Towards Clinical Integration of Deep Learning-Based Classification of Urinary Sediment Particles from Digital Microscopy Images: A Prospective Study

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: 97% overall accuracy (retrospective), 78% top-1 accuracy (prospective)

• Primary Outcome: Classification accuracy for urinary sediment particle identification

• Nnt Or Sensitivity: Top-3 accuracy: 92% (prospective validation)

• Confidence Interval: Not reported

Clinical Application

Requires Sysmex UD-10 or compatible digital microscopy platform; lightweight model suitable for clinical implementation Relevant to Australian pathology laboratories using automated urinalysis systems; potential for integration with existing TGA-approved platforms Clinical laboratories performing routine urinalysis with digital microscopy capabilities

Abstract

BACKGROUND: Urinalysis is a standard clinical test that includes the microscopic examination of urinary sediment to identify formed elements. Manual evaluation by laboratory technicians is time-intensive and subject to human error. Automated analysis using digital microscopy images presents a potential alternative. This study evaluates the integration of a deep learning approach to automatically classify urinary sediment images in the clinical laboratory, including independent prospective validation of its performance. METHODS: An annotated data set comprising 13 classes of urinary sediment elements was created from a database of Sysmex UD-10 digital microscope images. An EfficientNet-based model was trained and tested across three experimental scenarios to evaluate the effects of data collection strategies on performance. Uncertainty calibration was examined. The model's robustness and interpretability were examined using gradient-weighted class activation mapping (Grad-CAM) to visualize influential image regions and t-distributed stochastic neighbor embedding (t-SNE) to analyze learned feature embeddings. Lastly, a graphical user interface was developed for a prospective evaluation in the laboratory. RESULTS: The model achieved approximately 97% overall accuracy on the test set. Experiments revealed sensitivity to data set variability, suggesting that performance may improve by integrating additional training examples. Confidence scores aligned with accuracy, and interpretability analyses showed that the model focused on relevant image regions and learned embeddings demonstrated clear class separation. In the prospective evaluation, top 1 and top 3 accuracies decreased to approximately 78% and 92%, respectively. CONCLUSIONS: Our results indicate that a lightweight deep learning model can achieve high performance in classifying urine particles. Analysis of discrepancies between retrospective and prospective evaluations provides important insights toward reliable clinical application.

References

1. 1.Mouslech, S. G., Wijnants, S., van der Schagt, A. L., Van Hoovels, L., Deley, R., Oyaert, M., Neirinck, J., Billen, J., Frans, G., & De Vos, M. (2026). Towards Clinical Integration of Deep Learning-Based Classification of Urinary Sediment Particles from Digital Microscopy Images: A Prospective Study. Clinical Chemistry. https://doi.org/10.1093/clinchem/hvaf182