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
| CREATOR | Marius Gade, Kevin Mekhaphan Nguyen, Sol Gedde, Alvaro Fernandez-Quilez |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |