Automated segmentation of the mandibular canal and its anterior loop by deep learning

Abstract

Accurate mandibular canal (MC) detection is crucial to avoid nerve injury during surgical procedures. Moreover, the anatomic complexity of the interforaminal region requires a precise delineation of anatomical variations such as the anterior loop (AL). Therefore, CBCT-based presurgical planning is recommended, even though anatomical variations and lack of MC cortication make canal delineation challenging. To overcome these limitations, artificial intelligence (AI) may aid presurgical MC delineation. In the present study, we aim to train and validate an AI-driven tool capable of performing accurate segmentation of the MC even in the presence of anatomical variation such as AL. Results achieved high accuracy metrics, with 0.997 of global accuracy for both MC with and without AL. The anterior and middle sections of the MC, where most surgical interventions are performed, presented the most accurate segmentation compared to the posterior section. The AI-driven tool provided accurate segmentation of the mandibular canal, even in the presence of anatomical variation such as an anterior loop. Thus, the presently validated dedicated AI tool may aid clinicians in automating the segmentation of neurovascular canals and their anatomical variations. It may significantly contribute to presurgical planning for dental implant placement, especially in the interforaminal region.

The Impact of Artificial Intelligence on Dental Implantology: A Narrative Review

“…They stated that AI can serve as a reliable tool for canal determination and play a significant role in implant planning in the future. Similar results were also noted by Oliveira-Santos et al where the mandibular canal, along with its variation (anterior loop), was determined by AI with high accuracy [ 14 ]. For the segmentation of the maxillary sinus, the AI model used by Morgan et al provided consistent automatic segmentation, which could allow for the precise reproduction of 3D models for diagnosis and treatment planning [ 15 ].…”

Deep Learning for Mandibular Canal Segmentation in Digital Dental Radiographs: A Systematic Literature Review

“…The 3D U-Net model utilizes shortcut connections to merge highresolution data from the analysis and synthesis paths. Previous studies have used the 3D U-Net architecture for 3D MC segmentation in several research papers [33], [63], [84], [85], [86]. The 3D U-Net method was used to automatically locate the bilateral MC [63].…”

“…The 3D U-Net method was used to automatically locate the bilateral MC [63]. Additionally, previous studies have shown that using 3D U-Net has resulted in precise MC and alveolar bone segmentation, a critical factor in preventing nerve damage during surgical interventions [87].…”

“…Detecting the MC proves to be a formidable task for researchers due to its intricate anatomy shape. To enhance model performance, researchers engage in preliminary anatomical analyses, particularly concerning the loop position of the MC in the premolar teeth [87]. This initial stage holds substantial influence over the success of MC segmentation.…”