data_entry_ops · healthcare · workflow
Intuitive Surgical doubles labeled dataset delivery speed for robotic surgery ML models using Labelbox
Intuitive Surgical's data science team was bottlenecked by the need to annotate tens of thousands of surgical videos frame-by-frame — a tedious, time-consuming process — while also ensuring all labeled data adhered to a consistent ontology across clinical and data science teams.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Surgical video annotation need
Frame-by-frame bounding box annotation of tens of thousands of surgical videos creates the need for an efficient labeling pipeline.
Tools used
LabelboxAnnotate
Outcome
By adopting Labelbox, Intuitive Surgical doubled the speed of labeled dataset delivery for their ML models, scaled labeling efficiency and throughput, and lowered overhead for gathering quality and performance metrics.
Grounding & classification
Source type: vendor customer story
20 fields verified against source quotes.
computer visionquality inspectionhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhealthcareemployee productivitythroughput increasetime savedvendor customer storydata entry opsquality assurancehuman review queue