Belgian Neuroinformatics

Category Archives: Belgian News

Active Segmentation on FENS 2018

INCF hosted a booth with community demos at FENS Forum 2018. The Active Segmentation  plugin was presented there by Sumit Vohra, the main developer of the platform, who was funded by GSOC 2016. Sumit developed the initial version of  platform as pare of the master thesis project with Dimiter Prodanov, a Fellow of the Belgian INCF Node.

 

The Active Segmentation aims of providing a general purpose workbench that would allow biologists to access state-of-the-art techniques in machine learning and image processing to improve their image segmentation results. The major goal of the platform is to provide a well documented tool for users along with visual insights so that user can understand the underlined methodology

Currently, Active Segmentation supports various geometric features, such as Laplace of Gaussian , Gaussian Derivatives among others. It also provide various machine learning algorithms like Support Vector machine, Naive Bayes etc available in WEKA library. The platform allows researchers to add their own feature extraction and machine learning algorithms.

 

GSOC 2018 participation

The Belgian node will support the development of three Google Summer of Code projects in 2018.

Student developers

Sanjeev Dubey

 

Modular Machine Learning and Classification Toolbox for ImageJ

ImageJ is an open source Image Processing library written in Java which is being
extensively used by people working in Life and Material sciences. ImageJ supports various
application softwares through plugins. The Active Segmentation plugin provides a
general-purpose environment that allows biologists and other domain experts to use
transparently state-of-the-art techniques in machine learning to improve their image
segmentation results.

https://summerofcode.withgoogle.com/dashboard/project/4629497303793664/overview/

 

Building a portable open pipeline to detect the hemodynamic response function at rest

Madhur Tandon

 

Most of the currently used data is task-based fMRI data i.e. the data acquired when the subject performs an explicit task (such as finger-tapping). It is clear however, that the brain is active even when the subject is not performing a task. In fact, according to certain estimates, task-related changes in neuronal metabolism only account for about 5% of the brain’s total energy consumption. Resting state fMRI is a comparatively newer approach used to identify synchronous BOLD changes in multiple brain regions while the subjects lie comfortably in the scanner without performing a task. The correlations between spontaneous BOLD signals can be used to study intrinsic functional connectivity. The analysis is also useful in situations where it is advantageous to explore the brain’s functional organization in neurological or psychiatric diseases. INCF currently has a tool to retrieve the hemodynamic response function at rest from resting state fMRI, however, the code is currently written in MATLAB. In order to increase its diffusion and portability, the repository has to be converted to Python and follow the BIDS – Standards to eventually create the portable neuroimaging pipeline.

 

https://summerofcode.withgoogle.com/dashboard/project/6392610705375232/overview/

 

 

 

FOSDEM2018

Google has initiated a GSOC meetup on 3rd Feb for  FOSDEM  https://fosdem.org/2018/ in Brussels.

The meeting took place in a popular bar next to  the landmark Grand Place in Brussels.

It was a great opportunity for different open source  communities to interact.  INCF was represented informality by Dimiter Prodanov from the Belgian INCF node.

BeNet 2017

The 7th edition of the Belgian Network Research Meeting (BeNet) took place in Ghent on 6th Dec. This annual meeting is a place for the Belgium-based researchers interested in the network paradigm to meet and communicate their results and perspectives.

Daniele Marinazzo, from  UGent hosted the meeting.  Dimiter Prodanov from Imec presented a poster on fractional diffusion in the brain.

GSOC 2017 completed

The  GSOC 2017 was successfully completed by  Mukesh Gupta.  The aim of the project was to provide the general purpose environment that allows biologists and other domain experts to use  state-of-the-art techniques in machine learning to improve   segmentation of objects in different types of images.  The project was completed under the supervision of  Dimiter Prodanov  (Belgian INCF Node  Fellow) and Sumit Kumar Vohra (an Alumni of the Belgian INCF Node )

In this Google summer of code we expanded the existing functionality of the Active Segmentation plugin. Earlier this tool only used for Segmentation, now functionality has been extended to classification of the images. We used Zernike moments as a feature vector so we extracted Zernike moments from the images and then used these features to train our SVM classifier to classify images.

