Iterative deep learning for improved segmentation of endoscopic images

Authors

  • Sharib Ali University of Oxford
  • Nikhil K Tomar NepAl Applied Mathematics and Informatics Institute for Research (NAAMII)

DOI:

https://doi.org/10.5617/nmi.9137

Keywords:

deep learning, segmentation, polyps, instruments, endoscopy

Abstract

Iterative segmentation is a unique way to prune the segmentation maps initialized by faster inference techniques or even unsupervised traditional thresholding methods. We used our previous feedback attention-based method for this work and demonstrate that with optimal iterative procedure our method can reach competitive accuracies in endoscopic imaging. For this work, we have applied this segmentation strategy for polyps and instruments.

Downloads

Published

2021-11-01