Kolsanov A V, Popov N V, Ayupova I O, Tsitsiashvili A M, Gaidel A V, Dobratulin K S
Samara State Medical University, Samara, Russia.
A.I. Yevdokimov Moscow State University of Medicine and Dentistry, Moscow, Russia.
Stomatologiia (Mosk). 2021;100(4):63-67. doi: 10.17116/stomat202110004163.
Was to investigate the efficiency of decoding teleradiological studies using an algorithm based on the use of convolutional neural networks - a simple convolutional architecture, as well as an extended U-Net architecture.
For the experiment, a dataset was prepared by three orthodontists with over 10 years of clinical experience. Each of the orthodontists processed 100 X-ray images of the lateral projection of the head according to 27 parameters, 2700 measurements were made. The coordinates of the control points found by orthodontists in the images were compared with each other and a conclusion was made about the consistency of experts in the data obtained.
The results of convolutional neural network CNN were not satisfactory in 17 (62.96%) features, satisfactory in 10 (37.04%). The assessment of orthodontists resulted in non-satisfactory evaluation in 6 (22.22%), satisfactory in 8 (29.63%), good in 8 (29.63%), and excellent in 5 (18.52%) coordinates. Neural networks with U-Net architecture showed satisfactory results in 9 (33.3%) cases, good in 16 (59.3%) and excellent in 2 (7.4%) cases, with no non-satisfactory results.
The neural network of the U-Net architecture is more effective than a simple fully convolutional neural network and its results of determining anatomical reference points on two-dimensional images of the head are relatively comparable with the data obtained by medical specialists.
旨在研究使用基于卷积神经网络的算法（一种简单的卷积架构以及扩展的U-Net架构）对远程放射学研究进行解码的效率。
为进行该实验，由三位具有超过10年临床经验的正畸医生准备了一个数据集。每位正畸医生根据27个参数处理了100张头部侧位X线图像，共进行了2700次测量。将正畸医生在图像中找到的控制点坐标相互比较，并就所获得数据中专家的一致性得出结论。
卷积神经网络（CNN）的结果在17个特征（62.96%）中不令人满意，在10个特征（37.04%）中令人满意。正畸医生的评估结果显示，在6个坐标（22.22%）中评估不令人满意，在8个坐标（29.63%）中令人满意，在8个坐标（29.63%）中良好，在5个坐标（18.52%）中优秀。具有U-Net架构的神经网络在9个案例（33.3%）中显示出令人满意的结果，在16个案例（59.3%）中良好，在2个案例（7.4%）中优秀，没有不令人满意的结果。
U-Net架构的神经网络比简单的全卷积神经网络更有效，其在头部二维图像上确定解剖参考点的结果与医学专家获得的数据相对可比。
