use-of-an-ai-software-tool-for-prostate-volume-measurement-on-mri/
Ward, P. et al. To determine the ability of an AI software tool to detect significant prostate cancer on MRI, ESUR 2023, 21-24 September (poster), https://www.esur2023.com/to-determine-the-ability-of-an-ai-software-tool-to-detect-significant-prostate-cancer-on-mri/
Rix, A. et al. Integrating clinical data with AI to optimise biopsy decisions after prostate MRI. ESUR 2023, 21-24 September (poster), https://www.esur2023.com/integrating-clinical-data-with-ai-to-optimise-biopsy-decisions-after-prostate-mri/
Shah, A. et al. AI for prostate MRI: results from a large multi-centre, multi-vendor external validation study. BSUR 2023, 15 September (oral presentation)
Rix, A. et al. Integrating clinical data with AI to optimise biopsy decisions after prostate MRI. BSUR 2023, 14-15 September (poster presentation)
Shah, A. et al. Assessing the potential of artificial intelligence for prostate MRI in a diverse multi-centre diagnostic population. BAUS 2023, P8-3, https://www.baus.org.uk/_userfiles/pages/files/agm/2023-abstracts-book-2023.pdf
Shah, A. et al. Assessing the potential of artificial intelligence for prostate MRI in a diverse multi-centre diagnostic population. EAU 2023
Shah, A. et al. Can AI for prostate MRI generalise to multiple centres and scanners? ECR 2023, https://connect.myesr.org/course/new-frontiers-for-ai-in-prostate-mri/
2022
Shah, A. et al. Generalisation of AI analysis for prostate cancer diagnostic imaging to multiple centres and scanners. RSNA 2022, https://dps2022.rsna.org/exhibit/?exhibit=T2-SPIN-6, https://archive.rsna.org/2022/46570000.html
Colombo, A. et al. Intelligenza Artificiale Per Indentificare Lesioni Multi-Organo in Immagini RM Whole-Body, SIRM Annual Congress 2022, https://areasoci.sirm.org/congressi/1163/info-sessione/5025
2021
Suchánek, J. et al. Multi-stage Artificial Intelligence analysis system to support prostate cancer diagnostic imaging, EMJ Radiol. 2021;2[1]:28-30. Abstract Review No: AR3, https://www.emjreviews.com/wp-content/uploads/2021/04/EMJ-Radiology-2.1-2021.pdf
Suchánek, J. et al. Multi-stage Artificial Intelligence analysis system to support prostate cancer diagnostic imaging, ECR 2021, https://connect.myesr.org/course/artificial-intelligence-ai-in-unmet-clinical-needs/
2020
Suchánek, J. et al. Multi-stage AI analysis system to support prostate cancer diagnostic imaging, EuSoMII Virtual Annual Meeting, 24 October 2020, https://doi.org/10.26226/morressier.5f7f3e3d6934880e60c0a8b1
What is Pi ™?
Pi™, Prostate Intelligence™, is an AI and machine learning based software system designed to help radiologists detect and report the presence of prostate cancer lesions from MR scans (MRI).
We designed Pi to augment a radiologist’s interpretation of prostate MRI in three ways:
- Improve patient selection/prioritisation for biopsy
This is achieved by outputting a risk score aiming for both high negative predictive value (NPV) and specificity. Depending on clinical priorities, this could be used to reduce unnecessary biopsies and overdiagnosis of insignificant cancers, streamline workflow or waiting lists, or help reduce radiologists workload
- Improve identification of targets for biopsy
This involves identifying candidate regions of interest with high NPV, to help ensure that all areas of suspicion are targeted for biopsy and help reduce underdiagnosis (missed clinically significant cancers)
- Provide high quality segmentations
Outputting machine generated segmentations that compare well to human expert annotations, to support visualisation, analysis and biopsy targeting
Please note that Pi does not make a direct diagnosis and is only available in selected countries. Contact Lucida Medical for further details. The software is not for sale in the US.
To learn more, you can access a video and paper from EuSoMII Virtual Annual Meeting, 24 October 2020 and a published research paper by clicking the links below, or view our more recent publications/presentations linked to the left/above.
Our Partners
We collaborate with Cambridge University, we are a partner in the ReIMAGINE prostate imaging trial, are in the process of establishing collaborative partnerships with several UK NHS Trust hospitals to help further develop and validate and test Pi, our AI system for detecting prostate cancer from MRI.