Reliable quality assessment in digital pathology is essential to ensure the diagnostic usability of whole slide images (WSIs), as artifacts introduced during tissue preparation and scanning can degrade image quality and affect clinical interpretation. In this paper, we propose a framework that combines subjective usability evaluation with an objective no-reference quality assessment method. A dataset was constructed from WSIs of four tissue types (breast, fertility, gastrointestinal, and lung), where pristine patches were systematically degraded using simulated artifacts including blur, contrast, and color variations. A subjective study with eight pathologists was conducted using a five-point diagnostic usability scale, from which Mean Usability Scores (MUS) were derived and statistically validated. An objective metric was then developed based on contrastive learning–driven pseudo-reference generation, followed by a siamese feature extraction and regression model to predict usability. The proposed method shows strong correlation with expert scores and outperforms several existing quality assessment metrics, while demonstrating consistent performance across multiple distortion types and tissue categories. Our proposed model outperforms competing objective metrics, achieving strong consistency with subjective scores with SRCC of 0.945, PLCC of 0.952, and AUC of 0.98 on the benchmark dataset. The proposed objective metric, together with the designed subjective assessment method and the publicly available dataset, provides a reliable framework for expert-aligned quality assessment in digital pathology.
Nguyen, T, Mahmoudpour, S, Courtoy, GE, Waelput, W, Forsyth, R, De Vylder, J, Diricx, B, Vandemeulebroucke, J & Schelkens, P 2026, 'Perceptual quality assessment in digital pathology: Modeling diagnostic usability from expert opinions', Computer Methods and Programs in Biomedicine, vol. 285, 109473. https://doi.org/10.1016/j.cmpb.2026.109473
Nguyen, T., Mahmoudpour, S., Courtoy, G. E., Waelput, W., Forsyth, R., De Vylder, J., Diricx, B., Vandemeulebroucke, J., & Schelkens, P. (2026). Perceptual quality assessment in digital pathology: Modeling diagnostic usability from expert opinions. Computer Methods and Programs in Biomedicine, 285, Article 109473. https://doi.org/10.1016/j.cmpb.2026.109473
@article{200cd75d8d7342e8ba925a953666374c,
title = "Perceptual quality assessment in digital pathology: Modeling diagnostic usability from expert opinions",
abstract = "Reliable quality assessment in digital pathology is essential to ensure the diagnostic usability of whole slide images (WSIs), as artifacts introduced during tissue preparation and scanning can degrade image quality and affect clinical interpretation. In this paper, we propose a framework that combines subjective usability evaluation with an objective no-reference quality assessment method. A dataset was constructed from WSIs of four tissue types (breast, fertility, gastrointestinal, and lung), where pristine patches were systematically degraded using simulated artifacts including blur, contrast, and color variations. A subjective study with eight pathologists was conducted using a five-point diagnostic usability scale, from which Mean Usability Scores (MUS) were derived and statistically validated. An objective metric was then developed based on contrastive learning–driven pseudo-reference generation, followed by a siamese feature extraction and regression model to predict usability. The proposed method shows strong correlation with expert scores and outperforms several existing quality assessment metrics, while demonstrating consistent performance across multiple distortion types and tissue categories. Our proposed model outperforms competing objective metrics, achieving strong consistency with subjective scores with SRCC of 0.945, PLCC of 0.952, and AUC of 0.98 on the benchmark dataset. The proposed objective metric, together with the designed subjective assessment method and the publicly available dataset, provides a reliable framework for expert-aligned quality assessment in digital pathology.",
keywords = "Deep learning, Digital pathology, Generative models, Objective metrics, Subjective quality assessment, article, artifact, breast tissue, deep learning, diagnostic value, digital pathology, feature extraction, fertility, gastrointestinal tissue, generative model, human, human tissue, lung parenchyma, methodology, pathologist, quality control, regression model, scoring system, simulation, statistical analysis",
author = "Tien Nguyen and Saeed Mahmoudpour and Courtoy, \{Guillaume E.\} and Wim Waelput and Ramses Forsyth and \{De Vylder\}, Jonas and Bart Diricx and Jef Vandemeulebroucke and Peter Schelkens",
note = "Publisher Copyright: Copyright {\textcopyright} 2026. Published by Elsevier B.V.",
year = "2026",
month = oct,
day = "1",
doi = "10.1016/j.cmpb.2026.109473",
language = "English",
volume = "285",
journal = "Computer Methods and Programs in Biomedicine",
issn = "0169-2607",
publisher = "Elsevier",
}