Automated detection and classification of maxillary sinus variations using slice-based and full-volume CBCT deep learning models.
Authors
Affiliations (9)
Affiliations (9)
- School and Hospital of Stomatology, China Medical University, Liaoning Provincial Key Laboratory of Oral Diseases, China Medical University, Shenyang, 110002, China.
- Center for Implant Dentistry, School and Hospital of Stomatology, Liaoning Provincial Key Laboratory of Oral Disease , China Medical University, Shenyang, China.
- State Key Laboratory of Oral Diseases, West China School of Stomatology, National Clinical Research Centre for Oral Diseases, Med-X Centre for Manufacturing, Chongqing University, Chengdu, 610064, China.
- School and Hospital of Stomatology, China Medical University, Liaoning Provincial Key Laboratory of Oral Diseases, China Medical University, Shenyang, 110002, China. [email protected].
- Department of Oral and Maxillofacial Surgery, School and Hospital of Stomatology, Liaoning Province Key Laboratory of Oral Disease, China Medical University, Shenyang, 110002, China. [email protected].
- College of Computer Science, Chongqing University, Chongqing University Three Gorges Hospital, Chongqing, 400044, China.
- Center for Implant Dentistry, School and Hospital of Stomatology, Liaoning Provincial Key Laboratory of Oral Disease , China Medical University, Shenyang, China. [email protected].
- Chengdu Boltzmann Intelligence Technology Co., Ltd, Chengdu , 610095, China.
- Department of Periodontology and Oral Medicine, College of Dentistry, Ibb University, Ibb, Yemen.
Abstract
This study aimed to develop and compare two deep learning models for automated detection and classification of maxillary sinus variations using cone-beam computed tomography (CBCT): a slice-based two-dimensional (2D) model based on sagittal images and a three-dimensional (3D) volume model using full CBCT volumetric scans. CBCT scans from 452 patients (631 sinuses) were reviewed and categorized into six clinically relevant sinus radiographic variations: normal anatomy, hypoplasia, mucosal thickening, polypoid lesions, septa, and sinus opacification. For the two-dimensional slice-based model, 7,232 sagittal images were initially extracted; after quality screening, 1,880 representative slices were selected for model development. Three convolutional neural network architectures were evaluated, with DenseNet-121 demonstrating the best performance. For the 3D model, all sinuses were manually annotated using 3D Slicer to define inner and outer sinus regions of interest. Both models were independently trained and evaluated using standard classification performance metrics, including sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve. The 2D slice-based evaluation model achieved an overall accuracy of 83.2%, with high sensitivity for septa (0.93), normal anatomy (0.88), and polypoid lesions (0.81); however, it had lower sensitivity for hypoplasia (0.67). The 3D volume-based model demonstrated superior performance, achieving an accuracy of 87.2%, with improved sensitivity for hypoplasia (0.88), mucosal thickening (0.93), and polypoid lesions (0.75), as well as perfect classification of sinus opacification with both sensitivity and specificity: 1.00. Both slice-based and volume-based deep learning models showed strong potential for automated classification of maxillary sinus variations on CBCT images. While the 2D slice-based model offers a fast and computationally efficient approach, the full-volume 3D model benefits from enhanced spatial representation and higher diagnostic precision. These results highlight the potential of Artificial Intelligence as an adjunctive tool in radiographic assessment of the maxillary sinus.