OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, University of Leuven and Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium.
OMFS IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, University of Leuven and Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium; Department of Oral Health Sciences, KU Leuven and Paediatric Dentistry and Special Dental Care, University Hospitals Leuven, Leuven, Belgium.
J Endod. 2021 May;47(5):827-835. doi: 10.1016/j.joen.2020.12.020. Epub 2021 Jan 9.
Tooth segmentation on cone-beam computed tomographic (CBCT) imaging is a labor-intensive task considering the limited contrast resolution and potential disturbance by various artifacts. Fully automated tooth segmentation cannot be achieved by merely relying on CBCT intensity variations. This study aimed to develop and validate an artificial intelligence (AI)-driven tool for automated tooth segmentation on CBCT imaging.
A total of 433 Digital Imaging and Communications in Medicine images of single- and double-rooted teeth randomly selected from 314 anonymized CBCT scans were imported and manually segmented. An AI-driven tooth segmentation algorithm based on a feature pyramid network was developed to automatically detect and segment teeth, replacing manual user contour placement. The AI-driven tool was evaluated based on volume comparison, intersection over union, the Dice score coefficient, morphologic surface deviation, and total segmentation time.
Overall, AI-driven and clinical reference segmentations resulted in very similar segmentation volumes. The mean intersection over union for full-tooth segmentation was 0.87 (±0.03) and 0.88 (±0.03) for semiautomated (SA) (clinical reference) versus fully automated AI-driven (F-AI) and refined AI-driven (R-AI) tooth segmentation, respectively. R-AI and F-AI segmentation showed an average median surface deviation from SA segmentation of 9.96 μm (±59.33 μm) and 7.85 μm (±69.55 μm), respectively. SA segmentations of single- and double-rooted teeth had a mean total time of 6.6 minutes (±76.15 seconds), F-AI segmentation of 0.5 minutes (±8.64 seconds, 12 times faster), and R-AI segmentation of 1.2 minutes (±33.02 seconds, 6 times faster).
This study showed a unique fast and accurate approach for AI-driven automated tooth segmentation on CBCT imaging. These results may open doors for AI-driven applications in surgical and treatment planning in oral health care.
考虑到有限的对比分辨率和各种伪影的潜在干扰，在锥形束计算机断层扫描 (CBCT) 图像上进行牙齿分割是一项劳动密集型任务。仅依靠 CBCT 强度变化，无法实现完全自动的牙齿分割。本研究旨在开发和验证一种基于人工智能 (AI) 的工具，用于在 CBCT 成像上进行自动牙齿分割。
从 314 份匿名 CBCT 扫描中随机选择的单根和双根牙齿的共 433 张数字成像和通信医学图像被导入并进行手动分割。开发了一种基于特征金字塔网络的 AI 驱动的牙齿分割算法，用于自动检测和分割牙齿，替代手动用户轮廓放置。基于体积比较、交并比、骰子得分系数、形态表面偏差和总分割时间来评估 AI 驱动的工具。
总体而言，AI 驱动和临床参考分割产生了非常相似的分割体积。全牙分割的平均交并比为 0.87(±0.03)，半自动 (SA)（临床参考）与全自动 AI 驱动 (F-AI) 和细化 AI 驱动 (R-AI) 牙齿分割分别为 0.88(±0.03)。R-AI 和 F-AI 分割分别显示出与 SA 分割的平均中位数表面偏差为 9.96μm(±59.33μm)和 7.85μm(±69.55μm)。单根和双根牙齿的 SA 分割总时间平均为 6.6 分钟(±76.15 秒)，F-AI 分割为 0.5 分钟(±8.64 秒，快 12 倍)，R-AI 分割为 1.2 分钟(±33.02 秒，快 6 倍)。
本研究展示了一种独特的快速准确的基于人工智能的 CBCT 图像自动牙齿分割方法。这些结果可能为口腔保健中基于人工智能的手术和治疗计划应用开辟道路。
