Impact of uncertainty quantification through conformal prediction on volume assessment from deep learning-based MRI prostate segmentation
Conformal prediction can flag uncertain pixel predictions of prostate segmentations at a user-defined confidence level. Deep learning with conformal prediction shows high accuracy in prostate volumetric assessment. Agreement between automatic and ellipsoid-derived volume was significantly larger with conformal prediction.
Authors
- Álvaro Fernández-Quilez (ORCID: https://orcid.org/0000-0001-7544-0797)
- Marie Gade
- Kevin Mekhaphan Nguyen (ORCID: https://orcid.org/0000-0003-2118-5377)
- Sol Gedde
Institutions
- Stavanger University Hospital (NO)
- University of Stavanger (NO)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2024-11-29
- DOI
- https://doi.org/10.1186/s13244-024-01863-w
- Citations
- 6
- Primary Topic
- Prostate Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.51
Funders
- Universitetet i Stavanger
- Stavanger Universitetssjukehus