Metraipolis › archive › dc_1868e8707aed

Harnessing clinical annotations to improve deep learning performance in prostate segmentation — Europe PMC PMID:34170972

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/34170972
DOI
10.1371/journal.pone.0253829
License (as archived)
CC0-1.0
Archived
2026-11-03T22:18:46.884Z
SHA-256 of the archived text
b5f9d972cf43e54a6c679561a6ca9778d34db8a15d097fbcd2d989d45ff604d1
Stable URL of this page
https://metraipolis.com/documento/dc_1868e8707aed

How to cite

Harnessing clinical annotations to improve deep learning performance in prostate segmentation — Europe PMC PMID:34170972 — Europe PMC (en), https://europepmc.org/article/MED/34170972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1868e8707aed (Metraipolis archive dc_1868e8707aed, sha256 b5f9d972cf43e54a6c679561a6ca9778d34db8a15d097fbcd2d989d45ff604d1)
BibTeX
@misc{dc1868e8707aed,
  title = {Harnessing clinical annotations to improve deep learning performance in prostate segmentation — Europe PMC PMID:34170972},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/34170972},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1868e8707aed; sha256 b5f9d972cf43e54a6c679561a6ca9778d34db8a15d097fbcd2d989d45ff604d1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/34170972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Purpose: Developing large-scale datasets with research-quality annotations is challenging due to the high cost of refining clinically generated markup into high precision annotations. We evaluated the direct use of a large dataset with only clinically generated annotations in development of high-performance segmentation models for small research-quality challenge datasets. Materials and methods: We used a large retrospective dataset from our institution comprised of 1,620 clinically generated segmentations, and two challenge datasets (PROMISE12: 50 patients, ProstateX-2: 99 patients). We trained a 3D U-Net convolutional neural network (CNN) segmentation model using our entire dataset, and used that model as a template to train models on the challenge datasets. We also trained versions of the template model using ablated proportions of our dataset, and evaluated the relative benefit of those templates for the final models. Finally, we trained a version of the template model using an out-of-domain brain cancer dataset, and evaluated the relevant benefit of that template for the final models. We used five-fold cross-validation (CV) for all training and evaluation across our entire dataset. Results: Our model achieves state-of-the-art performance on our large dataset (mean overall Dice 0.916, average Hausdorff distance 0.135 across CV folds). Using this model as a pre-trained template for refining on two external datasets significantly enhanced performance (30% and 49% enhancement in Dice scores respectively). Mean overall Dice and mean average Hausdorff distance were 0.912 and 0.15 for the ProstateX-2 dataset, and 0.852 and 0.581 for the PROMISE12 dataset. Using even small quantities of data to train the template enhanced performance, with significant improvements using 5% or more of the data. Conclusion: We trained a state-of-the-art model using unrefined clinical prostate annotations and found that its use as a template model significantly improved performance in other prostate segmentation tasks, even when trained with only 5% of the original dataset.

Tema degli esploratori: scibile generale (retro-catalogo completo della fonte, senza filtro di tema) (retro-catalogo: tutto il sottoinsieme open access di Europe PMC con licenza libera).
Pubblicazione: PloS one, 2021 (prima pubblicazione 2021-06-25).
Identificativi: PMID 34170972 · PMCID PMC8232529 · DOI 10.1371/journal.pone.0253829.
Descrittori MeSH principali: Tomography, X-Ray Computed; Databases, Factual; Data Curation; Deep Learning.
Pagina: https://europepmc.org/article/MED/34170972 — https://doi.org/10.1371/journal.pone.0253829. 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 2026-11-03T22:11:32.661Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.