A new study has concluded that deep learning convolutional neural network (CNN) architecture to facilitate more objective, reproducible endoscopic assessment of ulcerative colitis (UC) is a promising technology (Scientific Reports2022 Feb 17. https://doi.org/10.1038/s41598-022-06726-2).
The researchers noted that endoscopic evaluation to reliably grade disease activity, detect complications—including cancer—and verify mucosal healing is needed to properly care for patients with UC. However, such evaluation is stymied by substantial intra- and interobserver variability.