SimpleITK Jupyter Notebooks: Biomedical Image Analysis in Python

Level: Intermediate Length: 4 hours Format: In-Person Lecture Intended Audience: Students, researchers and engineers involved in biomedical image analysis with the need for convenient image IO, image registration and image manipulation via spatial and intensity transformations. Knowledge of the Python programming language is assumed. Description: SimpleITK is a simplified programming interface to the algorithms and data structures of the Insight Segmentation and Registration Toolkit (ITK). It supports bindings for multiple programming languages including C++, Python, R, Java, C#, Lua, Ruby and TCL. Combining SimpleITK’s Python binding with the Jupyter notebook web application creates an environment which facilitates collaborative development of biomedical image analysis workflows. In this course, we will use a hands-on approach utilizing Python based SimpleITK Jupyter notebooks to explore and experiment with various toolkit features. Participants will follow along using their personal laptops, enabling them to explore the effects of changes and settings not covered by the instructor. We start by introducing the toolkit’s two basic data elements, Images and Transformations. We then combine the two, illustrating how to perform image resampling. Having mastered the concept of resampling, we show how to use SimpleITK as a tool for image preparation and data augmentation for deep learning via spatial and intensity transformations. We then turn our focus to the toolkit’s registration framework, exploring various components including: optimizer selection, the use of linear and deformable transformations, the embedded multi-resolution framework, self-calibrating optimizers and the use of callbacks for registration progress monitoring. Finally, we illustrate the use of a variety of SimpleITK filters to implement an image analysis workflow that includes segmentation and shape analysis. Learning Outcomes: This course will enable you to: - describe the components that comprise the SimpleITK registration framework. - use the SimpleITK registration framework to register their own data by selecting the appropriate components and settings. - list all of the SimpleITK transformation types and image intensity manipulation filters. - use SimpleITK to prepare images as input for deep learning networks, including generation of synthetic images for data augmentation. Instructor(s): Bradley Lowekamp is a Senior Computer Scientist at MSC LLC, and the Lister Hill National Center for Biomedical Communications, US National Library of Medicine. He is the lead architect and developer of SimpleITK. He is actively involved in the development of open source software, contributing to multiple projects including 3D Slicer, ITK, and SimpleITK. Mr. Lowekamp’s interests include biomedical image analysis and software engineering. Ziv Yaniv is a Senior Computer Scientist at TAJ Technologies Inc, and the Lister Hill National Center for Biomedical Communications, US National Library of Medicine. He is the lead maintainer of the SimpleITK Jupyter notebooks environment. He is actively involved in the development of open source software, contributing to multiple projects including IGSTK, ITK, and SimpleITK. Dr. Yaniv served as chair of the SPIE Image-Guided Procedures, Robotic Interventions and Modeling, conference 2013-2016, and was program chair for the Information Processing in Computer-Assisted Interventions conference 2016. He is on the editorial boards of IET Healthcare Technology Letters and Int. J. Comput. Assist. Radiol. Surg. Event: SPIE Medical Imaging 2019 Course Held: 17 February 2019