GIFT: An ImageJ macro for automated fiber diameter quantification

Abstract

This paper details the development and testing of the GIFT macro, which is a freely available program for ImageJ for the automated measurement of fiber diameters in SEM images of electrospun materials. The GIFT macro applies a validated method which distinguishes fiber diameters based on distance frequencies within an image. In this work, we introduce an applied version of the GIFT method which has been designed to be user-friendly while still allowing complete control over the various parameters involved in the image processing steps. The macro quickly processes large data sets and creates results that are reproducible and accurate. The program outputs both raw data and fiber diameter averages, so that the user can quickly assess the results and has the opportunity for further analysis if desired. The GIFT macro was compared directly to other software designed for fiber diameter measurements and was found to have comparable or lower average error, especially when measuring very small fibers, and reduced processing times per image. The macro, detailed instructions for use, and sample images are freely available online (https://github.com/IBMTRostock/GIFT). We believe that the GIFT macro is a valuable new tool for researchers looking to quickly, easily and reliably assess fiber diameters in electrospun materials.

Fig 1. Diagram of image processing pathway of the GIFT macro.

A) User-defined image processing parameters can be modified in the GIFT graphical user interface. These parameters are applied either to a single image or a batch of images in a single folder. B) Edge detection and thresholding is performed and then a set of rotated copies is made. An opening line filter is applied to isolate horizontal edge segments on each rotated image and the vertical distances between horizontal edge segments are measured. In the figure, the green arrows indicate the actual fiber diameter, which appears with a significantly high frequency in the image. Distances between fibers (orange arrows) are randomly distributed. C) Vertical distances are plotted as a histogram and a Gaussian fit is used to determine average fiber diameter. Users are provided with histograms and raw data for each image and a summary table with all average diameters.

Fig 2. Real world image analysis.

A) SEM images of electrospun fibers made from 10, 15 or 20% gelatin solutions. Manual fiber diameter measurements were made on 10 random fibers in each image. B) This SEM image set was also used to test the GIFT macro. The images were analyzed using default GIFT parameters. For comparison, the GIFT results were graphed with the results of hand measurement and DiameterJ and SIMPoly analysis of the same images. C) The fiber diameter histograms produced by the GIFT macro for each SEM image are shown. The x-axis units are μm. The blue line overlaid on the histograms represents the Gaussian fit curve. The parameters of the Gaussian fit are shown in the upper left corner.

Fig 3. GIFT parameter sensitivity.

SEM images of 10, 15 or 20% gelatin electrospun fibers were analyzed using the GIFT macro with 90, 45 or 6° angles of rotation and at all combinations of 4–12 pixel line length and 2–8% threshold parameters. The resulting fiber diameter measurements were graphed as heatmaps to visualize sensitivity of GIFT to changes in parameters. All graphs for each image (rows) have the same scale, with the fiber diameter measured with default parameters set as the midpoint of the scale bar (yellow color). Average diameters higher than the default are represented by increasingly red hues and diameter results lower than the default are increasingly blue in color. The black dots indicate the results under default parameters for reference.