Skip to main content

MD.ai Python client library

Project description

MD.ai Python Client Library

Currently pre-alpha -- API may change significantly in future releases.

The python client library is designed to work with the datasets and annotations generated by the MD.ai Medical AI platform.

You can download datasets consisting of images and annotations (i.e., JSON file), create train/validation/test datasets, integrate with various machine learing libraries (e.g., TensorFlow/Keras, Fast.ai) for developing machine learning algorithms.

To get started, check out the examples in the notebooks section, or our intro to deep learning for medical imaging lessons.

Installation

Requires Python 3.6+. Install and update using pip:

pip install --upgrade mdai

Documentation

Overview Documentation: https://docs.md.ai/libraries/python/ API Documentation coming soon.

The MD.ai Annotator

The MD.ai annotator is a powerful web based application, to store and view anonymized medical images (e.g, DICOM) on the cloud, create annotations collaboratively, in real-time, and export annotations, images and labels for training. The MD.ai python client library can be used to download images and annotations, prepare the datasets, and then used to train and evaluate deep learning models.

MD.ai Annotator

MD.ai Annotation JSON Format

More detailed information regarding the annotation JSON export format, see: https://docs.md.ai/data/json/

Example Notebooks

Introductory lessons to Deep Learning for medical imaging by MD.ai

The following are several Jupyter notebooks covering the basics of downloading and parsing annotation data, and training and evaluating different deep learning models for classification, semantic and instance segmentation and object detection problems in the medical imaging domain. The notebooks can be run on Google's colab with GPU (see instruction below).

  • Lesson 1. Classification of chest vs. adominal X-rays using TensorFlow/Keras Github | Annotator
  • Lesson 2. Lung X-Rays Semantic Segmentation using UNets. Github | Annotator
  • Lesson 3. RSNA Pneumonia detection using Kaggle data format Github | Annotator
  • Lesson 3. RSNA Pneumonia detection using MD.ai python client library Github | Annotator

Contributing

See contributing guidelines to set up a development environemnt and how to make contributions to mdai.

Running Jupyter notebooks Colab

It’s easy to run a Jupyter notebook on Google's Colab with free GPU use (time limited). For example, you can add the Github jupyter notebook path to https://colab.research.google.com/notebook: Select the "GITHUB" tab, and add the Lesson 1 URL: https://github.com/mdai/ml-lessons/blob/master/lesson1-xray-images-classification.ipynb

To use the GPU, in the notebook menu, go to Runtime -> Change runtime type -> switch to Python 3, and turn on GPU. See more colab tips.

Advanced: How to run on Google Cloud Platform with Deep Learning Images

You can also run the notebook with powerful GPUs on the Google Cloud Platform. In this case, you need to authenticate to the Google Cloug Platform, create a private virtual machine instance running a Google's Deep Learning image, and import the lessons. See instructions below.

GCP Deep Learnings Images How To


© 2023 MD.ai, Inc.

Download files

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

Source Distribution

mdai-0.15.0.tar.gz (281.9 kB view details)

Uploaded Source

Built Distribution

mdai-0.15.0-py3-none-any.whl (282.5 kB view details)

Uploaded Python 3

File details

Details for the file mdai-0.15.0.tar.gz.

File metadata

  • Download URL: mdai-0.15.0.tar.gz
  • Upload date:
  • Size: 281.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.8.17 Linux/5.15.0-1057-aws

File hashes

Hashes for mdai-0.15.0.tar.gz
Algorithm Hash digest
SHA256 af1c01a1323f09a0e43706c5c5943021d5ccc21279823b832b924efaf30f72dd
MD5 d2bc01de1190209946568045e31c82ca
BLAKE2b-256 812f7ea93f14d278663ca234b1c16b1c8bca6b8dd326db207a5709ddbe17d20d

See more details on using hashes here.

File details

Details for the file mdai-0.15.0-py3-none-any.whl.

File metadata

  • Download URL: mdai-0.15.0-py3-none-any.whl
  • Upload date:
  • Size: 282.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.8.17 Linux/5.15.0-1057-aws

File hashes

Hashes for mdai-0.15.0-py3-none-any.whl
Algorithm Hash digest
SHA256 848eb0806e8f7662d2ee95e9cd70d5d8745310b23e328da7defd3ccc0f68ef9c
MD5 c0fbc4a86b218f76011919760afaacf1
BLAKE2b-256 625410a960e39b797896e4bf391c12cb758c70ce000de5b06371b65ab2db81c2

See more details on using hashes here.

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