Radiology Residents: Medical Image Evaluation for AI Benchmarks

What We're Researching

We're running a paid study on medical imaging diagnostics to build high-quality clinical reference benchmarks. This work directly supports the validation of advanced clinical tools by establishing reliable scoring rubrics based on expert reads. Your input will ensure these evaluations are grounded in rigorous, modern radiological practices.

How It Works

You will review a series of de-identified medical images and associated clinical cases through a secure remote platform. For each case, you will provide a detailed expert read and fill out specific scoring rubrics. The task involves evaluating findings, noting diagnostic certainty, and structuring your observations into a standardized reference format. All reviews are conducted asynchronously, allowing you to complete the evaluations at your own pace within the study window.

Who This Is For

We are looking for current radiology residents with strong clinical diagnostic skills. We welcome residents across all years of training, as well as those pursuing sub-specialty fellowships in areas like neuroradiology, musculoskeletal, or body imaging. Ideal participants are comfortable navigating digital diagnostic environments and articulating structured clinical findings.

What You'll Do

• Review de-identified medical images and patient clinical cases
• Provide structured expert reads for assigned clinical scenarios
• Complete standardized scoring rubrics to benchmark diagnostic findings
• Articulate diagnostic reasoning and clinical confidence levels clearly

Who Should Apply

• Current radiology resident or fellow
• Comfortable interpreting complex medical images and clinical case notes
• Familiar with standard diagnostic reporting formats and medical terminology
• Able to complete detailed analytical tasks independently in a remote setting

Compensation

$105 per task

Ready to participate?

Start your paid interview now

About Terac

Terac is building the world's largest pool of vetted human experts for AI. Researchers, AI labs, and product teams use Terac to recruit, screen, and pay study participants across industries, languages, and skill sets.