Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Oct 26, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K

TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical

Fernando Pérez-García1, Rachel Sparks2, Sébastien Ourselin2

  • 1Department of Medical Physics and Biomedical Engineering, University College London, UK; Wellcome / EPSRC Centre for Interventional and Surgical Sciences (WEISS), University College London, UK; School of Biomedical Engineering & Imaging Sciences (BMEIS), King's College London, UK.

Computer Methods and Programs in Biomedicine
|July 26, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Novel utilization of the seaweed-based deoxy sugars rhamnose and fucose by engineered Corynebacterium glutamicum.

Microbial cell factories·2026
Same author

InnerEye-HS: a disease-agnostic clinical tool for hippocampal segmentation.

Brain communications·2026
Same author

SARS-CoV-2 infection and vaccination elicit distinct pharyngeal mucosal B cell responses in children.

Nature communications·2026
Same author

Production of the Antimicrobial Roseoflavin With Genetically Engineered Corynebacterium glutamicum.

Microbial biotechnology·2025
Same author

Mondo: integrating disease terminology across communities.

Genetics·2025
Same author

SARS-CoV-2 infection and vaccination elicit distinct pharyngeal mucosal B cell responses in children.

Research square·2025
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
Same journal

Evaluation of surrogate endpoints for survival outcomes using the surrogate package in R.

Computer methods and programs in biomedicine·2026
Same journal

Relative spectral and frication-based descriptors as numerical indicators of place of articulation shifts in fricatives produced by Polish children.

Computer methods and programs in biomedicine·2026
Same journal

Leaflet resection improves valve expansion and hemodynamic performance in redo TAVI with balloon- and self-expanding transcatheter heart valve configurations.

Computer methods and programs in biomedicine·2026
Same journal

Spectral super-resolution for Parkinson's voice via representation-level methods under mixed-reality acquisition.

Computer methods and programs in biomedicine·2026
See all related articles
This summary is machine-generated.

TorchIO is a Python library for efficient medical image processing in deep learning, addressing challenges like limited data and high computational costs. It standardizes pipelines, enabling reproducible research and easier focus on AI model development.

Area of Science:

  • Medical image analysis
  • Deep learning for healthcare
  • Computational imaging

Background:

  • Medical image processing (MRI, CT) presents unique challenges: lack of labeled data, high computational demands, and critical metadata requirements.
  • Standard computer vision techniques are insufficient for medical imaging due to voxel properties and spatial orientation needs.
  • Data augmentation and patch-based processing are crucial for efficient deep learning model training with medical images.

Purpose of the Study:

  • To introduce TorchIO, an open-source Python library designed for efficient medical image loading, preprocessing, and augmentation for deep learning.
  • To facilitate patch-based sampling and handle spatial metadata correctly for accurate medical image analysis.
  • To support researchers in standardizing medical image processing pipelines for deep learning applications.
Keywords:
Data augmentationDeep learningMedical image computingPreprocessing

More Related Videos

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.0K

Related Experiment Videos

Last Updated: Oct 26, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.4K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

1.0K

Main Methods:

  • TorchIO provides a PyTorch-compatible framework for medical image processing.
  • It integrates existing libraries for efficient image manipulation during neural network training.
  • The library offers composable, reproducible, and invertible transforms, including MRI artifact simulation and preprocessing operations.

Main Results:

  • TorchIO is available via PyPI and includes command-line and graphical user interfaces (in 3D Slicer) for transform application and visualization.
  • Comprehensive documentation and tutorials are accessible online.
  • The library supports efficient patch-based sampling and advanced augmentation techniques.

Conclusions:

  • TorchIO standardizes medical image processing, allowing researchers to concentrate on deep learning model development.
  • It promotes open-science practices through version control and precise citation support.
  • The modular design ensures compatibility with various deep learning frameworks for medical imaging.