Lucida launches validation study for AI software

By AuntMinnieEurope.com staff writers

September 7, 2021 -- Researchers from U.K. artificial intelligence (AI) software developer Lucida Medical and Hampshire Hospitals NHS Foundation Trust have launched a retrospective cohort validation study of the firm's Pi AI-based software for prostate cancer detection on MRI.

The study will include deidentified data from 2,100 patients who have been diagnosed with prostate cancer. The researchers will collaborate to check the performance of the software and, if necessary, calibrate its settings, validate its expected performance, and test it, Lucida said.

The figure above illustrates the RTSTRUCT format segmentations output by the software
The figure above illustrates the RTSTRUCT format segmentations output by the software. The segmentations are overlaid on a 3D multiplanar reconstruction of the T2 axial image, together with the 3D mesh view.

Colors shown are as follows:

  • Red: index lesion
  • Blue: prostate organ
  • Gray: seminal vesicles

Smaller lesions are also visible, with the smallest indicated by the software using labels (e.g., Lesion 5-1). Image courtesy of Lucida Medical.

A little over half of the data will be utilized to ensure that the software works well across the range of scanners and scanning protocols utilized in different hospitals. This data will be used to check that the software is correctly calibrated and to change settings if needed, according to the vendor. The AI software will then be tested on the rest of the data to assess its performance on MRI exams it hasn't seen yet.

The company said it will publish the data from the study once it's completed.


Copyright © 2021 AuntMinnieEurope.com
 

To read this and get access to all of the exclusive content on AuntMinnieEurope.com create a free account or sign-in now.

Member Sign In:
MemberID or Email Address:  
Do you have a AuntMinnieEurope.com password?
No, I want a free membership.
Yes, I have a password:  
Forgot your password?
Sign in using your social networking account:
Sign in using your social networking
account: