Researchers have developed RIQE, a new reference model for evaluating the quality of computed tomography (CT) images. Similar to the Natural Image Quality Evaluator (NIQE), RIQE is trained on medical imaging data rather than photographs. It was fitted on 3,792 full-dose CT slices and tested on reduced-dose reconstructions, where it successfully ranked degraded images as worse than their full-dose counterparts in most cases. However, the model's preferences for filtered images did not consistently align with lesion detectability, suggesting it should not be the sole criterion for selecting or tuning image processing techniques. AI
RANK_REASON The item describes a new research paper introducing a novel evaluation model for medical imaging. [lever_c_demoted from research: ic=1 ai=0.4]
- computed tomography
- LDCT-and-Projection-data
- Natural Image Quality Evaluator
- Radiology Image Quality Evaluator
- RIQE
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →