Computer Engineering Department, School of Engineering, The University of Jordan, Amman, Jordan.
Department of Oral and Maxillofacial Surgery, Oral Medicine, and Periodontics, School of Dentistry, The University of Jordan, Amman, Jordan.
Oral Dis. 2022 May;28(4):1123-1130. doi: 10.1111/odi.13825. Epub 2021 Mar 5.
To develop a lightweight deep convolutional neural network (CNN) for binary classification of oral lesions into benign and malignant or potentially malignant using standard real-time clinical images.
A small deep CNN, that uses a pretrained EfficientNet-B0 as a lightweight transfer learning model, was proposed. A data set of 716 clinical images was used to train and test the proposed model. Accuracy, specificity, sensitivity, receiver operating characteristics (ROC) and area under curve (AUC) were used to evaluate performance. Bootstrapping with 120 repetitions was used to calculate arithmetic means and 95% confidence intervals (CIs).
The proposed CNN model achieved an accuracy of 85.0% (95% CI: 81.0%-90.0%), a specificity of 84.5% (95% CI: 78.9%-91.5%), a sensitivity of 86.7% (95% CI: 80.4%-93.3%) and an AUC of 0.928 (95% CI: 0.88-0.96).
Deep CNNs can be an effective method to build low-budget embedded vision devices with limited computation power and memory capacity for diagnosis of oral cancer. Artificial intelligence (AI) can improve the quality and reach of oral cancer screening and early detection.
开发一种轻量级深度卷积神经网络（CNN），用于使用标准实时临床图像对口腔病变进行良性和恶性或潜在恶性的二分类。
提出了一种小型深度 CNN，它使用经过预训练的 EfficientNet-B0 作为轻量级迁移学习模型。使用 716 张临床图像数据集来训练和测试所提出的模型。使用准确性、特异性、敏感性、接收者操作特征（ROC）和曲线下面积（AUC）来评估性能。使用 120 次重复的引导来计算算术平均值和 95%置信区间（CI）。
所提出的 CNN 模型的准确率为 85.0%（95%CI：81.0%-90.0%），特异性为 84.5%（95%CI：78.9%-91.5%），敏感性为 86.7%（95%CI：80.4%-93.3%），AUC 为 0.928（95%CI：0.88-0.96）。
深度 CNN 可以成为构建具有有限计算能力和内存容量的低预算嵌入式视觉设备的有效方法，用于诊断口腔癌。人工智能（AI）可以提高口腔癌筛查和早期检测的质量和覆盖面。
