Radiological Sciences Department, College of Applied Medical Sciences, Najran University, Najran, Saudi Arabia.
Comput Intell Neurosci. 2022 Jun 21;2022:3061154. doi: 10.1155/2022/3061154. eCollection 2022.
Cephalometry is a medical test that can detect teeth, skeleton, or appearance problems. In this scenario, the patient's lateral radiograph of the face was utilised to construct a tracing from the tracing of lines on the lateral radiograph of the face of the soft and hard structures (skin and bone, respectively). Certain cephalometric locations and characteristic lines and angles are indicated after the tracing is completed to do the real examination. In this unique study, it is proposed that machine learning models be employed to create cephalometry. These models can recognise cephalometric locations in X-ray images, allowing the study's computing procedure to be completed faster. To correlate a probability map with an input image, they combine an Autoencoder architecture with convolutional neural networks and Inception layers. These innovative architectures were demonstrated. When many models were compared, it was observed that they all performed admirably in this task.
头影测量是一种医学测试，可以检测牙齿、骨骼或外观问题。在这种情况下，利用患者的面部侧位 X 光片，从面部侧位 X 光片上的线条追踪图来构建软组织和硬组织（分别为皮肤和骨骼）的追踪图。完成追踪后，会在特定的头影测量位置和特征线和角度上进行实际检查。在这项独特的研究中，提出使用机器学习模型对头影测量进行建模。这些模型可以识别 X 光图像中的头影测量位置，从而使研究的计算过程更快完成。为了将概率图与输入图像相关联，他们将自动编码器架构与卷积神经网络和 Inception 层相结合。这些创新的架构得到了展示。当比较许多模型时，观察到它们在这项任务中都表现出色。
