In early gastric cancer (EGC), tumor invasion depth is an important factor for determining the treatment method. However, as endoscopic ultrasonography has limitations when measuring the exact depth in a clinical setting as endoscopists often depend on gross findings and personal experience. The present study aimed to develop a model optimized for EGC detection and depth prediction, and we investigated factors affecting artificial intelligence (AI) diagnosis. We employed a visual geometry group(VGG)-16 model for the classification of endoscopic images as EGC (T1a or T1b) or non-EGC. To induce the model to activate EGC regions during training, we proposed a novel loss function that simultaneously measured classification and localization errors. We experimented with 11,539 endoscopic images (896 T1a-EGC, 809 T1b-EGC, and 9834 non-EGC). The areas under the curves of receiver operating characteristic curves for EGC detection and depth prediction were 0.981 and 0.851, respectively. Among the factors affecting AI prediction of tumor depth, only histologic differentiation was significantly associated, where undifferentiated-type histology exhibited a lower AI accuracy. Thus, the lesion-based model is an appropriate training method for AI in EGC. However, further improvements and validation are required, especially for undifferentiated-type histology.

Background/AimsA drug-eluting stent for unresectable malignant biliary obstruction was developed to increase stent patency by preventing tumor ingrowth. The safety and efficacy of a new generation of metallic stents covered with a paclitaxel-incorporated membrane using a Pluronic® mixture (MSCPM-II) were compared prospectively with those of covered metal stents (CMSs) in patients with malignant biliary obstructions.MethodsThis study was initially designed as a prospective randomized trial but was closed early because of a high incidence of early occlusion. Therefore, the data were analyzed using the intent-to-treat method. A total of 72 patients with unresectable distal malignant biliary obstructions were prospectively enrolled.ResultsThe two groups did not differ significantly in basic characteristics and mean follow-up period (MSCPM-II 194 days vs CMS 277 days, p=0.063). Stent occlusion occurred in 14 patients (35%) who received MSCPM-II and in seven patients (21.9%) who received CMSs. Stent patency and survival time did not significantly differ between the two groups (p=0.355 and p=0.570). The complications were mild and resolved by conservative management in both groups.ConclusionsThere were no significant differences in stent patency or patient survival in MSCPM-II and CMS patients with malignant biliary obstructions.

No abstract