Skip to content

loufay/Beyond-the-prompt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

108 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Beyond the Prompt: Deploying Medical Foundation Models on Diverse Chest X-ray Populations

Overview

Framework

Foundation models (FMs) have shown impressive performance in medical image analysis tasks, but their deployment in real-world clinical settings, especially across diverse patient populations such as adult and pediatric cases, remains challenging. Key open questions include optimal prompting techniques and strategies for model adaptation or fine-tuning for clinical use. In this study, we evaluated different approaches for deploying FMs in clinical scenarios for diverse patient populations. We use the lightweight, embedding-based vision-language FM \textit{MedImageInsight} to predict pneumonia from chest X-rays, a condition common in both adult and pediatric patients. We observed large variation in model predictive performance depending on the chosen prompt design, highlighting the importance of text prompt design for successful zero-shot (ZS) application. On in-domain datasets, we found performance differences of up to 15% in AUC across different text prompts. By introducing text and vision embedding ensembles, we achieved substantial ZS improvements, outperforming fine-tuning´with LoRA in low-data scenarios by up to 10% for adults and pediatric populations (AUC).

Paper

Read the full paper here.

Foundation Model

MedImageInsight (MI2)

More information about MedImageInsight.

Downloading MedImageInsight from Microsoft Azure.

Running MedImageInsight locally.

Datasets

MIMIC-CXR (in-domain, adult dataset)

CheXpert (out-of-domain, adult dataset)

VinDR-PCXR (out-of-domain, pediatric dataset)

Comparing FM

  • CheXagent
  • RAD-DINO
  • Biomed-CLIP

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors