林 芳和

Gastric mucosal changes associated with long-term potassium-competitive acid blocker and proton pump inhibitor (PPI) therapy may raise concern. In contrast to that for PPIs, the evidence concerning the safety of long-term potassium-competitive acid blocker use is scant. Vonoprazan (VPZ) is a representative potassium-competitive acid blocker released in Japan in 2015. In order to shed some comparative light regarding the outcomes of gastric mucosal lesions associated with a long-term acid blockade, we have reviewed six representative gastric mucosal lesions: fundic gland polyps, gastric hyperplastic polyps, multiple white and flat elevated lesions, cobblestone-like gastric mucosal changes, gastric black spots, and stardust gastric mucosal changes. For these mucosal lesions, we have evaluated the association with the type of acid blockade, patient gender, Helicobacter pylori infection status, the degree of gastric atrophy, and serum gastrin levels. There is no concrete evidence to support a significant relationship between VPZ/PPI use and the development of neuroendocrine tumors. Current data also shows that the risk of gastric mucosal changes is similar for long-term VPZ and PPI use. Serum hypergastrinemia is not correlated with the development of some gastric mucosal lesions. Therefore, serum gastrin level is unhelpful for risk estimation and for decision-making relating to the cessation of these drugs in routine clinical practice. Given the confounding potential neoplastic risk relating to H. pylori infection, this should be eradicated before VPZ/PPI therapy is commenced. The evidence to date does not support the cessation of clinically appropriate VPZ/PPI therapy solely because of the presence of these associated gastric mucosal lesions.

Background and study aims Diagnostic performance of a computer-aided diagnosis (CAD) system for deep submucosally invasive (T1b) colorectal cancer was excellent, but the "regions of interest" (ROI) within images are not obvious. Class activation mapping (CAM) enables identification of the ROI that CAD utilizes for diagnosis. The purpose of this study was a quantitative investigation of the difference between CAD and endoscopists. Patients and methods Endoscopic images collected for validation of a previous study were used, including histologically proven T1b colorectal cancers (n = 82; morphology: flat 36, polypoid 46; median maximum diameter 20 mm, interquartile range 15-25 mm; histological subtype: papillary 5, well 51, moderate 24, poor 2; location: proximal colon 26, distal colon 27, rectum 29). Application of CAM was limited to one white light endoscopic image (per lesion) to demonstrate findings of T1b cancers. The CAM images were generated from the weights of the previously fine-tuned ResNet50. Two expert endoscopists depicted the ROI in identical images. Concordance of the ROI was rated by intersection over union (IoU) analysis. Results Pixel counts of ROIs were significantly lower using 165K[x103] [108K-227K] than by endoscopists (300K [208K-440K]; P < 0.0001) and median [interquartile] of the IoU was 0.198 [0.024-0.349]. IoU was significantly higher in correctly identified lesions (n = 54, 0.213 [0.116-0.364]) than incorrect ones (n=28, 0.070 [0.000-0.2750, P = 0.033). Concusions IoU was larger in correctly diagnosed T1b colorectal cancers. Optimal annotation of the ROI may be the key to improving diagnostic sensitivity of CAD for T1b colorectal cancers.