Distributed ImageJ(Fiji): a framework for parallel image processing

• Published in: IET image processing Vol. 14; no. 12; pp. 2937 - 2947
• Main Authors: Hossain, Md Amjad, Khan, Preoyati, Lu, Cheng Chang, Clements, Robert J
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 16.10.2020
• Subjects: application program interfaces; combined results; designed cluster‐based system; developer API; distributed systems; existing 3D‐Object‐Counter plugin; existing plugins; image processing; image processing time; ImageJ plugins; medical image processing; medical images; open‐source application; parallel image processing; pattern clustering; Research Article; single machines; single machine‐based results; specific image processing tasks; Tagged Image File Format; test images; image processing; medical images; existing plugins; application program interfaces; test images; Tagged Image File Format; ImageJ plugins; single machine-based results; specific image processing tasks; single machines; parallel image processing; combined results; existing 3D-Object-Counter plugin; image processing time; pattern clustering; open-source application; developer API; distributed systems; designed cluster-based system; medical image processing
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/iet-ipr.2019.0150

ImageJ is an open-source application widely used for image processing. It has developer API that can be used to implement new plugins for specific image processing tasks. However, ImageJ wasn't designed to work on distributed systems. Currently, it is still being used on single machines to process large medical images, which takes several hours to complete. In this article, we present the approaches to make several essential and widely used ImageJ plugins to work in a cluster. As the cluster nodes parallelly run the existing plugins for image processing, they write the results on a shared drive. But one of the main challenges is, merging those results with high accuracy. Several ImageJ plugins were developed to distribute tasks and generate combined results efficiently. The existing 3D-Object-Counter plugin was used for testing the designed system. The experimental results on the test images of 3D objects stored in Tagged Image File Format(TIFF) show faster processing time with high accuracy and similarity compared to the single machine-based results. The image processing time depends on the number of nodes in the cluster. So, we present a mathematical model that determines the cluster size automatically for optimizing the overall image processing time.