Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation

Marius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, Alvaro Fernandez-Quilez · 2024

Read Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation by Marius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, Alvaro Fernandez-Quilez (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11607187.txt.

Description

Marius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, and Alvaro Fernandez-Quilez add an uncertainty flag to deep learning prostate sizing on MRI, in a study from two thousand twenty-four. The data held three hundred seventy-seven scans of men at risk for prostate cancer. A conformal method marked pixels the model could not trust at a set confidence level.

Dropping flagged pixels cut the average volume error sharply versus plain model output. Agreement with the standard formula volume rose to a near-perfect match class. The flagged volume also centered far closer to truth. The authors frame the flag as a safety gain for scan-based sizing. Readers get a trust check for automated prostate measures.

Catalog record

CREATORMarius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, Alvaro Fernandez-Quilez
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE33 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11607187

Browse the full library · About the Tower of Babel