Kim Jie-Hyun, Oh Sang-Il, Han So-Young, Keum Ji-Soo, Kim Kyung-Nam, Chun Jae-Young, Youn Young-Hoon, Park Hyojin
Department of Internal Medicine, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul 06273, Republic of Korea.
Waycen Inc., Seoul 03722, Republic of Korea.
Cancers (Basel). 2022 Dec 5;14(23):6000. doi: 10.3390/cancers14236000.
We previously constructed a VGG-16 based artificial intelligence (AI) model (image classifier [IC]) to predict the invasion depth in early gastric cancer (EGC) using endoscopic static images. However, images cannot capture the spatio-temporal information available during real-time endoscopy-the AI trained on static images could not estimate invasion depth accurately and reliably. Thus, we constructed a video classifier [VC] using videos for real-time depth prediction in EGC. We built a VC by attaching sequential layers to the last convolutional layer of IC 2, using video clips. We computed the standard deviation (SD) of output probabilities for a video clip and the sensitivities in the manner of frame units to observe consistency. The sensitivity, specificity, and accuracy of IC 2 for static images were 82.5%, 82.9%, and 82.7%, respectively. However, for video clips, the sensitivity, specificity, and accuracy of IC 2 were 33.6%, 85.5%, and 56.6%, respectively. The VC performed better analysis of the videos, with a sensitivity of 82.3%, a specificity of 85.8%, and an accuracy of 83.7%. Furthermore, the mean SD was lower for the VC than IC 2 (0.096 vs. 0.289). The AI model developed utilizing videos can predict invasion depth in EGC more precisely and consistently than image-trained models, and is more appropriate for real-world situations.
我们之前构建了一个基于VGG - 16的人工智能（AI）模型（图像分类器[IC]），用于使用内镜静态图像预测早期胃癌（EGC）的浸润深度。然而，图像无法捕捉实时内镜检查过程中可用的时空信息——在静态图像上训练的AI无法准确可靠地估计浸润深度。因此，我们构建了一个视频分类器[VC]，用于EGC的实时深度预测。我们通过使用视频片段，在IC 2的最后一个卷积层附加顺序层来构建VC。我们计算了视频片段输出概率的标准差（SD）以及以帧为单位的敏感度，以观察一致性。IC 2对静态图像的敏感度、特异度和准确率分别为82.5%、82.9%和82.7%。然而，对于视频片段，IC 2的敏感度、特异度和准确率分别为33.6%、85.5%和56.6%。VC对视频的分析表现更好，敏感度为82.3%，特异度为85.8%，准确率为83.7%。此外，VC的平均SD低于IC 2（0.096对0.289）。利用视频开发的AI模型比基于图像训练的模型能更精确、更一致地预测EGC的浸润深度，并且更适合实际应用场景。
