EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data

Sejin Kim, Michal Kazmierski, Kevin Qu iD, Jacob Peoples iD, Minoru Nakano, Vishwesh Ramanathan, Joseph Marsilla, Mattea Welch, Amber Simpson, Benjamin Haibe-Kains

F1000Research · 2025

DOI: 10.12688/f1000research.127142.3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift F1000Research, 2025. Verfasst von Sejin Kim und 9 weiteren Autor:innen. Beteiligte Einrichtung: Princess Margaret Cancer Centre, University Health Network, Canada, Toronto, ON, Canada. Hauptthemen laut MEDLINE: Software, Image Processing, Computer-Assisted, Diagnostic Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Canadian Cancer Society, Canadian Institutes of Health Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Machine learning and AI promise to revolutionize the way we leverage medical imaging data for improving care but require large datasets to train computational models that can be implemented in clinical practice. However, processing large and complex medical imaging datasets remains an open challenge.

Methods

To address this issue, we developed Med-ImageTools, a new Python open-source software package to automate data curation and processing while allowing researchers to share their data processing configurations more easily, lowering the barrier for other researchers to reproduce published works. Use cases We have demonstrated the efficiency of Med-ImageTools across three different datasets, resulting in significantly reduced processing times.

Conclusions

The AutoPipeline feature will improve the accessibility of raw clinical datasets on public archives, such as the Cancer Imaging Archive (TCIA), the largest public repository of cancer imaging, allowing machine learning researchers to process analysis-ready formats without requiring deep domain knowledge.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareImage Processing, Computer-AssistedDiagnostic ImagingHumansMachine LearningNeoplasms

Stichwörter der Autor:innen

data processingdeep learningdicommedical imagingniftinnunetopen source

Autor:innen und Institutionen

  • Princess Margaret Cancer Centre, University Health Network, Canada, Toronto, ON, Canada.
  • Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada.
  • Faculty of Engineering, University of Toronto, Toronto, ON, Canada.
  • Centre for Health Innovation, Queen's University and Kingston Health Science Centre, Kingston, ON, Canada.
  • Vector Institute, Toronto, ON, Canada.

ORCID-Profile: Kevin Qu, Jacob Peoples

Förderung

  • Canadian Cancer Society
  • Canadian Institutes of Health Research

Zitieren

APA

Kim, S., Kazmierski, M., Qu, K., Peoples, J., Nakano, M., Ramanathan, V., Marsilla, J., Welch, M., Simpson, A., & Haibe-Kains, B. (2025). Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data. F1000Research. https://doi.org/10.12688/f1000research.127142.3

Vancouver

Kim S, Kazmierski M, Qu K, Peoples J, Nakano M, Ramanathan V, et al. Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data. F1000Research. 2025. doi:10.12688/f1000research.127142.3

BibTeX
@article{Kim2025,
  author = {Kim, Sejin and Kazmierski, Michal and Qu, Kevin and Peoples, Jacob and Nakano, Minoru and Ramanathan, Vishwesh and Marsilla, Joseph and Welch, Mattea and Simpson, Amber and Haibe-Kains, Benjamin},
  title = {Med-ImageTools: An open-source Python package for robust data processing pipelines and curating medical imaging data},
  journal = {F1000Research},
  year = {2025},
  doi = {10.12688/f1000research.127142.3}
}
Kostenlos starten →