Visual Question Answering for a Pediatric Radiology Workflow
Overview
What this challenge is about.
Fine-tune a VQA model on pediatric X-rays to answer yes/no questions with localization. You get a verifiable certificate.
The scenario
The startup (~22 staff, Series A, partnering with two pediatric hospital networks in New England) is targeting a Software-as-a-Medical-Device pathway; everything shipped now is research-grade only and must be reproducible.
The Brief
What you'll do, and what you'll demonstrate.
Build a VQA prototype on pediatric chest X-rays that hits per-category sensitivity ≥0.80 at specificity ≥0.85 with calibrated probabilities and per-question attention maps.
Earning criteria — what you'll demonstrate
- Adapt an open vision-language model to a clinical-style visual reasoning task with LoRA
- Measure calibration of a yes/no medical classifier with reliability diagrams and Expected Calibration Error
- Generate and qualitatively assess attention/saliency maps as explanation surfaces
- Communicate model limitations and dataset bias honestly to a non-ML clinical audience
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Aligned coursework coming soon.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Vision Language Models
Apply vision language models to solve real industry problems and demonstrate production-level capability.
- Visual Question Answering
Apply visual question answering to solve real industry problems and demonstrate production-level capability.
- Lora Finetuning
Apply lora finetuning to solve real industry problems and demonstrate production-level capability.
- Calibration
Apply calibration to solve real industry problems and demonstrate production-level capability.
- Evaluation
Apply evaluation to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
ML Researcher
Fine-tuning an open vision-language model on a domain task and writing a careful, calibrated evaluation is the foundational deliverable expected of a junior ML researcher in healthtech or any domain-specific AI team.
This challenge sharpens
- vision-language-models
- lora-finetuning
- calibration
Research Scientist
Reporting per-category sensitivity/specificity with reliability diagrams and explicit limitations mirrors the rigor expected in a research-scientist's first publication-ready evaluation.
This challenge sharpens
- evaluation
- calibration
- visual-question-answering
Applied AI Scientist
Translating a research-grade VQA evaluation into a board-ready advisory deck with honest limitations is daily work for applied AI scientists in regulated industries.
This challenge sharpens
- evaluation
- visual-question-answering
- pytorch