Back To Projects
Back To Projects

Curation of medical imaging experts for thyroid ultrasound annotation

SUPA used a 12,000+ medical expert network to recruit 50 registered practitioners skilled in medical imaging interpretation.

Problem statement

SUPA’s medical partners require medical specialists to annotate thyroid ultrasound images, many of which have limited available hours per day.

SOLUTION

SUPA leveraged its vast network of medical experts to attract, assess, and onboard qualified medical practitioners, managed through SUPA’s platform.

RESULT

50 qualified experts were recruited within 14 days, with 800 additional practitioners on the waitlist to address surge demand.

Overview

The Problem

As SUPA continues its engagement with leading healthcare providers in Southeast Asia, the Talent Acquisition team was tasked to recruit a team of medical practitioners to annotate thyroid ultrasound images.

The resulting images will be utilized to develop AI models that enhance diagnostic accuracy and improve physician efficiency. A highly skilled team is especially important, given the potential consequences of unreliable diagnosis.

The task required:

  • Access to a wide pool of qualified experts in medical imaging, including radiology
  • The ability to assess and manage a workforce with limited availability, given that most experts have full-time responsibilities 

The Solution

Recognising these requirements, SUPA’s talent acquisition team:

  1. Tapped into an extensive network of 12,000+ healthcare practitioners across Southeast Asia, attracting qualified experts with a strong interest in contributing to medical AI development.
  2. Shortlisted candidates through a series of task-based assessments and video interviews.
  3. Leveraged SUPA’s workforce management platform to design a workflow that guarantees steady annotation output, working around the 2-hours-a-day availability of medical experts.

The Result

Within 14 days, SUPA successfully recruited a team of 50 qualified experts, with an additional 800 experts waitlisted to handle any surge demand from our partners.

These practitioners were also trained on segmentation techniques, allowing them to be swiftly deployed for our Partners’ projects.

Why SUPA?

SUPA’s vast network of domain experts, combined with our experience in managing an on-demand, distributed workforce, puts us in an unmatched position to assemble teams to complete highly complex annotation projects.

Other Projects

Discover the work we do

View All
View All

SUPA’s strategic use of graphic design experts for generative model excellence

SUPA leveraged domain-specific talent to source and label 600k stylized vector images, solving data diversity challenges

problem
The client struggled to source and label 600,000 diverse vector images for training a stylistically versatile GenAI model, hampered by inconsistent vendor quality.
solution
SUPA rapidly scaled domain-expert graphic designers to curate, label, and sketch assets via iterative workflows and ML-aligned quality checks.
result
SUPA delivered the dataset in three months with only 3.5% rework, enabling a 37% FID score improvement in the client’s AI model for style-diverse outputs.
SUPA’s strategic use of graphic design experts for generative model excellence

Enhancing AR footwear try-on precision through high-quality segmentation

>99% accurate semantic segmentation data for ZERO10’s AR footwear try-on, enabling a precise, immersive user experience with rapid 5-week turnaround

problem
ZERO10 required enhanced precision in their footwear try-on models to deliver a more immersive and accurate AR user experience
solution
SUPA deployed its expert annotators, skilled in semantic segmentation, alongside its advanced labeling infrastructure, ensuring high-quality, scalable data annotation
result
ZERO10 successfully launched their advanced AR footwear try-on feature, powered by SUPA’s rapid delivery of segmentation datasets with >99% accuracy, enabling superior model performance and user experience
Enhancing AR footwear try-on precision through high-quality segmentation