The ImageJ ecosystem: An open platform for biomedical image analysis

Abstract

Technology in microscopy advances rapidly, enabling increasingly affordable, faster, and more precise quantitative biomedical imaging, which necessitates correspondingly more-advanced image processing and analysis techniques. A wide range of software is available-from commercial to academic, special-purpose to Swiss army knife, small to large-but a key characteristic of software that is suitable for scientific inquiry is its accessibility. Open-source software is ideal for scientific endeavors because it can be freely inspected, modified, and redistributed; in particular, the open-software platform ImageJ has had a huge impact on the life sciences, and continues to do so. From its inception, ImageJ has grown significantly due largely to being freely available and its vibrant and helpful user community. Scientists as diverse as interested hobbyists, technical assistants, students, scientific staff, and advanced biology researchers use ImageJ on a daily basis, and exchange knowledge via its dedicated mailing list. Uses of ImageJ range from data visualization and teaching to advanced image processing and statistical analysis. The software's extensibility continues to attract biologists at all career stages as well as computer scientists who wish to effectively implement specific image-processing algorithms. In this review, we use the ImageJ project as a case study of how open-source software fosters its suites of software tools, making multitudes of image-analysis technology easily accessible to the scientific community. We specifically explore what makes ImageJ so popular, how it impacts the life sciences, how it inspires other projects, and how it is self-influenced by coevolving projects within the ImageJ ecosystem.

Figure 1

An unprocessed electron micrograph (left) has minimal contrast, making feature detection difficult. After running the Contrast-Limited Adaptive Histogram Equalization (CLAHE) plugin in ImageJ, the resulting image (right) is suitable for further analysis. The CLAHE plugin has three parameters: block size determines the local-region extents used for histogram equalization; bins determines the number of histogram bins to use in equalization; and max slope limits the maximum changes in contrast in the intensity transfer function. For this image, the following parameters were used: block, 50; bins, 256; max slope, 2.5.

Figure 2

An electron micrograph segmented with the Trainable Weka Segmentation plugin. Solid red lines (class 1: trace 0, 1) and green lines (class 2: trace 0, trace 1) were added manually by the user. The image regions covered by these traces make up the training sets passed to a WEKA classification algorithm. After training, the classifier can be applied to any input dataset. Applying the classifier to an image results in colored regions corresponding to the trained classes, as pictured here.

Figure 3

Drosophila larval nervous system, stitched from a 2 × 3 grid of images assembled in ImageJ (Preibisch 2009). This plugin reads tile coordinates from metadata, then computes the overlap between adjacent tiles to determine each image's output coordinates. Overlapping regions are blended to create a uniform result, allowing visualization of the complete organism at a resolution greater than would otherwise be possible.

Figure 4

ImageJ macro executed in a KNIME workflow. The Find Edges execution shown here, used to identify regions of high contrast, is one of several prepared functions bundled with the ImageJ KNIME node. This node is essentially an ImageJ script editor that is capable of running any ImageJ macro code that is headless-compatible (not requiring a user interface). In this way, users gain access to a significant number of ImageJ functions, coupled with the reproducibility and documentation inherent in KNIME workflows.