---
AI Summary: "\\- Developed an open-source Python library for extracting DICOM data.\
  \  \n- Simplified reconstruction of 3D scan data from MRI, CT, and PET images. \
  \ \n- Utilized numpy for handling data arrays and built on the pydicom library.\
  \  \n- Repository and documentation available on GitHub and ReadTheDocs."
Anonymous: false
Assignee:
- J. David Giese
Last Edited Time: '2024-01-27T21:17:00+00:00'
case_study_510ks: []
client_logo: []
client_name: Innolitics Open Source
date: '2017-01-27'
featured: false
medical_panel: Tooling
name: MR, CT, and PET Python DICOM Library
services: []
summary: Python module for extracting data contained in DICOM files
tags:
- Open-Source
- DICOM
testimonials: []
---

## The Problem

Often in medical imaging applications, developers need to access the pixel values of a MRI, CT, or PET scan. These images are stored in DICOM files. (Read about what DICOM is and why it exists [here](https://innolitics.com/articles/dicom-i-facilitating-interoperability/).) Combining raw imaging data from individual DICOM files into a single 3D array is tricky.

## The Solution

We found ourselves needing this frequently during client work and decided to open-source the solution that has worked well for us. This library allows developers to easily reconstruct the 3D scan data from DICOM files by returning it as a numpy `ndarray` for further processing and calculations. It is a higher-level library that builds on the excellent lower-level pydicom library.

You can find the repository [here](https://github.com/innolitics/dicom-numpy). All the documentation for the library can be found [on our ReadTheDocs page](http://dicom-numpy.readthedocs.io/en/latest/).