Tutorial: Accelerating research with the InnerEye medical imaging toolbox and Azure machine learning
420
20
Microsoft Research334 тыс
Следующее
Опубликовано 8 февраля 2022, 17:50
Speakers:
Anton Schwaighofer, Principal Researcher, Microsoft Research Cambridge
Michael Hansen, Director, Microsoft Health Futures
The InnerEye open-source toolbox powers the award-winning medical image project InnerEye and is based on the work of the Health Intelligence team at Microsoft Research Cambridge. In this session, we will provide a high-level introduction to this toolbox and explain how it can be used to facilitate efficient and reproducible research in health and life sciences. We will highlight the features that make this a generalizable tool so that medical imaging researchers can make their work more scalable and reproducible. We will describe how this toolbox can help researchers focus on their core task of building good AI models by re-using building blocks for infrastructure and cloud scale. As a case study, we will show how the InnerEye toolbox can be used to turbo-charge the creation of AI models for the reconstruction of magnetic resonance (MR) images from raw scanner data, where cloud scale-out is particularly important. In addition, we will also introduce a new dataset of clinical annotations, that helps to assess the clinical utility of the reconstruction models.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Anton Schwaighofer, Principal Researcher, Microsoft Research Cambridge
Michael Hansen, Director, Microsoft Health Futures
The InnerEye open-source toolbox powers the award-winning medical image project InnerEye and is based on the work of the Health Intelligence team at Microsoft Research Cambridge. In this session, we will provide a high-level introduction to this toolbox and explain how it can be used to facilitate efficient and reproducible research in health and life sciences. We will highlight the features that make this a generalizable tool so that medical imaging researchers can make their work more scalable and reproducible. We will describe how this toolbox can help researchers focus on their core task of building good AI models by re-using building blocks for infrastructure and cloud scale. As a case study, we will show how the InnerEye toolbox can be used to turbo-charge the creation of AI models for the reconstruction of magnetic resonance (MR) images from raw scanner data, where cloud scale-out is particularly important. In addition, we will also introduce a new dataset of clinical annotations, that helps to assess the clinical utility of the reconstruction models.
Learn more about the 2021 Microsoft Research Summit: Aka.ms/researchsummit
Свежие видео