Incorporating label uncertainty during the training of convolutional neural networks improves performance for the discrimination between certain and inconclusive cases in dopamine transporter SPECT
Making between-readers-discrepancy known to CNN during the training improves the utility of their sigmoid output to discriminate certain from inconclusive cases that might be misclassified by the CNN when the predefined decision threshold is strictly applied. This does not compromise on overall accuracy.
Authors
- Christian Ledig (ORCID: https://orcid.org/0000-0003-4862-3138)
- Ivayla Apostolova (ORCID: https://orcid.org/0000-0003-0290-7186)
- Susanne Klutmann
- Ralph Buchert (ORCID: https://orcid.org/0000-0002-0945-0724)
- Thomas Buddenkotte (ORCID: https://orcid.org/0000-0003-4872-4246)
- Aleksej Kucerenko
Institutions
- Universität Hamburg (DE)
- University Medical Center Hamburg-Eppendorf (DE)
- University of Bamberg (DE)
Publication Details
- Journal
- European Journal of Nuclear Medicine and Molecular Imaging
- Published
- 2024-11-27
- DOI
- https://doi.org/10.1007/s00259-024-06988-0
- Citations
- 1
- Primary Topic
- Machine Learning and Data Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.35