# A study on the adequacy of common IQA measures for medical images

arXiv: https://arxiv.org/abs/2405.19224 · HTML: https://mlsanity.com/paper/2405.19224/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 35 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 12 of 12)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [fastMRI: An Open Dataset and Benchmarks for Accelerated MRI](https://mlsanity.com/paper/1811.08839/) (2018)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessment](https://mlsanity.com/paper/1607.06140/) (2016)
- [Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluator](https://mlsanity.com/paper/1608.07433/) (2016)
- [A Hitchhiker's Guide to Structural Similarity](https://mlsanity.com/paper/2101.06354/) (2021)
- [XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge](https://mlsanity.com/paper/2010.07290/) (2020)
- [Moving beyond simulation: data-driven quantitative photoacoustic imaging using tissue-mimicking phantoms](https://mlsanity.com/paper/2306.06748/) (2023)
- [Artifact- and content-specific quality assessment for MRI with image rulers](https://mlsanity.com/paper/2111.03780/) (2021)

## Built on by (most cited first, 10 of 10)

- [Digital twins enable full-reference quality assessment of photoacoustic image reconstructions](https://mlsanity.com/paper/2505.24514/) (2025)
- [Parameter choices in HaarPSI for IQA with medical images](https://mlsanity.com/paper/2410.24098/) (2024)
- [A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis](https://mlsanity.com/paper/2509.16582/) (2025)
- [Learned denoising with simulated and experimental low-dose CT data](https://mlsanity.com/paper/2408.08115/) (2024)
- [Pathology-Guided Virtual Staining Metric for Evaluation and Training](https://mlsanity.com/paper/2507.12624/) (2025)
- [IXGS-Intraoperative 3D Reconstruction from Sparse, Arbitrarily Posed Real X-rays](https://mlsanity.com/paper/2504.14699/) (2025)
- [HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models](https://mlsanity.com/paper/2504.18405/) (2025)
- [PhotIQA: A photoacoustic image data set with image quality ratings](https://mlsanity.com/paper/2507.03478/) (2025)
- [No-reference based automatic parameter optimization for iterative reconstruction using a novel search space aware crow search algorithm](https://mlsanity.com/paper/2604.06246/) (2026)
- [Design Choices in Splitting-Based Self-Supervised Sparse-View CT Reconstruction](https://mlsanity.com/paper/2607.10898/) (2026)

## Abstract (arXiv)

Image quality assessment (IQA) is standard practice in the development stage of novel machine learning algorithms that operate on images. The most commonly used IQA measures have been developed and tested for natural images, but not in the medical setting. Reported inconsistencies arising in medical images are not surprising, as they have different properties than natural images. In this study, we test the applicability of common IQA measures for medical image data by comparing their assessment to manually rated chest X-ray (5 experts) and photoacoustic image data (2 experts). Moreover, we include supplementary studies on grayscale natural images and accelerated brain MRI data. The results of all experiments show a similar outcome in line with previous findings for medical images: PSNR and SSIM in the default setting are in the lower range of the result list and HaarPSI outperforms the other tested measures in the overall performance. Also among the top performers in our experiments are the full reference measures FSIM, LPIPS and MS-SSIM. Generally, the results on natural images yield considerably higher correlations, suggesting that additional employment of tailored IQA measures for medical imaging algorithms is needed.