Using signal-to-noise ratio to connect the quality assessment of natural and medical images

Medical image quality assessment (MIQA) is highly related to content interpretation and disease diagnosis in medical community. However, a few metrics have been developed. On the contrary, massive models have been designed for natural image quality assessment (NIQA) in the field of computer vision. Connect both sides of MIQA and NIQA is useful and challenging. This study explores signal-to-noise ratio (SNR) as the intermediate metric to bridge the gap between MIQA and NIQA and consequently, models for NIQA can be employed or modified for MIQA applications. A number of 411 images from 4 magnetic resonance (MR) imaging sequences are collected. First, the consistency of SNR in MIQA is validated which involves inter-rater and intra-rater (inter-session) reliability analysis. Then, 4 NIQA models (BIQI, BLIINDS-II, BRISQUE and NIQE) are evaluated on these MR images. After that, the correlation between SNR values and NIQA results are analyzed. Statistical analysis indicates that SNR measurement shows reliability regard to different raters in each sequence. Moreover, BLIINDS-II and BRISQUE have the potential for automated MIQA tasks. This study attempts to use SNR bridging the gap between MIQA and NIQA, and a large-scale experiment should be further conducted to verify the conclusion.