He Jiawei, Sun Muxi, Huo Youtong, Huang Dingming, Leng Sha, Zheng Qinghua, Ji Xiao, Jiang Li, Liu Guanghui, Zhang Lan
State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, 610041, China.
Department of Conservative Dentistry and Endodontics, West China Hospital of Stomatology, Sichuan University, Chengdu, Sichuan, 610041, China.
Clin Oral Investig. 2025 Jan 25;29(1):88. doi: 10.1007/s00784-025-06191-x.
To develop a platform including a deep convolutional neural network (DCNN) for automatic segmentation of the maxillary sinus (MS) and adjacent structures, and automatic algorithms for measuring 3-dimensional (3D) clinical parameters.
175 CBCTs containing 242 MS were used as the training, validating and testing datasets at the ratio of 7:1:2. The datasets contained healthy MS and MS with mild (2-4 mm), moderate (4-10 mm) and severe (10- mm) mucosal thickening. A DCNN algorithm adopting 2.5D structure was trained for automatic segmentation. Automatic measuring algorithms were further developed to evaluate the clinical reliability of the DCNN.
The median Dice Similarity Coefficient (DSC) for the air cavity, mucosa, teeth and maxillary bone segmentation were 0.990, 0.850, 0.961 and 0.953, respectively. The Intra-class Correlation Coefficien (ICC) of all automatic measuring algorithms exceeded 0.975. The 95% confidence interval (95%CI) of all volumetric metric bias were within ± 0.5 cm, of all 2D metric bias were within ± 1 mm. The DCNN also produced satisfying outcome for notably incomplete MS and edentulous alveolar crest.
The DCNN provided clinically reliable results. The automatic measuring algorithms could reveal 3D information embedded in CBCT 2D planes on the basis of automatic segmentation.
This platform helps dentists to conduct instant 3D reconstruction and automatic measuring of 3D clinical parameters of MS and adjacent structures.
开发一个平台，该平台包含用于上颌窦（MS）及相邻结构自动分割的深度卷积神经网络（DCNN），以及用于测量三维（3D）临床参数的自动算法。
175例包含242个上颌窦的锥形束计算机断层扫描（CBCT）图像按7:1:2的比例用作训练、验证和测试数据集。这些数据集包含健康的上颌窦以及伴有轻度（2 - 4毫米）、中度（4 - 10毫米）和重度（10 - 毫米）黏膜增厚的上颌窦。采用2.5D结构的DCNN算法进行自动分割训练。进一步开发自动测量算法以评估DCNN的临床可靠性。
气腔、黏膜、牙齿和上颌骨分割的中位骰子相似系数（DSC）分别为0.990、0.850、0.961和0.953。所有自动测量算法的组内相关系数（ICC）均超过0.975。所有体积测量偏差的95%置信区间（95%CI）在±0.5厘米内，所有二维测量偏差的95%CI在±1毫米内。对于明显不完整的上颌窦和无牙牙槽嵴，DCNN也产生了令人满意的结果。
DCNN提供了临床可靠的结果。自动测量算法能够在自动分割的基础上揭示CBCT二维平面中嵌入的三维信息。
该平台有助于牙医对上颌窦及相邻结构进行即时三维重建和三维临床参数的自动测量。
