Skip to main content

MedImgKit

A comprehensive toolkit for medical image processing, providing utilities for DICOM, NIfTI, and other medical image formats with seamless multi-format I/O operations.

Features

  • DICOM Support: Read, anonymize, and manipulate DICOM files
  • NIfTI Support: Work with neuroimaging data in NIfTI format
  • Multi-format I/O: Unified interface for reading various image formats
  • Anonymization: DICOM anonymization following DICOM standards
  • Coordinate Conversion: Convert between pixel and patient coordinates
  • Multi-frame Assembly: Combine multiple DICOM files into multi-frame volumes

Installation

From PyPI

pip install medimgkit

From Source

pip install git+https://github.com/SonanceAI/medimgkit

Quick Start

DICOM Operations

import medimgkit as mik
import pydicom

# Read and normalize DICOM image
ds = pydicom.dcmread('path/to/dicom.dcm')
image_array = mik.load_image_normalized(ds)

# Anonymize DICOM
anonymized_ds = mik.anonymize_dicom(ds)

# Convert pixel coordinates to patient coordinates
patient_coords = mik.pixel_to_patient(ds, pixel_x=100, pixel_y=150)

# Use a specific native axis or anatomical plane when working with reformatted slices
coronal_coords = mik.pixel_to_patient(ds, pixel_x=80, pixel_y=20, slice_index=120, axis_index='coronal')

NIfTI Operations

import nibabel as nib
import medimgkit as mik
from medimgkit.nifti_utils import read_nifti_slice

# Load NIfTI file
nifti_data = nib.load('path/to/image.nii.gz')

# Get a specific slice
slice_image = mik.get_slice(nifti_data, slice_index=50, slice_axis=2)

# Read a slice by anatomical plane while preserving native slice orientation
slice_image, nifti_img = read_nifti_slice(
	'path/to/image.nii.gz',
	slice_index=50,
	plane='coronal',
)

# Convert world coordinates to slice index
slice_idx, axis = mik.line_to_slice_index(nifti_data, point1, point2)

Multi-format Reading

import medimgkit as mik

# Read any supported format
image_array = mik.read_array_normalized('path/to/image.dcm')
image_array = mik.read_array_normalized('path/to/image.nii.gz')
image_array = mik.read_array_normalized('path/to/image.png')

API Reference

DICOM Utils (medimgkit.dicom_utils)

Core Functions

  • load_image_normalized(dicom, index=None): Load and normalize DICOM pixel data
  • read_dicom_standardized(filepath, index=None, ..., frame_order='geometric'): Read pixel data as (N, C, H, W). Multi-frame volumes are returned in geometric order (matching the Datamint web viewer); pass frame_order='stored' for the legacy on-disk order
  • compute_geometric_frame_order(ds, reference_index=0): Frame indices in the order Cornerstone displays them
  • anonymize_dicom(ds, retain_codes=[], copy=False, token_mapper=None): Anonymize DICOM following standards
  • assemble_dicoms(files_path, return_as_IO=False): Combine multiple DICOMs into multi-frame
  • is_dicom(f): Check if file is a DICOM

Coordinate Conversion

  • pixel_to_patient(ds, pixel_x, pixel_y, slice_index=None, axis_index=None, frame_order='geometric'): Convert pixel to patient coordinates, optionally along a native axis or anatomical plane
  • patient_to_voxel(ds, patient_coords, frame_order='geometric'): Convert patient coordinates to voxel coordinates
  • build_affine_matrix(ds, frame_order='geometric'): Build the voxel-to-patient affine
  • get_image_position(ds, slice_index=None): Get image position in patient coordinates
  • get_pixel_spacing(ds, slice_index): Get pixel spacing information

Anatomical Analysis

  • determine_anatomical_plane_from_dicom(ds, slice_axis, alignment_threshold=0.95): Determine anatomical plane

NIfTI Utils (medimgkit.nifti_utils)

Slice Operations

  • get_slice(data, slice_index, slice_axis=None, plane=None): Extract a slice from a 3D/4D volume
  • read_nifti_slice(file_path, slice_index, plane=None): Read one standardized slice in (C, H, W) format while preserving native orientation
  • get_slice_from_line(data, world_point1, world_point2): Get slice defined by line
  • slice_location_to_slice_index(data, slice_location, slice_axis): Convert location to index

Coordinate Conversion

  • line_to_slice_index(data, world_point1=None, world_point2=None, coplanar_vector=None): Convert line to slice
  • axis_name_to_axis_index(data, axis_name): Convert axis name to index

Utilities

  • is_nifti_file(file_path): Check if file is NIfTI format

I/O Utils (medimgkit.io_utils)

Reading Functions

  • read_array_normalized(file_path, index=None, return_metainfo=False, use_magic=False): Universal image reader
  • read_image(file_path): Read standard image formats (PNG, JPEG)
  • read_nifti(file_path, mimetype=None, slice_index=None, plane=None): Read NIfTI files and optionally order slices by anatomical plane
  • read_video(file_path, index=None): Read video files

Supported Formats

  • DICOM: .dcm, .dicom (and files without extension)
  • NIfTI: .nii, .nii.gz
  • Images: .png, .jpg, .jpeg
  • Video: .mp4, .avi, .mov, .mkv
  • NumPy: .npy

Development

Running Tests

pytest

License

MIT License - see LICENSE file for details.

Contributing

  1. Fork the repository
  2. Create a feature branch
  3. Make your changes
  4. Submit a pull request

Metadata

Release files for medimgkit 0.19.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for medimgkit 0.19.0
File Size Uploaded Provenance Actions
medimgkit-0.19.0.tar.gz 58.3 kB With provenance Details for medimgkit-0.19.0.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for medimgkit 0.19.0
File Interpreter ABI Platform Actions
medimgkit-0.19.0-py3-none-any.whl Python 3 none any Details for medimgkit-0.19.0-py3-none-any.whl

Total release size: 109.7 kB

Release files / medimgkit-0.19.0.tar.gz

Download URL medimgkit-0.19.0.tar.gz
Size 58.3 kB
Tags Source
SHA-256 checksum
How to use checksums
3dec6e6691110d0b596c11872ccdd81f62087c78a46bf8b500c63a48334f29f6
BLAKE2b-256 checksum
How to use checksums
4717394cb29aa55cb36d456a54587ec8a28258a2bc45430da7ccd850397befaa
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

Release files / medimgkit-0.19.0-py3-none-any.whl

Download URL medimgkit-0.19.0-py3-none-any.whl
Size 51.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1f176a6e1c4d1d5444cac7b234de0907f67bc87b12603ef4c9896ce844dde200
BLAKE2b-256 checksum
How to use checksums
b9bec21d7a170e83ff4676aad95b805dfc342eb14a28d3197d5878e41cced26d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

Security for medimgkit 0.19.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for medimgkit-0.19.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 5, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.19.0 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page