Automatic esophagus Z‐line delineation in endoscopic images using a new boundary linking method

Due to the American cancer society, many people with esophageal adenocarcinoma are not survived. The treatment rate can be significant in early detection of Barrett's esophagus (BE) as a premalignant stage for adenocarcinoma. An important landmark detect BE is Z-line. segmentation already highly dependent upon operator's knowledge and skill. main aim this study automatic Z-line extraction using endoscopic images leading stage. To end, computer-aided method exploiting k-means clustering, image edge detector, novel boundary linking algorithm proposed. For evaluation, gold standard considered average contours Z-lines extracted by three experts. proposed annotated accuracy precision 0.92 0.87, respectively, value distance 5.9 pixels. results visual inspection, presented used efficient robust at Furthermore, it other medical imaging applications complex boundaries low contrast images, limiting common methods.