Integration of the ImageJ Ecosystem in the KNIME Analytics Platform

Abstract

Open-source software tools are often used for analysis of scientific image data due to their flexibility and transparency in dealing with rapidly evolving imaging technologies. The complex nature of image analysis problems frequently requires many tools to be used in conjunction, including image processing and analysis, data processing, machine learning and deep learning, statistical analysis of the results, visualization, correlation to heterogeneous but related data, and more. However, the development, and therefore application, of these computational tools is impeded by a lack of integration across platforms. Integration of tools goes beyond convenience, as it is impractical for one tool to anticipate and accommodate the current and future needs of every user. This problem is emphasized in the field of bioimage analysis, where various rapidly emerging methods are quickly being adopted by researchers. ImageJ is a popular open-source image analysis platform, with contributions from a global community resulting in hundreds of specialized routines for a wide array of scientific tasks. ImageJ's strength lies in its accessibility and extensibility, allowing researchers to easily improve the software to solve their image analysis tasks. However, ImageJ is not designed for development of complex end-to-end image analysis workflows. Scientists are often forced to create highly specialized and hard-to-reproduce scripts to orchestrate individual software fragments and cover the entire life-cycle of an analysis of an image dataset. KNIME Analytics Platform, a user-friendly data integration, analysis, and exploration workflow system, was designed to handle huge amounts of heterogeneous data in a platform-agnostic, computing environment and has been successful in meeting complex end-to-end demands in several communities, such as cheminformatics and mass spectrometry. Similar needs within the bioimage analysis community led to the creation of the KNIME Image Processing extension which integrates ImageJ into KNIME Analytics Platform, enabling researchers to develop reproducible and scalable workflows, integrating a diverse range of analysis tools. Here we present how users and developers alike can leverage the ImageJ ecosystem via the KNIME Image Processing extension to provide robust and extensible image analysis within KNIME workflows. We illustrate the benefits of this integration with examples, as well as representative scientific use cases.

Keywords: Bioimaging; Fiji; ImageJ; KNIME; computational workflows; image analysis; interoperability; open-source.

Figure 1:

An ImageJ Macro node performing image segmentation and feature extraction.

Figure 2:

An ImageJ command for low-pass filtering used as a KNIME node.

Figure 3:

An example Java Snippet node operating on an image region of interest using ImgLib2 libraries.

Figure 4:

Side-by-side comparison of ImageJ macro with KNIME workflow using KNIME Image Processing nodes.

Figure 5:

Quantitative analysis of subcellular structures. To analyze the consequences of disrupting the cytoskeleton on matrix adhesion focal adhesion complex formation is visualized using TIRF imaging. A KNIME workflow was leveraged to define the number of focal adhesion complexes at the periphery of the cell vs. within the center of the cell using sequential steps with discrete objectives: I. Read file in, II. Processing of the images into labels that capture the individual focal adhesion complexes, III. Arithmetic on the labels to obtain the characteristics (features) for classification, IV. Classification of the labels using extracted features, V. Visualization of the classified focal adhesion complexes (periphery vs center). Note that the output of this pipeline is a combination of visualization and quantitation. Both of these can be leveraged for further analysis.

Figure 6:

Quantitative analysis of histological stain. The histological staining of a cell adhesion marker (CD166) related to tumor invasion and metastasis demonstrates significant variation across patient samples. As in user case #1, the KNIME workflow was divided into sequential steps that complete discrete objectives: 1) read in file , 2) pre-processing of the images and their annotation in preparation for analysis using ImageJ2 functionalities, 3) pixel classification using Weka-bases machine learning functionality, 4) post-classification processing of image data to labels that correspond to ‘positive’, 5) compilation of labels, images and annotations, 6) visualization of the quantitation by overlaying the labels with the original image.

Figure 7:

A KNIME workflow for channel-shift correction and particle tracking. The positions of bead detections are shown in three-pane scatter plots, before (left) and after (right) applying channel-shift correction. The density plots show absolute distances between apparent bead locations of two channels before (red) and after (cyan) correction.

Figure 8:

R1881 treatment shows nuclear translocation of the Androgen Receptor in LNCaP cells. (A) LNCaP cells were either left non-treated or treated with 1nM R1881. Under R1881 treatment conditions, AR localization shifts from nuclear and cytoplasmic to primarily nuclear. (B) xy scatter plot of the mean fluorescence intensity (MFI) of the cytoplasm (x) and the nucleus (y). The size of the point denotes sum of the cytoplasmic and nuclear signal (i.e. total cell signal). Treating LNCaP cells with R1881 induces a shift into the nucleus and increase in signal inside the nucleus. (C) A linear regression plot depicting the clear separation of the populations.