Skip to main content

In this final lecture of the INCF Short Course: Introduction to Neuroinformatics, you will hear about new advances in the application of machine learning methods to clinical neuroscience data. In particular, this talk discusses the performance of SynthSeg, an image segmentation tool for automated analysis of highly heterogeneous brain MRI clinical scans.

Difficulty level: Intermediate
Duration: 1:32:01

This lesson explores how researchers try to understand neural networks, particularly in the case of observing neural activity. 

Difficulty level: Intermediate
Duration: 8:20
Speaker: : Marcus Ghosh

This lecture provides an introduction to the Brain Imaging Data Structure (BIDS), a standard for organizing human neuroimaging datasets.

Difficulty level: Intermediate
Duration: 56:49

In this lesson, you will learn about the Python project Nipype, an open-source, community-developed initiative under the umbrella of NiPy. Nipype provides a uniform interface to existing neuroimaging software and facilitates interaction between these packages within a single workflow.

Difficulty level: Intermediate
Duration: 1:25:05
Speaker: : Satrajit Ghosh

This lecture introduces you to the basics of the Amazon Web Services public cloud. It covers the fundamentals of cloud computing and goes through both the motivations and processes involved in moving your research computing to the cloud.

Difficulty level: Intermediate
Duration: 3:09:12

This lecture gives an overview of how to prepare and preprocess neuroimaging (EEG/MEG) data for use in TVB.  

Difficulty level: Intermediate
Duration: 1:40:52
Speaker: : Paul Triebkorn
Course:

This Jupyter Book is a series of interactive tutorials about quantitative T1 mapping, powered by qMRLab. Most figures are generated with Plot.ly – you can play with them by hovering your mouse over the data, zooming in (click and drag) and out (double click), moving the sliders, and changing the drop-down options. To view the code that was used to generate the figures in this blog post, hover your cursor in the top left corner of the frame that contains the tutorial and click the checkbox “All cells” in the popup that appears.

Jupyter Lab notebooks of these tutorials are also available through MyBinder, and inline code modification inside the Jupyter Book is provided by Thebelab. For both options, you can modify the code, change the figures, and regenerate the html that was used to create the tutorial below. This Jupyter Book also uses a Script of Scripts (SoS) kernel, allowing us to process the data using qMRLab in MATLAB/Octave and plot the figures with Plot.ly using Python, all within the same Jupyter Notebook.

Difficulty level: Intermediate
Duration:
Speaker: :

This lightning talk describes an automated pipline for positron emission tomography (PET) data. 

Difficulty level: Intermediate
Duration: 7:27

This lecture goes into detailed description of how to process workflows in the virtual research environment (VRE), including approaches for standardization, metadata, containerization, and constructing and maintaining scientific pipelines. 

Difficulty level: Intermediate
Duration: 1:03:55
Speaker: : Patrik Bey

This lesson is the first of three hands-on tutorials as part of the workshop Research Workflows for Collaborative Neuroscience. This tutorial goes over how to visualize data with Scanpy, a scalable toolkit for analyzing single-cell gene expression. 

Difficulty level: Intermediate
Duration: 25:26

In this third and final hands-on tutorial from the Research Workflows for Collaborative Neuroscience workshop, you will learn about workflow orchestration using open source tools like DataJoint and Flyte. 

Difficulty level: Intermediate
Duration: 22:36
Speaker: : Daniel Xenes

This lecture describes how to build research workflows, including a demonstrate using DataJoint Elements to build data pipelines.

Difficulty level: Intermediate
Duration: 47:00
Speaker: : Dimitri Yatsenko

This lecture discusses the the importance and need for data sharing in clinical neuroscience.

Difficulty level: Intermediate
Duration: 25:22
Speaker: : Thomas Berger

This lecture gives insights into the Medical Informatics Platform's current and future data privacy model.

Difficulty level: Intermediate
Duration: 17:29
Speaker: : Yannis Ioannidis

This lecture gives an overview on the European Health Dataspace. 

Difficulty level: Intermediate
Duration: 26:33

This is a tutorial on designing a Bayesian inference model to map belief trajectories, with emphasis on gaining familiarity with Hierarchical Gaussian Filters (HGFs).

 

This lesson corresponds to slides 65-90 of the PDF below. 

Difficulty level: Intermediate
Duration: 1:15:04
Speaker: : Daniel Hauke

This tutorial covers the fundamentals of collaborating with Git and GitHub.

Difficulty level: Intermediate
Duration: 2:15:50
Speaker: : Elizabeth DuPre

This lesson provides an overview of Jupyter notebooks, Jupyter lab, and Binder, as well as their applications within the field of neuroimaging, particularly when it comes to the writing phase of your research. 

Difficulty level: Intermediate
Duration: 50:28
Speaker: : Elizabeth DuPre

This talk presents state-of-the-art methods for ensuring data privacy with a particular focus on medical data sharing across multiple organizations.

Difficulty level: Intermediate
Duration: 22:49

The Medical Informatics Platform (MIP) is a platform providing federated analytics for diagnosis and research in clinical neuroscience research. The federated analytics is possible thanks to a distributed engine that executes computations and transfers information between the members of the federation (hospital nodes). In this talk the speaker will describe the process of designing and implementing new analytical tools, i.e. statistical and machine learning algorithms.  Mr. Sakellariou will further describe the environment in which these federated algorithms run, the challenges and the available tools, the principles that guide its design and the followed general methodology for each new algorithm. One of the most important challenges which are faced is to design these tools in a way that does not compromise the privacy of the clinical data involved. The speaker will show how to address the main questions when designing such algorithms: how to decompose and distribute the computations and what kind of information to exchange between nodes, in order to comply with the privacy constraint mentioned above. Finally, also the subject of validating these federated algorithms will be briefly touched.

Difficulty level: Intermediate
Duration: 20:26
Speaker: : Jason Skellariou