Pi ™ – Applied Artificial Intelligence for diagnosing prostate cancer from MRI
The figure above illustrates the RTSTRUCT format segmentations output by the software. The segmentations are overlaid, on a 3D multi-planar reconstruction of the T2 axial image, together with the 3D mesh view.
Colours shown are:
• Red: index lesion
• Blue: prostate organ
• Grey: seminal vesicles
Smaller lesions are also visible, with the smallest indicated by the software using labels (e.g. Lesion 5-1).
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).
Pi is intended to augment a radiologist’s interpretation of prostate MRI in three ways
- Improve patient selection for biopsy
This is achieved by outputting a risk score aiming for both high negative predictive value (NPV) and specificity, to reduce unnecessary biopsies and overdiagnosis of insignificant cancers
- 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 with high DICE score compared to human expert annotations, to support 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
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.