Department of Electrical Electronic Engineering, Faculty of Engineering, Ataturk University, Erzurum, Turkey.
Department of Oral Diagnosis and Dentomaxillofacial Radiology, Faculty of Dentistry, Ataturk University, Erzurum, Turkey.
BMC Med Imaging. 2024 Mar 8;24(1):59. doi: 10.1186/s12880-024-01234-3.
This study aims to classify tongue lesion types using tongue images utilizing Deep Convolutional Neural Networks (DCNNs).
A dataset consisting of five classes, four tongue lesion classes (coated, geographical, fissured tongue, and median rhomboid glossitis), and one healthy/normal tongue class, was constructed using tongue images of 623 patients who were admitted to our clinic. Classification performance was evaluated on VGG19, ResNet50, ResNet101, and GoogLeNet networks using fusion based majority voting (FBMV) approach for the first time in the literature.
In the binary classification problem (normal vs. tongue lesion), the highest classification accuracy performance of 93,53% was achieved utilizing ResNet101, and this rate was increased to 95,15% with the application of the FBMV approach. In the five-class classification problem of tongue lesion types, the VGG19 network yielded the best accuracy rate of 83.93%, and the fusion approach improved this rate to 88.76%.
The obtained test results showed that tongue lesions could be identified with a high accuracy by applying DCNNs. Further improvement of these results has the potential for the use of the proposed method in clinic applications.
本研究旨在利用深度卷积神经网络（DCNN）对舌象进行舌病类型分类。
利用我院就诊的 623 名患者的舌象构建了一个包含五个类别的数据集，包括四个舌病类别（腻苔、地图舌、裂纹舌和菱形舌炎）和一个健康/正常舌类别。首次在文献中使用基于融合的多数投票（FBMV）方法对 VGG19、ResNet50、ResNet101 和 GoogLeNet 网络进行分类性能评估。
在正常与舌病的二分类问题中，利用 ResNet101 实现了最高的分类准确率 93.53%，应用 FBMV 方法后该准确率提高到 95.15%。在五种舌病类型的五分类问题中，VGG19 网络的准确率最高，为 83.93%，融合方法将该准确率提高到 88.76%。
研究结果表明，DCNN 可用于准确识别舌病。进一步提高这些结果的准确率，有望将所提出的方法应用于临床应用中。
