Back to the list
Congress: ECR25
Poster Number: C-20900
Type: Poster: EPOS Radiologist (scientific)
Authorblock: T. Yeshua, T. Amiel, E. Halle, C. Nadler; Jerusalem/IL
Disclosures:
Talia Yeshua: Nothing to disclose
Tevel Amiel: Nothing to disclose
Elia Halle: Nothing to disclose
Chen Nadler: Nothing to disclose
Keywords: Artificial Intelligence, Head and neck, Salivary glands, Cone beam CT, CAD, Pathology
Purpose Salivary gland dysfunction presents significant diagnostic challenges in clinical practice, with ductopenia emerging as a crucial structural indicator of glandular impairment [1]. Characterized by reduced ductal arborization, ductopenia has been associated with reduced salivary flow and increased inflammatory markers [2]. While sialo cone-beam CT (sialo-CBCT) enables detailed visualization of ductal architecture, the interpretation of these images remains largely subjective and time-consuming [3]. The primary objective of this study was to develop and validate an artificial intelligence (AI) application for automated...
Read more Methods and materials This retrospective study analyzed 180 parotid sialo-CBCT scans obtained between 2018 and 2024 from patients presenting with symptoms of xerostomia. Maxillofacial experts classified all scans according to their arborization pattern into two groups: normal-appearing glands (90 scans) and ductopenic glands (90 scans). The technical implementation involved a sophisticated data preprocessing pipeline, utilizing a Convolutional Neural Network (CNN) backbone for volume of interest (VOI) definition and gland classification. To enhance the robustness of the AI model, extensive data augmentation was performed...
Read more Results The AI application demonstrated progressive improvement through the development stages. Initial validation on original MIP images (without ROI definition) achieved an accuracy of 0.91, sensitivity of 0.94, and specificity of 0.88. After implementing ROI definition, the validation performance improved significantly, reaching an accuracy of 0.97, sensitivity of 0.99, and specificity of 0.94. The final evaluation on the independent test set of 40 cases showed exceptional performance, with an accuracy of 0.99, sensitivity of 1.0, and specificity of 0.99, with a...
Read more Conclusion This study presents a novel, highly accurate CNN-based application for rapid detection of ductopenic parotid glands in sialo-CBCT images. The achieved performance metrics demonstrate the tool's potential to standardize ductopenia assessment and significantly improve clinical workflow efficiency. By providing an objective assessment of ductal arborization, this application offers valuable support for clinical decision-making and monitoring of glandular dysfunction. Future research directions should focus on multi-center validation studies and the integration of this AI application into routine clinical workflows to further...
Read more References 1. Ship JA. (2002) Diagnosing, managing, and preventing salivary gland disorders. Oral Dis 8(2):77-89.2. Halle E, et al. (2024) Automated segmentation and deep learning classification of ductopenic parotid salivary glands in sialo cone-beam CT images. Int J Comput Assist Radiol Surg.3. Abdalla-Aslan R, et al. (2021) Standardization of terminology, imaging features, and interpretation of CBCT sialography of major salivary glands. Quintessence Int 52(8):728-740.4. Keshet N, et al. (2019) Novel parotid sialo-cone-beam computerized tomography features in patients with suspected Sjogren's syndrome....
Read more
GALLERY