文献速递口腔正畸

深度学习实现口腔正畸多类CBCT图像分割

Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning.
PubMed 文献 · J Dent Res · 2021-03-30

MS-D网络分割结果与金标准高度重叠(Dice系数:颌骨0.934±0.019,牙齿0.945±0.021),表面偏差小(颌骨0.390±0.093 mm,牙齿0.204±0.061 mm),单次扫描分割约25秒,而手动分割约5小时,表明多类分割准确且性能与二类分割相当。

要点

  • MS-D网络可同时分割颌骨、牙齿和背景,Dice系数分别为0.934和0.945。
  • 分割三维模型与金标准表面偏差小,颌骨0.390 mm,牙齿0.204 mm。
  • 自动分割约25秒,手动分割约5小时,大幅节省时间。

核心结论

  • MS-D网络对CBCT中颌骨和牙齿的多类分割准确,性能与二类分割相当。
  • 该网络可大幅减少分割多个解剖结构所需时间,使患者特异性正畸治疗更可行。

研究设计与样本

  • 由4名牙医手动创建金标准分割标签。
  • 训练并验证混合尺度密集(MS-D)卷积神经网络进行多类分割,并以二类分割MS-D网络为基准。
  • 所有分割CBCT扫描转换为虚拟三维模型,用Dice相似系数和表面偏差评估分割性能。

主要发现

  • MS-D网络分割与金标准高度重叠,Dice系数颌骨0.934±0.019、牙齿0.945±0.021。
  • 三维模型表面偏差颌骨0.390±0.093 mm、牙齿0.204±0.061 mm。
  • MS-D网络分割1例CBCT约25秒,手动分割约5小时。

关键数值与推荐

  • Dice相似系数:颌骨0.934±0.019,牙齿0.945±0.021。
  • 表面偏差:颌骨0.390±0.093 mm,牙齿0.204±0.061 mm。
  • 分割时间:MS-D网络约25秒/例,手动约5小时。

临床怎么用

  • 可用于正畸诊断和治疗规划中颌骨与牙齿的自动分割,减少人工分割时间。
  • 多类分割性能与二类分割相当,支持同时分割多个解剖结构。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network-based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.

来源:J Dent Res,查看原文。版权归原作者所有。

引用

  1. Wang H, Minnema J, Batenburg KJ, et al. Multiclass CBCT Image Segmentation for Orthodontics with Deep Learning. J Dent Res. 2021. PMID: 33783247. doi:10.1177/00220345211005338

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。