Deep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks
Clinical Snapshot
PICO Framework
| P — Population | Healthy volunteers (oral cavity imaging) and patients with cervical specimens containing precancerous lesions |
| I — Intervention | PrecisionView deep learning-enabled endomicroscope with phase mask optimization |
| C — Comparator | Conventional in vivo microscopy (IVM) systems |
| O — Outcomes | Diagnostic accuracy for detecting epithelial cell nuclear morphology and subsurface microvasculature patterns; field-of-view (20 mm²), depth-of-field (500 µm), and resolution (4 µm) performance metrics |
Bottom Line
PrecisionView represents a significant technological advancement in endomicroscopy, offering substantially improved field-of-view and depth-of-field compared to conventional systems. The device successfully demonstrates real-time imaging of cellular and vascular structures relevant to cancer detection. However, this study appears to focus primarily on technical validation rather than clinical diagnostic accuracy. Critical gaps include the absence of sensitivity/specificity data, unclear reference standards, and limited information about diagnostic performance compared to current screening methods. While the technology shows promise for point-of-care cancer screening, robust clinical validation studies with appropriate diagnostic accuracy endpoints are needed before clinical implementation. The enhanced imaging capabilities could potentially improve early detection of epithelial precancers, but evidence of clinical utility and impact on patient outcomes remains to be demonstrated.
Key Findings
P Value: Not reported
Effect Size: 5× increase in FOV and 8× larger DOF compared to conventional IVM
Primary Outcome: Technical performance: 20 mm² field-of-view, 500 µm depth-of-field, 4 µm resolution
Nnt Or Sensitivity: Sensitivity and specificity not reported
Confidence Interval: Not reported
Clinical Application
Point-of-care application claimed but requires validation of practical implementation, training requirements, and cost-effectiveness Could potentially enhance cervical screening programs under National Cervical Screening Program guidelines, but would require TGA approval and demonstration of clinical utility before PBS consideration Patients requiring screening for epithelial precancerous lesions, particularly cervical and oral cavity examinations
Abstract
In vivo microscopy (IVM) has shown great promise to improve early detection of epithelial precancer, but it suffers from fundamental trade-offs that limit the resolution, field-of-view (FOV) and depth-of-field (DOF). Here, we present PrecisionView, a compact, deep learning-enabled endomicroscope that breaks these constraints and achieves 20 mm2 FOV and 500 µm DOF with 4 µm resolution, representing approximately 5× increase in FOV and 8× larger DOF compared to conventional IVM with similar resolution. PrecisionView integrates a deep learning-optimized phase mask and real-time reconstruction, enabling rapid in vivo assessment of two key hallmarks of cancer: epithelial cell nuclear morphology and subsurface microvasculature through fluorescence and reflectance imaging. By imaging the oral cavity of healthy volunteers and cervical specimens with precancerous lesions, PrecisionView generates large-scale (1 to 3 cm2) coregistered maps of cellular and vascular structures, revealing distinct microscopic patterns associated with anatomic structures and precancerous lesions. Our results suggest the potential of this computational endomicroscope to address the unmet need for early cancer detection at the point of care.
References
- 1.Hou, H., Wu, J., Liu, J., Boominathan, V., Shende, A., Goli, K., Carns, J., Schwarz, R. A., Gillenwater, A. M., Ramalingam, P., Salcedo, M. P., Schmeler, K. M., Tkaczyk, T. S., Robinson, J. T., Veeraraghavan, A., & Richards-Kortum, R. R. (2026). Deep-learning endomicroscope with large field-of-view and depth-of-field for real-time in vivo imaging of epithelial cancer hallmarks. Proceedings of the National Academy of Sciences, 123. https://doi.org/10.1073/pnas.2602705123
Related Research
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
3 Aug 2026
Current opinion in chemical biology
Prediction of protein-protein interactions and co-complex models with deep learning
3 Aug 2026
European journal of radiology
A CT-based deep learning model to differentiate between benign and malignant adrenal lesions
3 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service