Department of Business Administration, School of Business, Yeungnam University, Gyeongsan, Korea.
Department of Rehabilitation Medicine, College of Medicine, Yeungnam University, Daegu, Korea.
J Korean Med Sci. 2022 Feb 14;37(6):e42. doi: 10.3346/jkms.2022.37.e42.
Videofluoroscopic swallowing study (VFSS) is currently considered the gold standard to precisely diagnose and quantitatively investigate dysphagia. However, VFSS interpretation is complex and requires consideration of several factors. Therefore, considering the expected impact on dysphagia management, this study aimed to apply deep learning to detect the presence of penetration or aspiration in VFSS of patients with dysphagia automatically.
The VFSS data of 190 participants with dysphagia were collected. A total of 10 frame images from one swallowing process were selected (five high-peak images and five low-peak images) for the application of deep learning in a VFSS video of a patient with dysphagia. We applied a convolutional neural network (CNN) for deep learning using the Python programming language. For the classification of VFSS findings (normal swallowing, penetration, and aspiration), the classification was determined in both high-peak and low-peak images. Thereafter, the two classifications determined through high-peak and low-peak images were integrated into a final classification.
The area under the curve (AUC) for the validation dataset of the VFSS image for the CNN model was 0.942 for normal findings, 0.878 for penetration, and 1.000 for aspiration. The macro average AUC was 0.940 and micro average AUC was 0.961.
This study demonstrated that deep learning algorithms, particularly the CNN, could be applied for detecting the presence of penetration and aspiration in VFSS of patients with dysphagia.
荧光透视吞咽研究（VFSS）目前被认为是精确诊断和定量研究吞咽困难的金标准。然而，VFSS 解读非常复杂，需要考虑多个因素。因此，考虑到对吞咽困难管理的预期影响，本研究旨在应用深度学习技术自动检测吞咽困难患者 VFSS 中是否存在渗透或吸入。
收集了 190 名吞咽困难患者的 VFSS 数据。从一个吞咽过程中选择了总共 10 帧图像（五个高峰图像和五个低峰图像），以便在吞咽困难患者的 VFSS 视频中应用深度学习。我们使用 Python 编程语言应用卷积神经网络（CNN）进行深度学习。为了对 VFSS 结果（正常吞咽、渗透和吸入）进行分类，在高峰和低峰图像中都进行了分类。然后，将通过高峰和低峰图像确定的两种分类整合为最终分类。
CNN 模型的 VFSS 图像验证数据集的曲线下面积（AUC）为正常发现 0.942、渗透 0.878、吸入 1.000。宏观平均 AUC 为 0.940，微观平均 AUC 为 0.961。
本研究表明，深度学习算法，特别是 CNN，可用于检测吞咽困难患者 VFSS 中是否存在渗透和吸入。
