Metraipolis › archive › dc_316aed5ad496

CEM500K, a large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning — Europe PMC PMID:33830015

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/33830015
DOI
10.7554/elife.65894
License (as archived)
CC0-1.0
Archived
2026-11-05T01:35:34.407Z
SHA-256 of the archived text
d4b96a18f0b019648e329c54722384069043e55e50d61f238624b0f7ff88b157
Stable URL of this page
https://metraipolis.com/documento/dc_316aed5ad496

How to cite

CEM500K, a large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning — Europe PMC PMID:33830015 — Europe PMC (en), https://europepmc.org/article/MED/33830015 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_316aed5ad496 (Metraipolis archive dc_316aed5ad496, sha256 d4b96a18f0b019648e329c54722384069043e55e50d61f238624b0f7ff88b157)
BibTeX
@misc{dc316aed5ad496,
  title = {CEM500K, a large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning — Europe PMC PMID:33830015},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/33830015},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_316aed5ad496; sha256 d4b96a18f0b019648e329c54722384069043e55e50d61f238624b0f7ff88b157},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/33830015. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated segmentation of cellular electron microscopy (EM) datasets remains a challenge. Supervised deep learning (DL) methods that rely on region-of-interest (ROI) annotations yield models that fail to generalize to unrelated datasets. Newer unsupervised DL algorithms require relevant pre-training images, however, pre-training on currently available EM datasets is computationally expensive and shows little value for unseen biological contexts, as these datasets are large and homogeneous. To address this issue, we present CEM500K, a nimble 25 GB dataset of 0.5 × 10 6 unique 2D cellular EM images curated from nearly 600 three-dimensional (3D) and 10,000 two-dimensional (2D) images from >100 unrelated imaging projects. We show that models pre-trained on CEM500K learn features that are biologically relevant and resilient to meaningful image augmentations. Critically, we evaluate transfer learning from these pre-trained models on six publicly available and one newly derived benchmark segmentation task and report state-of-the-art results on each. We release the CEM500K dataset, pre-trained models and curation pipeline for model building and further expansion by the EM community. Data and code are available at https://www.ebi.ac.uk/pdbe/emdb/empiar/entry/10592/ and https://git.io/JLLTz.

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: eLife, 2021 (prima pubblicazione 2021-04-08).
Identificativi: PMID 33830015 · PMCID PMC8032397 · DOI 10.7554/elife.65894.
Parole chiave degli autori: Electron microscopy; Cell biology; Neural network; Segmentation; systems biology; computational biology; None; Vem; Deep Learning; Image Dataset.
Descrittori MeSH principali: Microscopy, Electron; Image Processing, Computer-Assisted.
Pagina: https://europepmc.org/article/MED/33830015 — https://doi.org/10.7554/elife.65894. 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 2026-11-05T01:28:58.738Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.