Combined Use of Computed Tomography Enterography/Enteroclysis and Capsule Endoscopy Improves the Accuracy of Diagnosis of Small Bowel Bleeding.

Objective CT enterography/enteroclysis (CTE) is listed in the clinical practice guidelines as a method for diagnosing small bowel bleeding, as is capsule endoscopy (CE), but there are no real-world data yet available on CTE in Japan. This study aimed to investigate the diagnostic ability of CTE and long-term prognosis after CTE in Japan. Patients We conducted a retrospective cohort study of patients suspected of having small bowel bleeding who underwent both CTE and CE within 30 days between April 2008 and March 2019. The number of patients free from rebleeding for up to 24 months was thus determined. Results Seventy-one patients were extracted from the database. The 43 patients (60.6%) with a definite and suspicious source of bleeding in the small bowel were detected by CTE. When the 31 patients with a definite source of bleeding in the small bowel were analyzed, the sensitivity of CTE was 19/31 (61.3%) and that of CE was 24/31 (77.4%), thus indicating no significant difference (p=0.332). However, the sensitivity when CTE and CE were used in combination was 30/31 (96.8%), which was significantly higher than that of CE alone (p=0.0412). No rebleeding was observed in the CTE and CE negative group (p=0.0965). Conclusion The combined use of CTE and CE increased the detection rate of small bowel bleeding. Therefore, in patients with suspected tumor/polyp lesions, not only CE, but also CTE should be performed. This study provides the first real-world data on the diagnostic accuracy of CTE for small bowel bleeding in Japan.

Objective Assessment of the Utility of Chromoendoscopy with a Support Vector Machine.

PURPOSE: The utility of chromoendoscopy for early gastric cancer (GC) was determined by machine learning using data of color differences. METHODS: Eighteen histopathologically confirmed early GC lesions were examined. We prepared images from white light endoscopy (WL), indigo carmine (Indigo), and acetic acid-indigo carmine chromoendoscopy (AIM). A border between cancerous and non-cancerous areas on endoscopic images was established from post-treatment pathological findings, and 2000 pixels with equivalent luminance values were randomly extracted from each image of cancerous and non-cancerous areas. Each pixel was represented as a three-dimensional vector with RGB values and defined as a sample. We evaluated the Mahalanobis distance using RGB values, indicative of color differences between cancerous and non-cancerous areas. We then conducted diagnosis test using a support vector machine (SVM) for each image. SVM was trained using the 100 training samples per class and determined which area each of 1900 test samples per class came from. RESULTS: The means of the Mahalanobis distances for WL, Indigo, and AIM were 1.52, 1.32, and 2.53, respectively and there were no significant differences in the three modalities. Diagnosability per endoscopy technique was assessed using the F1 measure. The means of F1 measures for WL, Indigo, and AIM were 0.636, 0.618, and 0.687, respectively. AIM images were better than WL and Indigo images for the diagnosis of GC. CONCLUSION: Objective assessment by SVM found AIM to be suitable for diagnosis of early GC based on color differences.