ABSTRACT
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 v2, 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 v2 for static images were 82.5%, 82.9%, and 82.7%, respectively. However, for video clips, the sensitivity, specificity, and accuracy of IC v2 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 v2 (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.
ABSTRACT
Extrahepatic cholangiocarcinoma is often clinically challenging to diagnose. Even multidisciplinary approaches which include computed tomography, magnetic resonance imaging, and endoscopic retrograde cholangiography are unsatisfactory in some cases, especially with biliary stricture. Percutaneous transhepatic cholangioscopy (PTCS) with its direct visualization for biopsy appears to be a promising technique for detecting cholangiocarcinoma at an early stage. We report a case of adenocarcinoma in situ of the distal common bile duct (CBD) that was confirmed by PTCS. This case suggests the useful role of PTCS in the differential diagnosis of a distal CBD obstruction, particularly when other diagnostic modalities do not provide definitive information.
