Skip to main content

A Python library for working with medical image datasets.

Project description

Medidata - Medical Image Dataset

MediData is a Python library that provides access to medical image datasets. It aims to simplify the process of loading and working with medical image data in various machine learning and data analysis projects.


Load and preprocess medical image datasets. Resize images to the desired dimensions. Access images and corresponding labels as numpy arrays. Support for various medical imaging formats. Easily integrate with machine learning workflows.


You can install MediData using pip:

pip install medidata


To use the Medidata dataset, you can install the Medidata library and import it into your Python project. You can then access the dataset using the provided functions and utilities. Here's an example of how to load the dataset:

To use MediData, follow these steps:

  1. Import the medidata module:
from medidata import dataset
  1. Load the BR35H dataset using the load_br35h function:
X, y, labels = dataset.load_br35h()

This function loads the BR35H dataset from the default directory path and returns the resized images and corresponding labels as numpy arrays.

  1. You can now use the X, y, and labels variables in your data analysis or machine learning workflows.


Here's an example of how to use MediData to load and process the BR35H dataset:

from medidata import dataset

X, y, labels = dataset.load_br35h()

# Perform further operations on the loaded dataset
# ...


We welcome contributions to the Medidata library, including the addition of new medical image datasets. If you have other medical image datasets that you would like to include in Medidata, please reach out to us or submit a pull request.

Together, let's build a comprehensive and valuable resource for medical image analysis.


If you use the Medidata dataset in your research or projects, we kindly request that you cite the original source of the dataset. The dataset can be found at:

Br35H Dataset on Kaggle

Please refer to the original dataset and follow any additional citation guidelines provided by the dataset creators.


For any questions or inquiries regarding the Medidata dataset, please contact


[1] Ahmed Hamada. (2023). Br35H: Brain Tumor Detection Dataset. Kaggle Datasets. Retrieved from

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

medidata-0.6.0.tar.gz (64.4 MB view hashes)

Uploaded Source

Built Distribution

medidata-0.6.0-py3-none-any.whl (65.8 MB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page