An automatic annotation method for early esophageal cancers based on saliency guided superpixel segmentation

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

“…The value of $$Scor{e}_s$$ is obtained as 0.63 for this phase. The best results of EAC annotation in [33, 34] are achieved for large EAC regions. According to the results, the dice, recall, and precision values are 0.77, 0.75, and 0.77, respectively.…”

“…However, BE and EAC regions are more recognizable than the regions that suffer from early-stage Barrett (our case) due to their tissue deformation and/or colour changes. Therefore, the methods presented in [28][29][30][31][33][34][35][36] could not help annotate the Z-line in our dataset. Along with this reason, the deep learning-based methods provided in [13,18,32] cannot be suitable due to the difference in the quality of the images.…”

“…In this method, the cancerous region is assumed to be uniform area with a deformed texture. Early esophageal cancer segmentation is achieved by applying a super-pixel based segmentation method called simple linear iterative clustering (SLIC) on the low and high salient regions [33,34]. To this end, the local boundaries in the superpixels resulting from the ROI segmentation are extracted.…”

“…✓ Progressive BE and polyp are segmented so the method works when changes in tissue colour or texture have occurred. [33,34] ✓ EAC is segmented, so the method works when tissue colour or texture changes have occurred.…”