PARASIDE: An Automatic Paranasal Sinus Segmentation and Structure Analysis Tool for MRI

2025-01-24

AI Summary

Chronic rhinosinusitis (CRS) clinical assessment suffers from subjectivity and lack of objective quantification. Method: We propose the first deep learning framework enabling fully automatic segmentation of 16 sinonasal anatomical structures—including maxillary, frontal, sphenoid, and ethmoid sinuses, along with their aerated cavities and soft tissues—on T1-weighted MRI. Our approach integrates anatomical priors and multi-structure joint optimization to achieve precise air/soft-tissue separation. Results: The method achieves excellent cavity segmentation accuracy (Dice >0.92) and robust soft-tissue segmentation. It establishes, for the first time, objective quantitative correlations between air/soft-tissue volumes and signal intensities, and successfully reproduces the Lund-Mackay scoring system. Validation confirms significantly lower soft-tissue volume and signal intensity in healthy controls versus CRS patients (p<0.001), demonstrating statistically significant concordance between imaging biomarkers and clinical reporting—overcoming key limitations of manual interpretation.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Neuro-Symbolic Learning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Machine learning and data science for the Web

Abstract

Chronic rhinosinusitis (CRS) is a common and persistent sinus imflammation that affects 5 - 12% of the general population. It significantly impacts quality of life and is often difficult to assess due to its subjective nature in clinical evaluation. We introduce PARASIDE, an automatic tool for segmenting air and soft tissue volumes of the structures of the sinus maxillaris, frontalis, sphenodalis and ethmoidalis in T1 MRI. By utilizing that segmentation, we can quantify feature relations that have been observed only manually and subjectively before. We performed an exemplary study and showed both volume and intensity relations between structures and radiology reports. While the soft tissue segmentation is good, the automated annotations of the air volumes are excellent. The average intensity over air structures are consistently below those of the soft tissues, close to perfect separability. Healthy subjects exhibit lower soft tissue volumes and lower intensities. Our developed system is the first automated whole nasal segmentation of 16 structures, and capable of calculating medical relevant features such as the Lund-Mackay score.

Problem

• MRI analysis
• Chronic Sinusitis Evaluation
• Automated Diagnosis Tool

Innovation

• PARASIDE
• MRI sinus analysis
• Lund-Mackay scoring