Ulrik Stig Hansen
Published December 16, 2022•Edited May 18, 2023• 3 min read
6x Faster Video Annotation for King's College London
King's College London used Encord to achieve a 6.4x average increase in labeling efficiency for GI videos.
Using clinicians to annotate pre-cancerous polyp videos had prohibitively high costs to produce large datasets.
Deployed Encord's micro-model module to increase clinician labeling efficiency and automate 97% of produced labels.
The highest-expense clinician saw a 16x labeling efficiency improvement. Cut model development time from 1 year to 2 months.
- 6.4X faster than manual labeling
- 97% automated labels
- 6X faster to AI in production