#124124th of 168 in ML frameworks and librariesFor image, video and design, 3d, science, health and research
torchio
PyTorch library for loading, augmenting and patch-sampling 3D medical images
- Stars
- 2.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- Python
2,381 on 21 Apr 20262,454 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
TorchIO is a Python package for reading, preprocessing, sampling, augmenting and writing 3D medical images in PyTorch training pipelines. It provides intensity and spatial transforms, including random affine and elastic deformation, plus MRI-specific artifact simulation (bias field, motion, spike, ghosting). A Queue class supports patch-based training.
Who it is for: Researchers training deep learning models on 3D medical images in PyTorch
Strengths
- MRI-specific augmentations: bias field, k-space motion, spike and ghosting artifacts
- Queue for patch-based training on large 3D volumes
- Peer-reviewed paper (2021), docs and Colab tutorials
- Installable from PyPI and conda-forge
Weaknesses
- Scoped to 3D medical imaging, not a general vision augmentation library
- Tied to PyTorch; no other tensor framework mentioned
- Data pipeline only; no models or training loop included
What it needs
- Needs PyTorch
Quick answers
Is torchio open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |