Published August 20, 2025
| Version v2.1
Dataset
Open
PhotIQA: A photoacoustic image data set with image quality ratings
Authors/Creators
-
1.
University of Cambridge
-
2.
Medical University of Vienna
Description
To support the development and testing of full- and no-reference IQA measures we assembled PhotIQA, a data set consisting of 1134 photoacoustic (PA) images reconstructed with 3 different algorithms and ratings by 2 experts across five quality properties (overall quality, edge visibility, homogeneity, inclusion and background intensity). To allow full-reference assessment, highly characterised imaging test objects were used, providing a ground truth. A detailed description of the data set can be found in [1], where also baseline experiments give first insights.
We have decided to make the data set available to the research community under the Creative Commons Attribution 4.0 International license. If you use the data in your research, we kindly ask that you reference the repository and the corresponding paper
[1] A. Breger, J.Gröhl, C. Karner, T.R. Else, I. Selby, J. Weir-McCall, C.-B. Schönlieb: PhotIQA: A photoacoustic image data set with image quality ratings, preprint on arXiv: http://arxiv.org/abs/2507.03478, July 2025
Update v2.0 (July 7): quality ratings of more properties are available now, including edge visibility, object homogeneity, intensity (background), intensity (inclusions), overall quality
Update v2.1 (August 20): the z-scores of the raters have been added and updated for mos
Files
data_descriptor.md
Additional details
Funding
- Deutsche Forschungsgemeinschaft
- GR 5824/1 GR 5824/1
- FWF Austrian Science Fund
- Image based Data Evaluation Analyses and Medical Application T 1307