Quote of the day

What we know is a drop, what we don't know is an ocean.

- Isaac Newton

Contact

Uncertainty-Aware Edge AI for Chest Radiograph Screening in Primary Care Settings

Open Medicine & Healthcare

Uncertainty-Aware Edge AI for Chest Radiograph Screening in Primary Care Settings

Uncertainty-Aware Edge AI for Chest Radiograph Screening in Primary Care Settings

Description

Develop an edge-deployable chest-radiograph pre-screening model that detects out-of-distribution cases and explicitly refers uncertain images to a radiologist.

Details

Context and Problem Statement

Chest-radiography AI can support regions with limited radiology capacity, but performance may degrade on older equipment, poor exposures, image artifacts, or population shifts. Silent degradation is clinically unsafe.

Research Question

Which out-of-distribution detection method can reliably identify images on which an embedded screening model should not make a prediction under strict computational constraints?

Proposed Approach

Train a compact model through knowledge distillation, add uncertainty mechanisms such as small ensembles, Monte-Carlo dropout, and energy scores, and evaluate under simulated acquisition and population shifts.

Expected Contribution

A rigorous comparison of OOD detection methods under edge constraints using safety-oriented metrics.

Expected Prototype

A low-cost offline pre-screening station that prioritizes cases and flags images requiring mandatory radiologist review.

Datasets

CheXpert, NIH ChestX-ray14, and a deliberately constructed OOD test set.

Challenges

Device shift, false negatives, lack of prospective validation, regulation, and preservation of clinician authority.

Research Question

Can an embedded chest-radiograph screening system reliably detect cases outside its competence, and does this capability reduce clinical risk?

Innovation

The project explicitly couples strict edge-computing constraints with out-of-distribution detection.

Expected Deliverable

A pre-screening station prototype, an evaluation protocol under distribution shift, and a clinical risk-analysis report.

Technologies

Edge AI and Model Quantization Out-of-Distribution Detection Medical Vision and Knowledge Distillation Uncertainty Quantification Explainable AI

Required Skills

  • Computer Vision and Medical Imaging
  • Embedded Optimization and Deployment
  • Uncertainty Quantification
  • Medical-Device Regulation Fundamentals

Datasets

  • CheXpert
  • NIH ChestX-ray14
  • Locally constructed out-of-distribution evaluation set

Morocco & Africa Relevance

Many rural health centers in Morocco and Africa have radiography equipment without on-site radiologists, making reliable offline triage valuable.