Background and study aims: Artificial intelligence (AI) is increasingly being used to detect neoplasia and interpret endoscopic images. The T stage of Barrett’s carcinoma is a major criterion for deciding on subsequent treatment. Although endoscopic ultrasound is still the standard for preoperative staging, its value is debatable. Novel tools are required to assist with staging, to optimize results. This study aimed to investigate correctly identified T stages of Barrett’s carcinoma using an artificial intelligence system, on the basis of endoscopic images. Patients and methods: 1020 images (minimum one per patient, maximum three) from 577 patients with Barrett’s adenocarcinoma were used for training and internal validation of a convolutional neuronal network. In all, 821 images were selected to train the model and 199 images were ultimately used for validation. Results: AI recognized Barrett’s mucosa without neoplasia with an accuracy of 85% (95% CI, 82.7–87.1). Mucosal cancer was identified with a sensitivity of 72% (95% CI, 67.5–76.4), specificity of 64% (95% CI, 60.0–68.4), and accuracy of 68% (95% CI, 64.6–70.7). The sensitivity, specificity, and accuracy for early Barrett’s neoplasia < T1b (sm2) were 57% (95% CI, 51.8–61.0), 77% (95% CI, 72.3–80.2), and 67% (95% CI, 63.4–69.5), respectively. More advanced stages (T3/T4) were diagnosed correctly with a sensitivity of 71% (95% CI, 65.1–76.7) and specificity of 73% (95% CI, 69.7–76.5). The overall accuracy was 73% (95% CI, 69.6–75.5). Conclusions: Clinically important decision-making on endoscopic therapy can be achieved with a high degree of certainty using artificial intelligence.

Background/Aims: Endoscopic therapy for neoplastic Barrett’s esophagus (BE) has become the standard of care over the past two decades. In clinical practice, we regularly encounter patients who fail to achieve complete squamous epithelialization of the esophagus. Although the therapeutic strategies in the individual stages of BE, dysplasia, and esophageal adenocarcinoma are well studied and largely standardized, the problem of inadequate healing after endoscopic therapy is only marginally considered. This study aimed to shed light on the variables influencing inadequate wound healing after endoscopic therapy and the effect of bile acid sequestrants (BAS) on healing.Methods: Retrospective analysis of endoscopically treated neoplastic BE in a single referral center.Results: In 12.1% out of 627 patients, insufficient healing was present 8 to 12 weeks after previous endoscopic therapy. The average follow-up duration was 38.8±18.4 months. Complete healing was achieved in 13 patients already after intensifying proton pump inhibitor therapy. Out of 48 patients under BAS, 29 patients (60.4%) showed complete healing. An additional eight patients (16.7%) improved, but only partial healing was achieved. Eleven (22.9%) patients showed no response to BAS augmented therapy.Conclusions: In cases of insufficient healing even under exhaustion of proton pump inhibitors, treatment with BAS can be an option as an ultimate healing attempt.

Purpose Early detection of adenocarcinomas in the esophagus is crucial for achieving curative endoscopic therapy. Targeted biopsies of suspicious lesions, as well as four-quadrant biopsies, represent the current diagnostic standard. However, this procedure is time-consuming, cost-intensive, and examiner-dependent. The aim of this study was to test whether impedance spectroscopy is capable of distinguishing between healthy, premalignant, and malignant lesions. An ex vivo measurement method was developed to examine esophageal lesions using impedance spectroscopy immediately after endoscopic resection. Methods After endoscopic resection of suspicious lesions in the esophagus, impedance measurements were performed on resected cork-covered tissue using a measuring head that was developed, with eight gold electrodes, over 10 different measurement settings and with frequencies from 100 Hz to 1 MHz. Results A total of 105 measurements were performed in 60 patients. A dataset of 400 per investigation and a total of more than 42,000 impedance measurements were therefore collected. Electrical impedance spectroscopy (EIS) was able to detect dysplastic esophageal mucosa with a sensitivity of 81% in Barrett’s esophagus. Conclusion In summary, EIS was able to distinguish different tissue characteristics in the different esophageal tissues. EIS thus holds potential for further development of targeted biopsies during surveillance endoscopy. Trial Registration NCT04046601

No abstract