Towards Recommendations and Guidelines for Subjective Medical Image and Video Quality Assessment

Evaluating the quality of medical images is a critical step in developing precise, trustworthy, and clinically applicable image processing algorithms and machine learning models for medical imaging applications. This evaluation serves to both benchmark and optimize algorithms. However, there is a lack of standard or guidelines for conducting subjective Medical Image and Video Quality Assessment (MIVQA) tests. Although there are existing standards for natural image and video quality assessment that provide information on selecting images and video sequences, assessor types and numbers, subjective testing procedures (test environment, participant selection, methodology, etc.) and model performance evaluation, they are not tailored to medical images. Although this study does not aim to propose a comprehensive method for MIVQA subjective tests, it addresses several aspects that may be worth considering when a MIVQA subjective test is conducted.