Goblet cells segmentation from confocal laser endomicroscopy with an improved U-Net

Abstract

Gastric intestinal metaplasia (GIM) is regarded as a remarkable precursor
for the development of intestinal-type stomach cancer. Goblet cell (GC) segmentation
is the crucial step for assessing the degree of GIM by confocal laser endomicroscopy
(CLE). However, GC segmentation by hand is difficult, unreliable, and time consuming. Meanwhile, due to the high resolution and noise interference of CLE
images, existing segmentation approaches perform poorly on this task. To tackle those
issue, we collected 343 confocal laser endomicroscopy images of 62 patients from a
Grade-A tertiary hospital. Each CLE image is manually annotated and then verified
three times by skilled medical specialists. Then, U-Net is improved by incorporating
the pixel gradient attention mechanism, which focuses on color gradient information
around GC and captures color gradient features to direct feature maps in the skip
connection layer. At last, the model output vector is used to calculate the possibility
map and generate the final segmentation area. Compared with mainstream models,
GCSCLE performs the best segmentation result when tested on our CLE dataset and
achieved an IOU of 87.95% and a DICE of 86.64%. Our result shows, the performance
of the GCSCLE can be compared with the manual CLE image processing in clinical
settings, and it can improve segmentation accuracy and save time and costs.