Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, 30-059 Krakow, Poland.
Department of Algorithmics and Software, Silesian University of Technology, 44-100 Gliwice, Poland.
Sensors (Basel). 2021 Nov 10;21(22):7481. doi: 10.3390/s21227481.
The aim of this study was to evaluate whether textural analysis could differentiate between the two common types of lytic lesions imaged with use of radiography. Sixty-two patients were enrolled in the study with intraoral radiograph images and a histological reference study. Full textural analysis was performed using MaZda software. For over 10,000 features, logistic regression models were applied. Fragments containing lesion edges were characterized by significant correlation of structural information. Although the input images were stored using lossy compression and their scale was not preserved, the obtained results confirmed the possibility of distinguishing between cysts and granulomas with use of textural analysis of intraoral radiographs. It was shown that the important information distinguishing the aforementioned types of lesions is located at the edges and not within the lesion.
本研究旨在评估纹理分析是否可区分影像学显示的两种常见溶骨性病变。62 名患者纳入本研究，均行口腔内射线照相图像和组织学参考研究。使用 MaZda 软件进行全纹理分析。针对 10000 多个特征，应用逻辑回归模型。包含病变边缘的片段表现出结构信息的显著相关性。尽管输入图像使用有损压缩存储且其比例未保留，但获得的结果证实了使用口腔射线照相的纹理分析区分囊肿和肉芽肿的可能性。结果表明，区分上述病变类型的重要信息位于病变边缘而非病变内部。
