What does this research mean for the field?

A convolutional neural network-based medical decision making support system can accurately classify digital diaphanograms to detect and differentiate maxillary sinus pathologies, achieving a sensitivity of 0.95 and specificity of 0.88. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop a medical decision making support system (MDMSS) for classifying maxillary sinus diaphanograms using a convolutional neural network.

March 29, 2026Russian Rhinology

Classification of maxillary sinus states according to digital diaphanoscopy with the use of machine learning

View Full Paper

Ask AI

Bookmark

Authors

EBE.O. Bryanskaya DGD.V. Gerasin ABA.V. Bakotina

Discussion

Member takes

Overview

Analysis classifies maxillary sinus conditions in patients, suggesting improved diagnostic accuracy for treatments.

Key Points

Develop a medical decision making support system (MDMSS) for classifying maxillary sinus diaphanograms using a convolutional neural network.
Involved 80 healthy volunteers and 76 patients with maxillary sinus pathology.
Used digital diaphanoscopy at wavelengths of 650 and 850 nm.
Analyzed 160 healthy diaphanograms, 78 sinusitis, and 32 cystic diaphanograms with ResNet-50 CNN.
Achieved a sensitivity of 0.95 and specificity of 0.88 for classification.
Exceeding previous linear discriminant analysis methods in accuracy.
Successfully differentiated between sinusitis and cystic fluid classes.

Cite This Study

Bryanskaya et al. (2026) studied this question.

synapsesocial.com/papers/69c8c34bde0f0f753b39def2 https://doi.org/10.17116/rosrino20263401119

View Full Paper

Ask AI

Bookmark

March 29, 2026Russian Rhinology

Classification of maxillary sinus states according to digital diaphanoscopy with the use of machine learning

View Full Paper

Ask AI

Bookmark

Authors

EBE.O. Bryanskaya DGD.V. Gerasin ABA.V. Bakotina

Discussion

Member takes

Overview

Analysis classifies maxillary sinus conditions in patients, suggesting improved diagnostic accuracy for treatments.

Key Points

Develop a medical decision making support system (MDMSS) for classifying maxillary sinus diaphanograms using a convolutional neural network.
Involved 80 healthy volunteers and 76 patients with maxillary sinus pathology.
Used digital diaphanoscopy at wavelengths of 650 and 850 nm.
Analyzed 160 healthy diaphanograms, 78 sinusitis, and 32 cystic diaphanograms with ResNet-50 CNN.
Achieved a sensitivity of 0.95 and specificity of 0.88 for classification.
Exceeding previous linear discriminant analysis methods in accuracy.
Successfully differentiated between sinusitis and cystic fluid classes.

Cite This Study

Bryanskaya et al. (2026) studied this question.

synapsesocial.com/papers/69c8c34bde0f0f753b39def2 https://doi.org/10.17116/rosrino20263401119

View Full Paper

Ask AI

Bookmark