Long-running GSoC project on image segmentation results in a paper

One of INCF’s longest running GSoC projects, Active Segmentation for ImageJ, has resulted in  a paper. Congratulations to mentor Dimiter Prodanov (Belgian Neuroinformatics Node), co-mentor (and former GSoC student) Sumit Vohra, and to GSoC students Mukesh Gupta (2017), Sanjeev Dubay (2018), Joanna Stachera (2020), Raghavendra Singh Chauhan (2020) and Piyumal Demotte (2021)!

ImageJ is an open source Java image processing program extensively used in life sciences. The program was designed with an open architecture that provides extensibility via Java plugins. User-written plugins make it possible to solve almost any image processing or analysis problem or integrate the program with 3rd party software. 

Image segmentation aims to divide an image into multiple regions that represent anatomical objects of interest. Manual segmentation is labor-intensive and subject to inter-observer variations, while traditional image segmentation algorithms are problem-specific and limited in scope - if they are tailored for one imaging modality they are very likely to fail in other modalities.

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. Furthermore, the file format is transparent for both human eyes and algorithms as JSON is a subset of the standard web language JavaScript.

The paper is published as part of a special issue on Neuroinformatics and Signal Processing in Brain Sciences.

Read more: The Active Segmentation Platform for Microscopic Image Classification and Segmentation, Brain Sci. 2021, 11(12), 1645; https://doi.org/10.3390/brainsci11121645