Enhancing clinical CT image quality assessment: adapting no-reference methods NIQE and BRISQUE

This study investigates the application of NIQE and BRISQUE to assess the clinical CT image quality by the example of the LDCTIQAC2023 dataset. Our approach involves refining NIQE to focus the method on relevant anatomical areas, which significantly improves the algorithm score from 1.98 to 2.70, with 3.00 being the maximum achievable score. The adaptation of BRISQUE elevated the performance from a score of 2.12 to 2.58. While BRISQUE-CT required the entire dataset of 1000 quality-labelled images, 87 best-scoring images were sufficient for our refined NIQE-CT method. The findings underscore the potential of NIQE-CT and BRISQUE-CT as effective tools for developing reliable and efficient image quality assessment models for clinical CT scans.