EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images

Nicolás Gaggion iD, Candelaria Mosquera, Lucas Mansilla, Julia Mariel Saidman, Martina Aineseder, Diego H Milone, Enzo Ferrante iD

Scientific Data · 17.05.2024 · 11 (1)

DOI: 10.1038/s41597-024-03358-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Data, online erschienen am 17.05.2024. Verfasst von Nicolás Gaggion und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Signals, Systems and Computational Intelligence, sinc(i) CONICET-UNL, Santa Fe, CP 3002, Argentina. Hauptthemen laut MEDLINE: Radiography, Thoracic. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidad Nacional del Litoral, Ministry of Science, Technology and Productive Innovation, Argentina | Agencia Nacional de Promoción Científica y Tecnológica.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The development of successful artificial intelligence models for chest X-ray analysis relies on large, diverse datasets with high-quality annotations. While several databases of chest X-ray images have been released, most include disease diagnosis labels but lack detailed pixel-level anatomical segmentation labels. To address this gap, we introduce an extensive chest X-ray multi-center segmentation dataset with uniform and fine-grain anatomical annotations for images coming from five well-known publicly available databases: ChestX-ray8, CheXpert, MIMIC-CXR-JPG, Padchest, and VinDr-CXR, resulting in 657,566 segmentation masks. Our methodology utilizes the HybridGNet model to ensure consistent and high-quality segmentations across all datasets. Rigorous validation, including expert physician evaluation and automatic quality control, was conducted to validate the resulting masks. Additionally, we provide individualized quality indices per mask and an overall quality estimation per dataset. This dataset serves as a valuable resource for the broader scientific community, streamlining the development and assessment of innovative methodologies in chest X-ray analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radiography, ThoracicHumansDatabases, FactualArtificial IntelligenceLung

Autor:innen und Institutionen

  • Institute for Signals, Systems and Computational Intelligence, sinc(i) CONICET-UNL, Santa Fe, CP 3002, Argentina.
  • Health Informatics Department at Hospital Italiano de Buenos Aires, Buenos Aires, CP 1199, Argentina.
  • Universidad Tecnológica Nacional, Buenos Aires, CP 1179, Argentina.
  • Radiology Department, Hospital Italiano de Buenos Aires, Buenos Aires, CP 1199, Argentina.
  • Institute for Signals, Systems and Computational Intelligence, sinc(i) CONICET-UNL, Santa Fe, CP 3002, Argentina. eferrante@sinc.unl.edu.ar.

ORCID-Profile: Nicolás Gaggion, Enzo Ferrante

Förderung

  • Universidad Nacional del Litoral
  • Ministry of Science, Technology and Productive Innovation, Argentina | Agencia Nacional de Promoción Científica y Tecnológica

Zitieren

APA

Gaggion, N., Mosquera, C., Mansilla, L., Saidman, J. M., Aineseder, M., Milone, D. H., & Ferrante, E. (2024). CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images. Scientific Data, 11(1). https://doi.org/10.1038/s41597-024-03358-1

Vancouver

Gaggion N, Mosquera C, Mansilla L, Saidman JM, Aineseder M, Milone DH, et al. CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images. Scientific Data. 2024;11(1). doi:10.1038/s41597-024-03358-1

BibTeX
@article{Gaggion2024,
  author = {Gaggion, Nicolás and Mosquera, Candelaria and Mansilla, Lucas and Saidman, Julia Mariel and Aineseder, Martina and Milone, Diego H and Ferrante, Enzo},
  title = {CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images},
  journal = {Scientific Data},
  year = {2024},
  volume = {11},
  number = {1},
  doi = {10.1038/s41597-024-03358-1}
}
Kostenlos starten →