SIMPoly: A Matlab-Based Image Analysis Tool to Measure Electrospun Polymer Scaffold Fiber Diameter

Abstract

Quantifying fiber diameter is important for characterizing electrospun polymer scaffolds. Many researchers use manual measurement methods, which can be time-consuming and variable. Semi-automated tools exist, but there is room for improvement. The current work used Matlab to develop an image analysis program to quickly and consistently measure fiber diameter in scanning electron micrographs. The new Matlab method, termed "SIMPoly" (Semiautomated Image Measurements of Polymers) was validated by using synthetic images with known fiber size and was found to be accurate. The Matlab method was also applied by three different researchers to scanning electron microscopy (SEM) images of electrospun poly(lactic-co-glycolic acid) (PLGA). Results were compared with the semi-automated DiameterJ method and a manual ImageJ measurement approach, and it was found that the Matlab-based SIMPoly method provided measurements in the expected range and with the least variability between researchers. In conclusion, this work provides and describes SIMPoly, a Matlab-based image analysis method that can simply and accurately measure polymer fiber diameters in SEM images with minimal variation between users.

Keywords: Matlab tool; electrospinning; electrospun scaffolds; polymer fiber measurement.

FIG. 1.

The SIMPoly algorithm includes an initial built-in step that uses the SEM micrograph scale bar to convert pixels to micrometers. This allows fiber diameter measurements to be output in microns. If the micrometer/pixel ratio is already known, it can be entered without measurement of the scale bar, or if it is unknown but there is no scale bar, the output will be in pixels. SEM, scanning electron microscopy; SIMPoly, Semiautomated Image Measurements of Polymers.

FIG. 2.

Diagram of the overall workflow in the SIMPoly fiber analysis algorithm. Starting with an original image (A), image processing steps include contrast enhancement through histogram equalization (B), reconstruction to brighten desired fibers (C), edge overlay for later background noise removal (D), thresholding for initial removal of background noise (E), image dilation and erosion for “closing” to correct any gaps created from previous filtering step (F), median filter application to smooth fiber edges and remove any leftover noise (G), dilation of fibers to brighten edges to normal size without presence of background noise (H), and skeletonization of image and overlay of skeleton onto the binary image (I). Color images are available online.

FIG. 3.

Workflow for manual fiber diameter measurements using ImageJ. Original SEM images were selected and opened in ImageJ (A) and enhanced (B). Then, a 5 × 5 circle template was overlaid onto each image and 25 fiber diameter measurements were made by using the line tool to manually measure the fiber closest to the middle of each circle (C).

FIG. 4.

Example output of the SIMPoly algorithm after analyzing a PLGA nanofiber image. (A) Original SEM Image. (B) Color map displaying distribution of fibers based on standard deviation. (C) Command Window displaying average diameter and standard deviation of fiber diameter measurements in pixels and microns. (D) Histogram of measured fibers with Gaussian curve fit over data. PLGA, poly(lactic-co-glycolic acid). Color images are available online.

FIG. 5.

Bar graph displaying the actual diameter versus the diameter measured by using the SIMPoly method for each synthetic image. The average percent error between the measured and known diameters was 2.1% for the synthetic ordered images, and 1.6% for the synthetic disordered images. Color images are available online.

FIG. 6.

Bar graph displaying the average fiber diameter measurements made by each researcher using each of the three analysis methods (manual ImageJ, DiameterJ, and Matlab-based SIMPoly) for the PLGA nanofiber images. Although there is no known “true” fiber size for these samples, the new Matlab-based SIMPoly method provided appropriate fiber diameter measurements, as compared with the more well-established manual and DiameterJ approaches, and the SIMPoly method had the least variation between researchers. Color images are available online.