Evaluation of generative models for synthetic CT images using SINGHA, a new spectrally informed metric

Motivation: Synthetic CT (sCT) based on MRI could improve the characterization of bone pathology by estimating bone mineral density and providing a high level of structural details. However, evaluating the performance of sCT is challenging in both respects. Goal(s): To propose an evaluation framework for sCT that quantifies accuracy both in terms of image intensity and depiction of structural details. Approach: We propose the new frequency-based metric SINGHA that captures the sharpness difference between images. Results: SINGHA was complementary to standard metrics and captured differences in high frequency content, thereby contributing to a more comprehensive evaluation of sCT images. Impact: Using the newly introduced Spectrally-INformed Grading of High-frequency Attributes (SINGHA) in conjunction with standard intensity-based metrics enables to simultaneously evaluate synthetic CT accuracy in terms of bone mineral density and sharpness.