---
id: itk-io
version: "5.4.7"
license: Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for… (full text in the JSON record)
license_treatment: permissive
maintenance: active
---

# itk-io — ITK is an open-source toolkit for multidimensional image analysis

License: permissive · Maintenance: active · Downloads: 229.9K/mo

## What it is and what it does

itk-io is the input/output module of the Insight Toolkit, a cross-platform C++ library for N-dimensional scientific image processing. It exposes Python bindings for reading and writing medical and scientific images in a variety of formats, typically used in conjunction with itk-core for image manipulation and analysis. The package is part of a larger ecosystem designed for medical image segmentation and registration tasks—common workflows in medical imaging, research, and diagnostic applications. It depends on itk-core and is distributed as pre-compiled wheels for modern Python versions across major operating systems.

The package targets researchers, medical imaging professionals, and developers building image analysis pipelines. Installation is straightforward via pip or conda, though the compiled nature of the wheels means medium install friction. The toolkit is actively maintained by the Insight Software Consortium, which is fiscally sponsored by NumFOCUS, and has been in active development since 2017.

Use it for:

- Load DICOM images from CT or MRI scanners for analysis in Python medical imaging workflows.
- Convert between medical image formats (e.g., DICOM to NIfTI) for interoperability with other tools.
- Write segmentation or registration results back to disk in standard medical imaging formats.
- Build image processing pipelines that read, process, and save scientific image data.
- Integrate ITK image I/O into research code for reproducible medical image analysis.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

itk-io provides Python bindings for reading and writing medical and scientific image files in multiple formats as part of the Insight Toolkit ecosystem.

Yes, if you are building medical or scientific image processing workflows in Python and need reliable, format-agnostic image I/O. The package is actively maintained, permissively licensed, has no known vulnerabilities, and integrates seamlessly with itk-core. Install friction is moderate but manageable via pre-built wheels. Not necessary if you only need basic image reading (e.g., via PIL or OpenCV) or work exclusively with a single format.

## Install

pip install itk-io
uv add itk-io
poetry add itk-io

## Installing itk-io

Before you install: Medium install friction due to compiled binary wheels; pre-built wheels available for Python 3.9–3.11 across Linux, macOS (including Apple Silicon), and Windows. Actively maintained with a release 7 days old and recent commits.

License in practice: Apache License 2.0 permits both commercial and non-commercial use with minimal restrictions; you may use, modify, and distribute the package provided you include license notices and attribute changes.

Quickstart:

pip install itk-io

import itk

image = itk.imread('input_image.dcm')
itk.imwrite(image, 'output_image.nii')

Requires itk-core as a runtime dependency; ensure your Python version is 3.8 or later.

Verify before relying:

- Whether itk-io alone is sufficient for typical image I/O workflows or if additional ITK modules are commonly required.
- Performance characteristics and supported image formats beyond those mentioned in the description excerpt.

## Package facts

- License: Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "License" shall mean the terms and conditions for… (full text in the JSON record) (permissive)
- Python support: supports_current
- Install friction: medium
- Maintenance: active
- Downloads: 229.9K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

medical image file I/O, read write medical images, DICOM image processing, scientific image format conversion, ITK image I/O bindings, medical imaging file formats, image segmentation data loading, medical-imaging, image-io, scientific-computing

[View on SkillFed](https://skillfed.io/packages/itk-io) · [View on PyPI](https://pypi.org/project/itk-io/)