Use of the cross-correlation component of the multiscale structural similarity metric (R metric) for the evaluation of medical images

Abstract

Purpose: The aim of the present work is to analyze the potential of the cross-correlation component of the multiscale structural similarity metric (R*) to predict human performance in detail detection tasks closely related with diagnostic x-ray images. To check the effectiveness of R, the authors have initially applied this metric to a contrast detail detection task.

Methods: Threshold contrast visibility using the R* metric was determined for two sets of images of a contrast-detail phantom (CDMAM). Results from R and human observers were compared as far as the contrast threshold was concerned. A comparison between the R* metric and two algorithms currently used to evaluate CDMAM images was also performed.

Results: Similar trends for the CDMAM detection task of human observers and R* were found in this study. Threshold contrast visibility values using R* are statistically indistinguishable from those obtained by human observers (F-test statistics: p > 0.05).

Conclusions: These results using R* show that it could be used to mimic human observers for certain tasks, such as the determination of contrast detail curves in the presence of uniform random noise backgrounds. The R* metric could also outperform other metrics and algorithms currently used to evaluate CDMAM images and can automate this evaluation task.