The Belgian Neuroinformatics node will participate with two project ideas announced on https://neurostars.org/:
GSoC 2022 Project Idea 18.2: High content image feature and classification database – 350 h
and
GSoC 2022 Project Idea 18.1: Deep Learning using Geometric Features – 175 h
The proposals should be submitted by 19 April. The full timeline is available here.
The special issue “Neuroinformatics and Signal Processing” has been successfully completed.
The issue has published 9 articles from leading experts in the field.
INCF’s Active Segmentation for ImageJ working group – including GSOC students – has just published a paper in Brain Sciences as part of a special issue on neuroinformatics and signal processing. Congratulations to mentors Dimiter Prodanov & Sumit Vohra, and GSOC students Mukesh Gupta, Sanjeev Dubay, Joanna Stachera, Raghavendra Singh Chauhan, & Piyumal Demotte!
The Active Segmentation platform is an ImageJ plugin that integrates expert domain knowledge, providing partial ground truth, with geometrical feature extraction based on multi-scale signal processing combined with machine learning. The filtering functionality of the platform is extendable via plugins, and the built-in filters can also be used in stand-alone mode.
The platform supports rich and extensible metadata to ensure reproducibility of the classification and segmentation results across sessions. This design choice is made specifically to ensure support of the Findability, Accessibility, Interoperability, and Reusability (FAIR) data management principles. All filtering settings are stored in the project file in JavaScript Object Notation (JSON) format.
Learn more about it here: bit.ly/
The Belgian Node is pleased to announce that GSOC 2021 has been completed successfully.
Piyumal Demotte has developed Input/Out Workflows for Active Segmentation Platform. The project includes mainly incorporating ground truth labels-based segmentation implementation for weka classifiers and enhancing deep learning-based training. The workflow for ground truth labels-based segmentation is completed and the capsule network-based deep learning procedure is yet to be completed. The project was mentored by Dimiter Prodanov and Sumit Vohra. The rest of the project will be continued after the GSOC period.
The final report can be read here.
Aditya Wagh has developed a demo and documentation tool for wxMaxima. The package wxmx2texi, is a loadable package in Maxima that provides WxMaxima Worksheet to TexInfo conversion functionality. It was developed under the mentorship of Dimiter Prodanov and Robert Dodier as an INCF project during Google Summer of Code 2021 by Aditya Sandeep Wagh of the National Institute of Technology Karnataka Surathkal.
The final report can be read here.
The Belgian Node is pleased to announce that 2 projects – one about Active Segmentation and one about neuroimaging were selected for support by GSOC 2021.
Piyumal Demotte will develop Input/Out Workflows for Active Segmentation Platform.
Pranav Mahajan will develop A Python toolbox for computing high-order information in neuroimaging.
Dear Colleagues,
Neuroinformatics stands at the intersection of neuroscience and information science. With the diversity of the data generated in neuroscience, going from the genetic and molecular level to cognitive functions and the diversity of acquisition systems, the necessity of developing software tools, ontologies, and standards to describe the data appears crucial for better integration of these heterogeneous data for further understanding the brain.
Neuroinformatics leverages theoretical achievements of applied mathematics, computer science, and engineering to cope with the inherent complexity of real neuroscience experiments. Neuroinformatics stands firmly on the developments in neurophysiology, brain imaging, and microscopy to contribute to deciphering the secrets of the brain and the human mind.
Signal processing and applied mathematical methods go hand-in-hand with data-driven approaches and artificial intelligence. They enable crucial developments in the field of neuroscience, and further our understanding of the brain.
This Special Issue is dedicated to cutting-edge research in data structures, neuroinformatic databases, machine learning, and analysis pipelines combined with advanced signal processing algorithms.
We invite and welcome review, expository, and original research articles dealing with the recent advances in the application of the following topics to neuroscience:
It is a prerequisite that the code used in the papers be available in a public repository.
Submission: https://www.mdpi.com/journal/brainsci/special_issues/Neuroinformatics_Signal
Dr. Dimiter Prodanov
Prof. Dr. Newton Howard
Guest Editors
INCF presenting how to participate on Youtube
We are pleased to announce that INCF was accepted as an organization for GSOC 2021.
The Belgian node has formulated 2 projects. Candidates are welcome.
The list of ideas can be found here. Please stay tuned.
The Active Segmentation platform for ImageJ (ASP/IJ) was developed in the scope of GSoC 2016 – 2019. The 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 achieve excellent image segmentation and classification. ImageJ is a public domain Java image processing program extensively used in life and material sciences. The program was designed with an open architecture that provides extensibility via plugins.
The project idea: The existing machine learning model of Active Segmentation is based on the Weka library. However, this is limited to traditional machine learning approaches. The objective of the project will be to incorporate deep-learning functionality into the platform. Deep neural nets are capable of record-breaking accuracy.
The project is a continuation of GSOC 2020. The project will start from an already available codebase implemented using Deeplearning4j. At present, there are 2 implemented architectures U-Net — an architecture for biomedical image segmentation, and SegNet — a deep learning semantic segmentation architecture. The candidate will work out the GUI integration with the rest of the ASP/IJ platform.
Tasks:
Minimal set of deliverables:
Desired skills: Java, Machine Learning
Mentors: Sumit Vohra, ZIB, Berlin, Germany; Dimiter Prodanov @dprodanov, INCF Belgian Node (backup)
References:
ImageJ: https://imagej.nih.gov/ 6
Weka https://www.cs.waikato.ac.nz/ml/weka/ 3
Active Segmentation : https://github.com/sumit3203/ACTIVESEGMENTATION 6
Deeplearning4J: https://deeplearning4j.org/ 1
Tags: ImageJ, segmentation, machine learning, deep learning, GUI
The Belgian Neuroinformatics Node has successfully completed two GSOC projects under the mentorship of Dimiter Prodanov and Sumit Vohra.
The first one aimed at the application of the Viterbi algorithm for cell tracking. The project was proposed and executed by Raghavendra Singh Chauhan.
The second project aimed at using geometric features for deep learning. The project was proposed and executed by Joanna Stachera.
