What does this research mean for the field?

A custom deep learning workflow utilizing multi-view classification, segmentation, and feature extraction can accurately detect and differentiate maxillary sinusitis of endodontic origin from normal and non-endodontic sinusitis in cone-beam CT images. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to detect maxillary sinusitis of endodontic origin using deep learning algorithms applied to CBCT images.

May 28, 2026Scientific ReportsOpen Access

Detection of maxillary sinusitis of endodontic origin in cone-beam CT images using deep learning algorithms

View Full Paper

Ask AI

Bookmark

Authors

OSOmar Ayman Saleh Sherif NTNora Saif Taha AFAhmed Maged Fahmy

Discussion

Member takes

Overview

Randomized trial shows detection of maxillary sinusitis in images, indicating improved diagnosis efficiency.

Key Points

The study aims to detect maxillary sinusitis of endodontic origin using deep learning algorithms applied to CBCT images.
Retrospective collection and examination of CBCT scans labeled into NMS, MSEO, and MS-NEO.
Development of a custom model for anatomical classification and segmentation before feature extraction.
Evaluation of model performance using Accuracy, Precision, Recall, F1, and DICE scores on testing and external datasets.
Anatomic classifier achieved Accuracy, Precision, Recall, and F1 scores of 0.99 and 0.98 on testing and external datasets.
DICE scores for sagittal, coronal, and axial segmenters were 0.8, 1, and 0.9 on the testing dataset, respectively.
The Multi-View classifier provided excellent metrics across datasets, enhancing clinical diagnosis of MSEO.

Cite This Study

Sherif et al. (2026) studied this question.

synapsesocial.com/papers/6a17dd123fad632b0f9d9d06 https://doi.org/10.1038/s41598-026-52147-w

View Full Paper

Ask AI

Bookmark

May 28, 2026Scientific ReportsOpen Access

Detection of maxillary sinusitis of endodontic origin in cone-beam CT images using deep learning algorithms

View Full Paper

Ask AI

Bookmark

Authors

OSOmar Ayman Saleh Sherif NTNora Saif Taha AFAhmed Maged Fahmy

Discussion

Member takes

Overview

Randomized trial shows detection of maxillary sinusitis in images, indicating improved diagnosis efficiency.

Key Points

The study aims to detect maxillary sinusitis of endodontic origin using deep learning algorithms applied to CBCT images.
Retrospective collection and examination of CBCT scans labeled into NMS, MSEO, and MS-NEO.
Development of a custom model for anatomical classification and segmentation before feature extraction.
Evaluation of model performance using Accuracy, Precision, Recall, F1, and DICE scores on testing and external datasets.
Anatomic classifier achieved Accuracy, Precision, Recall, and F1 scores of 0.99 and 0.98 on testing and external datasets.
DICE scores for sagittal, coronal, and axial segmenters were 0.8, 1, and 0.9 on the testing dataset, respectively.
The Multi-View classifier provided excellent metrics across datasets, enhancing clinical diagnosis of MSEO.

Cite This Study

Sherif et al. (2026) studied this question.

synapsesocial.com/papers/6a17dd123fad632b0f9d9d06 https://doi.org/10.1038/s41598-026-52147-w

View Full Paper

Ask AI

Bookmark