Intracranial Calcification Detection; a Comparison Between Micro-CT, Conventional CT and Ultra-high-resolution Photon-Counting Detector CT

Abstract

Rationale and Objectives

To evaluate the performance of photon-counting detector CT (PCD-CT) in identifying and quantifying intracranial calcifications compared to conventional energy-integrating CT (EID-CT), utilizing micro-CT (µCT) as benchmark.

Method

Thirty cross-sectional histopathological samples of the intracranial arteries were scanned using PCD-CT, EID-CT and µCT. Scans were optimized for µCT for maximum image quality, while clinical protocols were followed for PCD-CT and EID-CT. Additional reconstruction kernels (EID-CT: Hv40/Hv49/Hv59, PCD-CT: Hv40/Hv48/Hv56/Hv64/Hv72/Hv89) were used to enhance the spatial resolution. Two observers evaluated calcification presence subjectively, using Cohen's kappa (κ) and concordance percentages. Mass scores were utilized to objectively analyze calcium detection using intraclass correlation coefficients and Bland–Altman plots.

Results

Observer 1 detected calcifications in 24 samples and Observer 2 in 23 samples using µCT (90% concordance, κ = 0.706). The highest agreement was with EID-CT Hv59 (97% concordance, κ = 0.911), but calcium detection rates were low (observer 1; 27%, observer 2: 25%) compared to µCT. The most optimal results of calcium detection were obtained with PCD-CT Hv48 (observer 1: concordance = 90%, κ = 0.706) and PCD-CT Hv56 (observer 2: concordance 77%, κ = 0.314) compared to μCT. Mass scores revealed the highest detection rate with PCD-CT Hv64 but also increased noise levels compared to softer kernels (<Hv56). Hv48/Hv56 kernels with PCD-CT were considered most optimal, which yielded sensitivity, specificity, and accuracy of 83%/92%, 50%/83%, and 77%/90%, respectively, for observers 1 and 2.

Conclusion

PCD-CT outperformed EID-CT in detecting intracranial calcifications compared to µCT. Reconstructions with Hv48 or Hv56 kernels are recommended, considering the noise increase with sharper kernels.