Artificial Intelligence Applications in Paranasal Sinus Imaging

Artificial intelligence (AI) is revolutionising paranasal sinus imaging by enhancing the detection, characterisation and quantification of sinonasal pathology. Advances in deep learning, particularly convolutional neural networks, have enabled automated segmentation of complex sinus anatomy on computed tomography (CT), calculation of radiological severity scores and classification of inflammatory, fungal and neoplastic conditions. Multi-view models applied to standard radiographs rival expert interpretation in recognising frontal, ethmoid and maxillary sinusitis, while three-dimensional architectures facilitate volumetric assessment and self-supervised methods improve feature extraction in the absence of large annotated datasets. These technologies promise standardised reporting, faster turnaround and wider access to specialist-level assessment, especially in resource-limited settings. Ongoing collaboration between engineers, radiologists and otolaryngologists remains essential to validate algorithms across diverse populations, integrate AI seamlessly into clinical workflows and ensure robust regulatory and ethical oversight.

Research from Nature Portfolio

No recent Nature Portfolio content available.

Artificial Intelligence Applications in Paranasal Sinus Imaging publication trend

The graph below shows the total number of articles in artificial intelligence applications in paranasal sinus imaging across all publications each year (not limited to Nature Index journals).

Technical terms

Convolutional neural network: A deep learning architecture composed of layers of convolutional filters designed to automatically extract hierarchical features from imaging data.

Deep learning: A subset of machine learning employing multi-layer neural networks to model complex patterns in large datasets.

Lund–Mackay score: A semiquantitative CT-based scoring system for assessing the extent and severity of paranasal sinus opacification.

Waters’ and Caldwell views: Standard two-dimensional radiographic projections of the paranasal sinuses used for initial screening of sinusitis.

Dice score: A statistical measure of spatial overlap between predicted and ground truth segmentations, ranging from 0 (no overlap) to 1 (perfect overlap).

References

1. NeuroNasal: Advanced AI-Driven Self-Supervised Learning Approach for Enhanced Sinonasal Pathology Detection. Sensors (2025).
2. The use of a convolutional neural network to automate radiologic scoring of computed tomography of paranasal sinuses. BioMedical Engineering OnLine (2025).
3. Deep Learning for Diagnosis of Paranasal Sinusitis Using Multi-View Radiographs. Diagnostics (2021).
4. Detection of maxillary sinus fungal ball via 3-D CNN-based artificial intelligence: Fully automated system and clinical validation. PLOS ONE (2022).