Metraipolis › archive › dc_ec50ebda93b1
Leveraging deep learning to infer continuous predictions from ordinal labels in medical imaging — Europe PMC PMID:41996486
- Source
- Europe PMC (en)
- Original
- https://europepmc.org/article/MED/41996486
- DOI
- 10.1371/journal.pdig.0001248
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T07:52:26.124Z
- SHA-256 of the archived text
efc826eae1e99c4d249ff340396c534ed9b38f443a39e7f5c27ab1852cc4b786- Stable URL of this page
https://metraipolis.com/documento/dc_ec50ebda93b1
How to cite
Leveraging deep learning to infer continuous predictions from ordinal labels in medical imaging — Europe PMC PMID:41996486 — Europe PMC (en), https://europepmc.org/article/MED/41996486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec50ebda93b1 (Metraipolis archive dc_ec50ebda93b1, sha256 efc826eae1e99c4d249ff340396c534ed9b38f443a39e7f5c27ab1852cc4b786)
BibTeX
@misc{dcec50ebda93b1,
title = {Leveraging deep learning to infer continuous predictions from ordinal labels in medical imaging — Europe PMC PMID:41996486},
howpublished = {Europe PMC (en)},
url = {https://europepmc.org/article/MED/41996486},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec50ebda93b1; sha256 efc826eae1e99c4d249ff340396c534ed9b38f443a39e7f5c27ab1852cc4b786},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/41996486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
In clinical medicine, variables like disease severity are often categorized into discrete ordinal labels such as normal/mild/moderate/severe. However, these labels, commonly used to train and evaluate disease severity prediction models, simplify an underlying continuous severity spectrum. Using continuous scores can aid in detecting small severity changes more sensitively over time. We introduce a deep learning based approach that predicts continuously valued variables from medical images using only discrete ordinal labels during model development. We evaluated this approach using three medical imaging datasets: disease severity prediction for retinopathy of prematurity and knee osteoarthritis, and breast density prediction from mammograms. Deep learning models were trained with discrete labels, and model outputs were transformed into continuous scores. These were then compared against detailed expert severity assessments, which exceeded the granularity of training labels. Our study explored conventional and Monte Carlo dropout multi-class classification, ordinal classification, regression, and twin models. We found that models incorporating the ordinal nature of training labels significantly outperformed conventional multi-class classification. Notably, continuous scores from ordinal classification and regression models demonstrated a higher correlation with expert severity rankings and lower mean squared errors than multi-class models. The application of Monte Carlo dropout further enhanced the prediction accuracy of continuously valued scores, aligning closely with the continuous target variable. Our findings confirm that accurate continuous scores can be learned from discrete ordinal labels using deep learning, offering a robust method that effectively bridges the gap between discrete and continuous data across various image analysis tasks. Tema degli esploratori: finanziamenti e grant (ricerca Europe PMC «research funding», solo open access). Pubblicazione: PLOS digital health, 2026 (prima pubblicazione 2026-04-17). Identificativi: PMID 41996486 · PMCID PMC13089899 · DOI 10.1371/journal.pdig.0001248. Pagina: https://europepmc.org/article/MED/41996486 — https://doi.org/10.1371/journal.pdig.0001248. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0. Letto il 2026-10-06T07:47:41.320Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.