Kim Ye-Hyun, Park Jae-Bong, Chang Min-Seok, Ryu Jae-Jun, Lim Won Hee, Jung Seok-Ki
Department of Orthodontics, School of Dentistry, Dental Research Institute, Seoul National University, Seoul 03080, Korea.
Department of Oral and Maxillofacial Surgery, School of Dentistry, Seoul National University, Seoul 03080, Korea.
J Pers Med. 2021 Apr 29;11(5):356. doi: 10.3390/jpm11050356.
The aim of this study was to investigate the relationship between image patterns in cephalometric radiographs and the diagnosis of orthognathic surgery and propose a method to improve the accuracy of predictive models according to the depth of the neural networks. The study included 640 and 320 patients requiring non-surgical and surgical orthodontic treatments, respectively. The data of 150 patients were exclusively classified as a test set. The data of the remaining 810 patients were split into five groups and a five-fold cross-validation was performed. The convolutional neural network models used were ResNet-18, 34, 50, and 101. The number in the model name represents the difference in the depth of the blocks that constitute the model. The accuracy, sensitivity, and specificity of each model were estimated and compared. The average success rate in the test set for the ResNet-18, 34, 50, and 101 was 93.80%, 93.60%, 91.13%, and 91.33%, respectively. In screening, ResNet-18 had the best performance with an area under the curve of 0.979, followed by ResNets-34, 50, and 101 at 0.974, 0.945, and 0.944, respectively. This study suggests the required characteristics of the structure of an artificial intelligence model for decision-making based on medical images.
本研究的目的是调查头影测量X线片中的图像模式与正颌外科诊断之间的关系，并根据神经网络的深度提出一种提高预测模型准确性的方法。该研究分别纳入了640例需要非手术正畸治疗和320例需要手术正畸治疗的患者。150例患者的数据被专门分类为测试集。其余810例患者的数据被分为五组，并进行了五折交叉验证。所使用的卷积神经网络模型为ResNet-18、34、50和101。模型名称中的数字表示构成模型的模块深度的差异。对每个模型的准确性、敏感性和特异性进行了估计和比较。ResNet-18、34、50和101在测试集中的平均成功率分别为93.80%、93.60%、91.13%和91.33%。在筛查中，ResNet-18表现最佳，曲线下面积为0.979，其次是ResNets-34、50和101，分别为0.974、0.945和0.944。本研究提出了基于医学图像进行决策的人工智能模型结构所需的特征。