 

 

The code can be found here: https://mukesh14149.github.io/

Postdoc in computational modeling of brain networks

The Stanford Cognitive and Systems Neuroscience Laboratory invites applications for postdoctoral fellowships in brain network modeling and analysis. We seek candidates with strong research backgrounds in one or more of the following areas: resting-state fMRI, DTI, functional and structural brain connectivity analysis, and network modeling. This is an exciting opportunity to work on NIH- and NSF-funded projects using computational, network modeling and multimodal (fMRI, DTI, EEG) brain imaging techniques. The successful candidate will develop a vigorous research program that contributes to, and complements, ongoing research studies. The candidate will have access to state-of-the-art brain imaging and computational facilities. Strong programming skills and previous experience with DTI analysis are desirable. Please email a CV, statement of research interests and relevant background, and names of three referees to Drs. Vinod Menon and Aarthi Padmanabhan at scsnl.stanford+postdoc@gmail.com.

 

Stanford University’s Department of Psychiatry & Behavioral Sciences is seeking to hire full time post-doctoral fellows for their Cognitive & Systems Neuroscience Laboratory. This lab is headed by Dr. Vinod Menon who has broad multidisciplinary expertise that spans several scientific disciplines and has published extensively on various aspects of human cognition and brain function.

 

Explore our lab website for more information: http://med.stanford.edu/scsnl.html.

Call for paper F1000

The INCF Neuroinformatics gateway on F1000Research will publish an article series on open neuroscientific methods, software, data descriptions and training approaches in advance of the this year’s Neuroinformatics Congress.

The submission deadline is Aug 7th with articles being publicized by both us and the INCF before, during and after the Congress (Aug 20-21st). The gateway also supports LaTeX submissions via Overleaf.

Articles in this series will be published using a novel publication model designed to reduce publication delays and research waste, and increase transparency: manuscripts are published within a few days of submission (pending an editorial check to ensure research reporting guidelines are met, and associated non-identifiable data and code is publicly available), ready for open peer review by invited experts. Once an article passes peer review, it is indexed in PubMed, Scopus and elsewhere. Articles are versioned, so authors can update their paper to respond to peer review comments.

Would you be able to contribute an article to the series? If you have any questions please get in touch with the F1000Research staff publishers@f1000.com

BrainHack@Ghent

BrainHack@Ghent will take place on April 12-13th at the Faculty of Psychology and Educational Sciences, Ghent.
The event is now accepted as part of the Doctoral Training Programme. This means that PhD students in Psychology and Life Sciences can include BrainHack in their curriculum.

Brainhack?

The purpose of BrainHack is to bring together brain enthusiasts with varying backgrounds and skills to build relationships, learn from one another and collaborate on projects related to neuroscience during two days of intense interaction. Participants can either bring their own project/question and recruit a team of collaborators, or come to learn methods, develop skills and collaborate with other participants.
Participants will receive advice on processing from a team of experts including Russell Poldrack, Danilo Bzdok, Camille Maumet, Roberto Toro, Daniel Margulies, Ben Jeurissen and Dante Mantini during the two days.

Registration & Slack

For PhD students of Ghent University, the registration fee is €70. For all other participants, the registration fee is €90. This includes breakfast, lunch and drinks on both days and dinner on the first day. Registration is only possible with credit card.  We encourage interested persons to join our public Slack channel to discuss and propose projects and to recruit collaborators. You can register for the official Brainhack Ghent 2017 slack channel on the Register page of the website: http://brainhackghent.wixsite.com/brainhackghent/register
For all information, check our website: http://brainhackghent.wixsite.com/brainhackghent
You can also contact us by email at [email protected]
We hope to see you all there!

Close
loading...