Machine Learning Creates a Simple Endoscopic Classification System that Improves Dysplasia Detection in Barrett’s Oesophagus amongst Non-expert Endoscopists

<div>Endoscopic appearances of different mucosal, microvascular patterns, and architecture of Barrett’s segment using i-Scan. Arrows denote particular areas of interest. (a) M1: regular circular, oval pits; (b) M1: villous/gyrus ridged pits; (c) M2: distorted, featureless mucosa with surface ulceration; (d) V1: regular uniform vessels; (e) V2: irregular, “corkscrew-like” vessels; (f) nodularity with surrounding distortion of the normal mucosal surface pattern.</div>

Gastroenterology Research and Practice

fig2

Figure 2

Figure 2: Machine Learning Creates a Simple Endoscopic Classification System that Improves Dysplasia Detection in Barrett’s Oesophagus amongst Non-expert Endoscopists 

Figure 2 | Machine Learning Creates a Simple Endoscopic Classification System that Improves Dysplasia Detection in Barrett’s Oesophagus amongst Non-expert Endoscopists 