- 📖 Articles
- 🔥 Open-source
- 📊 Datasets
- Combining structured and unstructured data for predictive models: a deep learning approach
- pymia: A Python package for data handling and evaluation
- MINIMAR (MINimum Information for Medical AI Reporting): Developing reporting standards for artificial intelligence in health care
-
NLP
- medaCy - Medical Text Mining and Information Extraction with spaCy.
- deidentify - A Python library to de-identify medical records with state-of-the-art NLP methods. Pre-trained models for the Dutch language are available.
-
Computer Vision
- monai - MONAI is a PyTorch-based, open-source framework for deep learning in healthcare imaging, part of PyTorch Ecosystem.
-
Imaging
- cornerstone - Cornerstone.js delivers a complete web based medical imaging platform.
- DWV - s an open source zero footprint medical image viewer library. It uses only javascript and HTML5 technologies, meaning that it can be run on any platform that provides a modern browser (laptop, tablet, phone and even modern TVs).
- OHIF Medical Imaging Viewer - The OHIF Viewer is a zero-footprint medical image viewer provided by the Open Health Imaging Foundation (OHIF). It is a configurable and extensible progressive web application with out-of-the-box support for image archives which support DICOMweb.
- Papaya - Papaya is a pure JavaScript medical research image viewer, supporting DICOM and NIFTI formats, compatible across a range of web browsers. This orthogonal viewer supports overlays, atlases, GIFTI & VTK surface data and DTI data.
- pymia - pymia is an open-source Python (py) package for deep learning-based medical image analysis (mia). The package addresses two main parts of deep learning pipelines: data handling and evaluation.
-
Frameworks
- CareKit - CareKit is an open source software framework for creating apps that help people better understand and manage their health.
- Clinical Meteor - Meteor.js packages for HIPAA security, FDA precertification, and EHR interoperability.
- Fhirbase - Open source storage based on the FHIR standard ready for use in production.
- IBM/FHIR - The IBM® FHIR® Server is a modular Java implementation of version 4 of the HL7 FHIR specification with a focus on performance and configurability.
- Opal - Opal is a full stack web framework that makes building digital tools for health care easy.
- google/fhir - FhirProto is Google’s implementation of the FHIR Standard for Health Care data using Protocol Buffers.
-
Compliance
- MedPix Database of 53,000 medical images from 13,000 patients with annotations. Requires registration.
- Medical Decathlon - Generalisable 3D Semantic Segmentation
- MedNIST
- Building the graph of medicine from millions of clinical narratives [data] - Co-occurence statistics for medical terms extracted from 14 million clinical notes and 260,000 patients.
- Learning Low-Dimensional Representations of Medical Concept - Anonymized critical care EHR database on 38,597 patients and 53,423 ICU admissions. Requires registration.
- Clinical Concept Embeddings Learned from Massive Sources of Medical Data - Embeddings for 108,477 medical concepts learned from 60 million patients, 1.7 million journal articles, and clinical notes of 20 million patients. Interactive tool.
- MIMIC critical care database - MIMIC is an openly available dataset developed by the MIT Lab for Computational Physiology, comprising deidentified health data associated with ~60,000 intensive care unit admissions. It includes demographics, vital signs, laboratory tests, medications, and more.