Microsoft Health Futures
Downloads
RAD-DINO model
November 2024
RAD-DINO is a vision transformer model trained to encode chest X-rays using the self-supervised learning method DINOv2. RAD-DINO is described in detail in RAD-DINO: Exploring Scalable Medical Image Encoders Beyond Text Supervision (F. Pérez-García, H. Sharma, S. Bond-Taylor, et al., 2024).
MAIRA-2 model
November 2024
MAIRA-2 is a multimodal transformer designed for the generation of grounded or non-grounded radiology reports from chest X-rays. It is described in more detail in MAIRA-2: Grounded Radiology Report Generation (S. Bannur, K. Bouzid et al., 2024). MAIRA-2 has been built…
RadFact: An LLM-based Evaluation Metric for AI-generated Radiology Reporting
November 2024
RadFact is a framework for the evaluation of model-generated radiology reports given a ground-truth report, with or without grounding. Leveraging the logical inference capabilities of large language models, RadFact is not a single number but a suite of metrics, capturing aspects of precision…
RadFact
August 2024
RadFact is a framework for the evaluation of model-generated radiology reports given a ground-truth report, with or without grounding. Leveraging the logical inference capabilities of large language models, RadFact is not a single number but a suite of metrics, capturing…
Vaccine Search Study
September 2023
This repository contains code and data for “Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs” (2023) by Serina Chang, Adam Fourney, and Eric Horvitz.
HI-ML Multimodal Toolbox
May 2023
HI-ML toolbox for deep learning for medical imaging and Azure integration. The Microsoft Health Intelligence Machine Learning Toolbox aims at providing low-level and high-level building blocks for Machine Learning / AI researchers and practitioners. It helps to simplify and streamline…
Biomedical Signal Processing: “Yardl” tooling
November 2022
Yardl is a simple schema language and command-line tool that generates domain types and serialization code. This is a tool for generating code based on a schema for raw instrument data.
Exercise Recognition from Wearable Sensors
June 2019
This data set contains accelerometer and gyroscope recordings from over 200 participants performing various gym exercises. This data set is described in more detail in the associated manuscript: Morris, D., Saponas, T. S., Guillory, A., & Kelner, I. (2014, April).…