Mattos Claudia Trindade, Dole Lucie, Mota-Júnior Sergio Luiz, Cury-Saramago Adriana de Alcantara, Bianchi Jonas, Oh Heesoo, Evangelista Karine, Valladares-Neto José, Ruellas Antonio Carlos de Oliveira, Prieto Juan Carlos, Cevidanes Lucia Helena Soares
Department of Orthodontics, Faculdade de Odontologia, Universidade Federal Fluminense, Rua Mário Santos Braga, 30, 2° andar, sala 214, Centro, Niterói, RJ, CEP 24020-140, Brazil; Department of Orthodontics and Pediatric Dentistry, School of Dentistry, University of Michigan, 1011 North University Avenue, Ann Arbor, Michigan, 48104, USA.
Department of Psychiatry, School of Medicine, University of North Carolina, 333 S. Columbia Street, Suite 304, MacNider Hall, Chapel Hill, North Carolina, 27514, USA.
J Dent. 2025 May;156:105689. doi: 10.1016/j.jdent.2025.105689. Epub 2025 Mar 14.
To develop and validate an explainable Artificial Intelligence (AI) model for classifying and quantifying upper airway obstruction related to adenoid hypertrophy using three-dimensional (3D) shape analysis of cone-beam computed tomography (CBCT) scans.
400 CBCT scans of patients aged 5-18 years were analyzed. Nasopharyngeal airway obstruction (NAO) ratio was calculated to label scans into four grades of obstruction severity, used as the ground truth. Upper airway surface meshes were used to train a deep learning model combining multiview and point-cloud approaches for 3D shape analysis and obstruction severity classification and quantification. Surface Gradient-weighted Class Activation Mapping (SurfGradCAM) generated explainability heatmaps. Performance was evaluated using area under the curve (AUC), precision, recall, F1-score, mean absolute error, root mean squared error, and correlation coefficients.
The explainable AI model demonstrated strong performance in both classification and quantification tasks. The AUC values for the classification task ranged from 0.77 to 0.94, with the highest values of 0.88 and 0.94 for Grades 3 and 4, respectively, indicating excellent discriminative ability for identifying more severe cases of obstruction. The SurfGradCAM-generated heatmaps consistently highlighted the most relevant regions of the upper airway influencing the AI's decision-making process. In the quantification task, the regression model successfully predicted the NAO ratio, with a strong correlation coefficient of 0.854 (p < 0.001) and R= 0.728, explaining a substantial proportion of the variance in NAO ratios.
The proposed explainable AI model, using 3D shape analysis, demonstrated strong performance in classifying and quantifying adenoid hypertrophy-related upper airway obstruction in CBCT scans.
This AI model provides clinicians with a reliable, automated tool for standardized adenoid hypertrophy assessment. The model's explainable nature enhances clinical confidence and patient communication, potentially improving diagnostic workflow and treatment planning.
利用锥形束计算机断层扫描（CBCT）的三维（3D）形状分析，开发并验证一种可解释的人工智能（AI）模型，用于对上气道阻塞与腺样体肥大相关情况进行分类和量化。
对400例5至18岁患者的CBCT扫描进行分析。计算鼻咽气道阻塞（NAO）比值，将扫描结果标记为四个阻塞严重程度等级，作为基准真值。利用上气道表面网格训练一个深度学习模型，该模型结合多视图和点云方法进行3D形状分析以及阻塞严重程度分类和量化。表面梯度加权类激活映射（SurfGradCAM）生成可解释性热图。使用曲线下面积（AUC）、精确率、召回率、F1分数、平均绝对误差、均方根误差和相关系数评估性能。
该可解释AI模型在分类和量化任务中均表现出强大性能。分类任务的AUC值范围为0.77至0.94，其中3级和4级的最高值分别为0.88和0.94，表明在识别更严重阻塞病例方面具有出色的判别能力。SurfGradCAM生成的热图始终突出显示了影响AI决策过程的上气道最相关区域。在量化任务中，回归模型成功预测了NAO比值，相关系数为0.854（p < 0.001），R = 0.728，解释了NAO比值中很大一部分方差。
所提出的可解释AI模型利用3D形状分析，在CBCT扫描中对腺样体肥大相关的上气道阻塞进行分类和量化方面表现出强大性能。
该AI模型为临床医生提供了一种可靠的自动化工具，用于标准化腺样体肥大评估。该模型的可解释性增强了临床信心和医患沟通，有可能改善诊断流程和治疗规划。
