We present a method for measuring small, discrete features near the resolution limit of X-ray computed tomography (CT) data volumes with the aim of providing consistent answers across instruments and data resolutions. The appearances of small features are impacted by the partial volume effect and blurring due to the data point-spread function, and we call our approach the partial-volume and blurring (PVB) method. Features are segmented to encompass their total attenuation signal, which is then converted to a volume, in turn allowing a subset of voxels to be used to measure shape and orientation. We demonstrate the method on a set of gold grains, scanned with two instruments at a range of resolutions and with various surrounding media. We recover volume accurately over a factor of 27 range in grain volume and factor of 5 range in data resolution, successfully characterizing particles as small as 5.4 voxels in true volume. Shape metrics are affected variably by resolution effects and are more reliable when based on image-based caliper measurements than perimeter length or surface area. Orientations are reproducible when maximum or minimum axis lengths are sufficiently different from the intermediate axis. Calibration requires end-member CT numbers for the materials of interest, which we obtained empirically; we describe a first-principles calculation and discuss its challenges. The PVB method is accurate, reproducible, resolution invariant, and objective, all important improvements over any method based on global thresholds.
Plain Language SummaryWe present a method for measuring small, discrete features, such as mineral grains or pores, in scans of solid objects produced by X-ray computed tomography. Our method is aimed at giving the same answer for feature size, shape, and orientation regardless of the data resolution, as long as the feature is larger than the detection limit. We demonstrate the method on a series of gold grains, notable for their high density and unusual shapes. We find that our method gives results that are superior to the usual approach of using a threshold, or constant gray value, to identify which data voxels (pixels with volume) show the feature of interest.
Key Points:• We present an accurate, reproducible, resolution-invariant, objective means for measuring small features in X-ray CT data sets • The method is demonstrated on gold particles spanning a 27 times range in volume over a 5 times range in data resolution • Threshold-based segmentation is inaccurate for features with one or more dimensions close to the data point-spread function