SISTR: Sinus and Inferior alveolar nerve Segmentation with Targeted Refinement on Cone Beam Computed Tomography images

Abstract

AbstractBackgroundAccurate delineation of the maxillary sinus and inferior alveolar nerve (IAN) is crucial in dental implantology to prevent surgical complications. Manual segmentation from CBCT scans is labor-intensive and error-prone.MethodsWe introduce SISTR (Sinus and IAN Segmentation with Targeted Refinement), a deep learning framework for automated, high-resolution instance segmentation of oral cavity anatomies. SISTR operates in two stages: first, it predicts coarse segmentation and offset maps to anatomical regions, followed by clustering to identify region centroids. Subvolumes of individual anatomical instances are then extracted and processed by the model for fine structure segmentation. Our model was developed on the most diverse dataset to date for sinus and IAN segmentation, sourced from 11 dental clinics and 10 manufacturers (358 CBCTs for sinus, 499 for IAN).ResultsSISTR shows robust generalizability. It achieves strong segmentation performance on an external test set (98 sinus, 91 IAN CBCTs), reaching average DICE scores of 96.64% (95.38-97.60) for sinus and 83.43% (80.96-85.63) for IAN, representing a significant 10 percentage point improvement in Dice score for IAN compared to single-stage methods. Chamfer distances of 0.38 (0.24-0.60) mm for sinus and 0.88 (0.58-1.27) mm for IAN confirm its accuracy. Its inference time of 4 seconds per scan reduces time required for manual segmentation, which can take up to 28 minutes.ConclusionsSISTR offers a fast, accurate, and efficient solution for the segmentation of critical anatomies in dental implantology, making it a valuable tool in digital dentistry.Plain text summaryAccurately determining the locations of important structures such as the maxillary sinus and inferior alveolar nerve is crucial in dental implant surgery to avoid complications. The conventional method of manually mapping these areas from CBCT scans is time-consuming and prone to errors. To address this issue, we have developed SISTR, an AI-based framework that efficiently and accurately automates this process, trained on extensive datasets, sourced from 11 dental clinics and 10 manufacturers. It surpasses conventional methods by identifying anatomical regions within seconds. SISTR provides a rapid and accurate solution for high-resolution segmentation of critical anatomies in dental implantology, making it a valuable tool in digital dentistry.