OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven & Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Belgium; Department of Oral Health Sciences, Periodontology and Oral Microbiology, University Hospitals of Leuven, Belgium.
Relu BV, Leuven, Belgium.
J Dent. 2022 Jan;116:103891. doi: 10.1016/j.jdent.2021.103891. Epub 2021 Nov 13.
The objective of this study is the development and validation of a novel artificial intelligence driven tool for fast and accurate mandibular canal segmentation on cone beam computed tomography (CBCT).
A total of 235 CBCT scans from dentate subjects needing oral surgery were used in this study, allowing for development, training and validation of a deep learning algorithm for automated mandibular canal (MC) segmentation on CBCT. Shape, diameter and direction of the MC were adjusted on all CBCT slices using a voxel-wise approach. Validation was then performed on a random set of 30 CBCTs - previously unseen by the algorithm - where voxel-level annotations allowed for assessment of all MC segmentations.
Primary results show successful implementation of the AI algorithm for segmentation of the MC with a mean IoU of 0.636 (± 0.081), a median IoU of 0.639 (± 0.081), a mean Dice Similarity Coefficient of 0.774 (± 0.062). Precision, recall and accuracy had mean values of 0.782 (± 0.121), 0.792 (± 0.108) and 0.99 (± 7.64×10) respectively. The total time for automated AI segmentation was 21.26 s (±2.79), which is 107 times faster than accurate manual segmentation.
This study demonstrates a novel, fast and accurate AI-driven module for MC segmentation on CBCT.
Given the importance of adequate pre-operative mandibular canal assessment, Artificial Intelligence could help relieve practitioners from the delicate and time-consuming task of manually tracing and segmenting this structure, helping prevent per- and post-operative neurovascular complications.
本研究的目的是开发和验证一种新的人工智能驱动工具，用于快速准确地对锥形束计算机断层扫描（CBCT）中的下颌管进行分割。
本研究共使用了 235 例需要口腔手术的有牙受试者的 CBCT 扫描，允许开发、训练和验证一种用于 CBCT 上自动下颌管（MC）分割的深度学习算法。使用体素方法对所有 CBCT 切片上的 MC 形状、直径和方向进行调整。然后在一组 30 例随机的 CBCT 上进行验证，这些 CBCT 以前未被算法看到，其中体素级注释允许评估所有 MC 分割。
主要结果表明，成功实现了人工智能算法对 MC 分割的应用，平均 IoU 为 0.636（±0.081），中位数 IoU 为 0.639（±0.081），平均 Dice 相似系数为 0.774（±0.062）。精度、召回率和准确率的平均值分别为 0.782（±0.121）、0.792（±0.108）和 0.99（±7.64×10）。自动人工智能分割的总时间为 21.26s（±2.79），比精确的手动分割快 107 倍。
本研究展示了一种新的、快速和准确的人工智能驱动的 CBCT 中 MC 分割模块。
鉴于充分的术前下颌管评估的重要性，人工智能可以帮助医生从手动追踪和分割这一结构的繁琐和耗时的任务中解脱出来，有助于预防围手术期的血管神经并发症。
