A study of why we need to reassess full reference image quality assessment with medical images
🤖 AI Summary
Conventional full-reference image quality assessment (FR-IQA) metrics—such as PSNR and SSIM—exhibit systematic failure in medical imaging, as they neglect anatomical structure, diagnostic semantics, and clinical task relevance, leading to weak or even negative correlation with radiologist perception and diagnostic accuracy.
Method: We construct the first cross-modal FR-IQA failure evidence atlas covering MRI, CT, OCT, X-ray, digital pathology, and photoacoustic imaging, grounded in quantitative experiments on multicenter real-world data and perceptual validation by radiology and ophthalmology experts.
Contribution/Results: We propose a paradigm-restructuring framework for clinically trustworthy AI-driven FR-IQA evaluation, comprising medical-specific assessment principles, practical guidelines, and recommendations for open-source benchmark development. This work provides both theoretical foundations and empirical evidence to advance standardized, task-aware medical IQA.
Application Category
📝 Abstract
Image quality assessment (IQA) is indispensable in clinical practice to ensure high standards, as well as in the development stage of machine learning algorithms that operate on medical images. The popular full reference (FR) IQA measures PSNR and SSIM are known and tested for working successfully in many natural imaging tasks, but discrepancies in medical scenarios have been reported in the literature, highlighting the gap between development and actual clinical application. Such inconsistencies are not surprising, as medical images have very different properties than natural images, and PSNR and SSIM have neither been targeted nor properly tested for medical images. This may cause unforeseen problems in clinical applications due to wrong judgment of novel methods. This paper provides a structured and comprehensive overview of examples where PSNR and SSIM prove to be unsuitable for the assessment of novel algorithms using different kinds of medical images, including real-world MRI, CT, OCT, X-Ray, digital pathology and photoacoustic imaging data. Therefore, improvement is urgently needed in particular in this era of AI to increase reliability and explainability in machine learning for medical imaging and beyond. Lastly, we will provide ideas for future research as well as suggesting guidelines for the usage of FR-IQA measures applied to medical images.
Problem
Research questions and friction points this paper is trying to address.
Reassess FR-IQA for medical imaging accuracy
PSNR, SSIM unsuitable for medical image evaluation
Need improved AI reliability in medical imaging
Innovation
Methods, ideas, or system contributions that make the work stand out.
Reassess FR-IQA for medical images
Highlight PSNR and SSIM limitations
Propose new FR-IQA guidelines
🔎 Similar Papers
No similar papers found.
