Department of Dentistry, State University of Paraíba, Campina Grande, Paraíba, Brazil.
Computer Science, Federal University, Campina Grande, Brazil.
Dentomaxillofac Radiol. 2022 Feb 1;51(2):20210318. doi: 10.1259/dmfr.20210318. Epub 2021 Oct 6.
To assess three machine learning (ML) attribute extraction methods: radiomic, semantic and radiomic-semantic association on temporomandibular disorder (TMD) detection using infrared thermography (IT); and to determine which ML classifier, KNN, SVM and MLP, is the most efficient for this purpose.
78 patients were selected by applying the Fonseca questionnaire and RDC/TMD to categorize control patients (37) and TMD patients (41). IT lateral projections of each patient were acquired. The masseter and temporal muscles were selected as regions of interest (ROI) for attribute extraction. Three methods of extracting attributes were assessed: radiomic, semantic and radiomic-semantic association. For radiomic attribute extraction, 20 texture attributes were assessed using co-occurrence matrix in a standardized angulation of 0°. The semantic features were the ROI mean temperature and pain intensity data. For radiomic-semantic association, a single dataset composed of 28 features was assessed. The classification algorithms assessed were KNN, SVM and MLP. Hopkins's statistic, Shapiro-Wilk, ANOVA and Tukey tests were used to assess data. The significance level was set at 5% ( < 0.05).
Training and testing accuracy values differed statistically for the radiomic-semantic association ( = 0.003). MLP differed from the other classifiers for the radiomic-semantic association ( = 0.004). Accuracy, precision and sensitivity values of semantic and radiomic-semantic association differed statistically from radiomic features ( = 0.008, = 0.016 and = 0.013).
Semantic and radiomic-semantic-associated ML feature extraction methods and MLP classifier should be chosen for TMD detection using IT images and pain scale data. IT associated with ML presents promising results for TMD detection.
评估三种机器学习（ML）属性提取方法：放射组学、语义学和放射组学-语义学关联，用于使用红外热成像（IT）检测颞下颌关节紊乱（TMD）；并确定哪种 ML 分类器（KNN、SVM 和 MLP）最适合此目的。
通过应用 Fonseca 问卷和 RDC/TMD 对 78 名患者进行选择，将患者分为对照组（37 名）和 TMD 组（41 名）。获取每位患者的 IT 侧位投影。选择咀嚼肌和颞肌作为感兴趣区域（ROI）进行属性提取。评估了三种属性提取方法：放射组学、语义学和放射组学-语义学关联。对于放射组学属性提取，使用共生矩阵评估了 20 个纹理属性，角度标准化为 0°。语义特征是 ROI 的平均温度和疼痛强度数据。对于放射组学-语义学关联，评估了一个由 28 个特征组成的单一数据集。评估的分类算法包括 KNN、SVM 和 MLP。使用霍普金斯统计、Shapiro-Wilk、方差分析和 Tukey 检验来评估数据。显著性水平设置为 5%（<0.05）。
放射组学-语义学关联的训练和测试准确性值存在统计学差异（=0.003）。MLP 在放射组学-语义学关联方面与其他分类器不同（=0.004）。语义学和放射组学-语义学关联的准确性、精度和敏感性值与放射组学特征存在统计学差异（=0.008、=0.016 和=0.013）。
应选择语义学和放射组学-语义学关联的 ML 特征提取方法和 MLP 分类器，用于使用 IT 图像和疼痛量表数据检测 TMD。IT 与 ML 结合为 TMD 检测提供了有前景的结果。
