Search

Background and Aims Narrow-band imaging (NBI) is currently regarded as the standard modality for diagnosing esophageal squamous cell carcinoma (SCC). We developed a computerized image-analysis system for diagnosing esophageal SCC by NBI and estimated its performance with video images. Methods Altogether, 23,746 images from 1544 pathologically proven superficial esophageal SCCs and 4587 images from 458 noncancerous and normal tissue were used to construct an artificial intelligence (AI) system. Five- to 9-second video clips from 144 patients captured by NBI or blue-light imaging were used as the validation dataset. These video images were diagnosed by the AI system and 13 board-certified specialists (experts). Results The diagnostic process was divided into 2 parts: detection (identify suspicious lesions) and characterization (differentiate cancer from noncancer). The sensitivities, specificities, and accuracies for the detection of SCC were, respectively, 91%, 51%, and 63% for the AI system and 79%, 72%, and 75% for the experts. The sensitivity of the AI system was significantly higher than that of the experts, but its specificity was significantly lower. Sensitivities, specificities, and accuracy for the characterization of SCC were, respectively, 86%, 89%, and 88% for the AI system and 74%, 76%, and 75% for the experts. The receiver operating characteristic curve showed that the AI system had significantly better diagnostic performance than the experts. Conclusions Our AI system showed significantly higher sensitivity for detecting SCC and higher accuracy for characterizing SCC from noncancerous tissue than endoscopic experts.

After resecting colonic polyps, retrieval through the scope channel may lead to polyp fragmentation, making pathologic evaluation challenging. An easy and reliable method for complete polyp retrieval is needed.We developed the water-slider method (WSM), in which the resected polyp is surrounded by water from an auxiliary water channel during suctioning. We prospectively randomized patients who underwent endoscopic resection for colonic polyps in our institute into WSM and non-WSM groups, and evaluated the polyp fragmentation rate.Analysis of the data regarding small polyps (≤10 mm in size) revealed that the WSM group had a significantly lower polyp fragmentation rate (8.2%) than the non-WSM group (23.8%, p0.001). Polyp retrieval time did not differ significantly between groups. The rate of a clear-cut end on neoplastic polyps was significantly higher in the WSM group (63.8%) than in the non-WSM group (50.0%; p = 0.029).The WSM achieved a significantly lower polyp fragmentation rate, allowing for more accurate histologic evaluation than the conventional method. The WSM did not influence the polyp retrieval time.