Rapid Endoscopic Diagnosis of Benign Ulcerative Colorectal Diseases With an Artificial Intelligence Contextual Framework.

BACKGROUND & AIMS: Benign ulcerative colorectal diseases (UCDs) such as ulcerative colitis, Crohn's disease, ischemic colitis, and intestinal tuberculosis share similar phenotypes with different etiologies and treatment strategies. To accurately diagnose closely related diseases like UCDs, we hypothesize that contextual learning is critical in enhancing the ability of the artificial intelligence models to differentiate the subtle differences in lesions amidst the vastly divergent spatial contexts. METHODS: White-light colonoscopy datasets of patients with confirmed UCDs and healthy controls were retrospectively collected. We developed a Multiclass Contextual Classification (MCC) model that can differentiate among the mentioned UCDs and healthy controls by incorporating the tissue object contexts surrounding the individual lesion region in a scene and spatial information from other endoscopic frames (video-level) into a unified framework. Internal and external datasets were used to validate the model's performance. RESULTS: Training datasets included 762 patients, and the internal and external testing cohorts included 257 patients and 293 patients, respectively. Our MCC model provided a rapid reference diagnosis on internal test sets with a high averaged area under the receiver operating characteristic curve (image-level: 0.950 and video-level: 0.973) and balanced accuracy (image-level: 76.1% and video-level: 80.8%), which was superior to junior endoscopists (accuracy: 71.8%, P < .0001) and similar to experts (accuracy: 79.7%, P = .732). The MCC model achieved an area under the receiver operating characteristic curve of 0.988 and balanced accuracy of 85.8% using external testing datasets. CONCLUSIONS: These results enable this model to fit in the routine endoscopic workflow, and the contextual framework to be adopted for diagnosing other closely related diseases.

MFGE8 in exosomes derived from mesenchymal stem cells prevents esophageal stricture after endoscopic submucosal dissection in pigs.

BACKGROUND: Endoscopic submucosal dissection (ESD) is the current standard treatment for early-stage esophageal neoplasms. However, the postoperative esophageal stricture after extensive mucosal dissection remains a severe challenge with limited effective treatments available. In this study, we introduced a chitosan/gelatin (ChGel) sponge encapsulating the adipose mesenchymal stem cells (ADMSCs)-derived exosomes (ChGelMSC-Exo) for the prevention of esophageal stenosis after ESD in a porcine model. RESULTS: Pigs were randomly assigned into (1) ChGelMSC-Exo treatment group, (2) ChGelPBS group, and (3) the controls. Exosome treatments were applied immediately on the day after ESD as well as on day 7. Exosome components crucial for wound healing were investigated by liquid chromatography-tandem mass spectrometry (LC-MS/MS) and small RNA sequencing. ChGelMSC-Exo treatment significantly reduced mucosal contraction on day 21, with less fiber accumulation and inflammatory infiltration, and enhanced angiogenesis when compared with the control and ChGelPBS groups. The anti-fibrotic effects following MSC-Exo treatment were further found to be associated with the anti-inflammatory M2 polarization of the resident macrophages, especially within the M2b subset characterized by the reduced TGFß1 secretion, which sufficiently inhibited inflammation and prevented the activation of myofibroblast with less collagen production at the early stage after ESD. Moreover, the abundant expression of exosomal MFGE8 was identified to be involved in the transition of the M2b-macrophage subset through the activation of MFGE8/STAT3/Arg1 axis. CONCLUSIONS: Our study demonstrates that exosomal MFGE8 significantly promotes the polarization of the M2b-macrophage subset, consequently reducing collagen deposition. These findings suggest a promising potential for MSC-Exo therapy in preventing the development of esophageal stricture after near-circumferential ESD.

Curative endoscopic full-thickness resection of a fundic gland-type gastric adenocarcinoma.

Video 1Summary of the presented case. Macroscopic images of the lesion in a white-light endoscopy and narrow-band imaging and in an underwater view followed by scenes from the resection with circular marking, submucosal injection, circumferential incision, and submucosal dissection using a multi-bend double-channel endoscope, as well as clip traction, controlled full-thickness dissection, and inspection of the defect plus closure of the defect with the clip-and-loop technique.