Li Liangbo, Pu Cheng, Tao Jingqiao, Zhu Liang, Hu Suixin, Qiao Bo, Xing Lejun, Wei Bo, Shi Chuyan, Chen Peng, Zhang Haizhong
Medical School of Chinese PLA, Beijing, China.
Department of Stomatology, Chinese PLA General Hospital, 28 Fuxing road, Haidian District, Beijing, 100853, China.
BMC Oral Health. 2024 Dec 4;24(1):1468. doi: 10.1186/s12903-024-05195-5.
We aimed to develop an AI-based model that uses a portable electronic oral endoscope to capture intraoral images of patients for the detection of oral cancer.
From September 2019 to October 2023, 205 high-quality annotated images of oral cancer were collected using a portable oral electronic endoscope at the Chinese PLA General Hospital for this study. The U-Net and ResNet-34 deep learning models were employed for oral cancer detection. The performance of these models was evaluated using several metrics: Dice coefficient, Intersection over Union (IoU), Loss, Precision, Recall, and F1 Score.
During the algorithm model training phase, the Dice values were approximately 0.8, the Loss values were close to 0, and the IoU values were around 0.7. In the validation phase, the highest Dice values ranged between 0.4 and 0.5, while the Loss values increased, and the training loss began to decrease gradually. In the test phase, the model achieved a maximum Precision of 0.96 with a confidence threshold of 0.990. Additionally, with a confidence threshold of 0.010, the highest F1 score reached was 0.58.
This study provides an initial demonstration of the potential of deep learning models in identifying oral cancer.
我们旨在开发一种基于人工智能的模型，该模型使用便携式电子口腔内窥镜拍摄患者的口腔内图像，以检测口腔癌。
2019年9月至2023年10月，本研究在中国人民解放军总医院使用便携式口腔电子内窥镜收集了205张高质量的口腔癌标注图像。采用U-Net和ResNet-34深度学习模型进行口腔癌检测。使用多个指标评估这些模型的性能：骰子系数、交并比（IoU）、损失、精度、召回率和F1分数。
在算法模型训练阶段，骰子值约为0.8，损失值接近0，IoU值约为0.7。在验证阶段，最高骰子值在0.4至0.5之间，而损失值增加，训练损失开始逐渐下降。在测试阶段，该模型在置信阈值为0.990时达到最大精度0.96。此外，在置信阈值为0.010时，最高F1分数达到0.58。
本研究初步证明了深度学习模型在识别口腔癌方面的潜力。
