Department of Oral Surgery, Wroclaw Medical University, Poland.
Department of Maxillofacial Surgery, Faculty of Military Medicine, Medical University of Lodz, Poland.
Adv Clin Exp Med. 2019 Nov;28(11):1469-1476. doi: 10.17219/acem/104524.
A noninvasive, accurate and quick diagnosis is very important to general practitioners and specialists who care for the health of patients' oral cavity mucosa. The main enemies are precancerous lesions: leukoplakia and lichen planus (LP).
The aim of this study was to attempt to formulate a differential diagnosis for leukoplakia vs LP in the oral mucosa based on digital texture analysis in intraoral macrophotography.
The study was comprised of 21 patients affected by leukoplakia, 21 affected by LP and 21 healthy volunteers. Intraoral photography of all participants was taken perpendicularly to the buccal mucosa. To achieve the maximum possible contrast, a high-pass filter was applied and level tools were then used to equalize the histograms of the images. After that, the images were converted into 8-bit grayscale. Two features of run length matrix and 2 of co-occurrence matrix were used for texture analysis. Analysis of variance (ANOVA) was used to check for differences. Factor analysis (FA) and classification with artificial neural network (ANN) were performed.
The results revealed a simple possible differentiation of both types of precancerous lesions from normal mucosa (p < 0.05). Factor analysis and ANN can help in differentiating the 3 study groups from one another.
Differential diagnosis of leukoplakia and LP in the oral mucosa based on digital texture analysis in intraoral macrophotography is possible. It can be used to develop smartphone applications and can be also a helpful tool for general dentists to define the clinical problem before a consultation with a specialist.
对于关注患者口腔黏膜健康的全科医生和专家来说，非侵入性、准确且快速的诊断非常重要。主要的敌人是癌前病变：白斑和扁平苔藓（LP）。
本研究旨在尝试通过口腔内体视学的数字纹理分析，为口腔黏膜的白斑与 LP 制定鉴别诊断。
该研究包括 21 名患有白斑的患者、21 名患有 LP 的患者和 21 名健康志愿者。所有参与者的口腔内摄影均垂直于颊黏膜进行。为了获得最大的对比度，应用了高通滤波器，然后使用水平工具来均衡图像的直方图。之后，图像被转换为 8 位灰度。使用 2 个游程长度矩阵特征和 2 个共生矩阵特征进行纹理分析。使用方差分析（ANOVA）检查差异。进行因子分析（FA）和人工神经网络（ANN）分类。
结果显示，这两种癌前病变与正常黏膜之间存在简单的可能差异（p<0.05）。因子分析和 ANN 可以帮助区分这 3 个研究组。
基于口腔内体视学的数字纹理分析对口腔黏膜的白斑和 LP 进行鉴别诊断是可行的。它可用于开发智能手机应用程序，也可作为全科牙医在与专家咨询前确定临床问题的有用工具。
