MerMED-FM: Multimodal, Multi-Disease Medical Imaging Foundation Model.

AI / informaticsThe Lancet. Digital health· 2027

MerMED-FM: Multimodal, Multi-Disease Medical Imaging Foundation Model.

Yang Zhou, Chrystie Wan Ning Quek, Jun Zhou … Daniel Shu Wei Ting

Read paper

OphthalmologyAI / informaticsQ1IF 14.4

MerMED-FM showed excellent diagnostic accuracy for optical coherence tomography.

MerMED-FM: Multimodal, Multi-Disease Medical Imaging Foundation Model.

Yang Zhou … Daniel Shu Wei Ting

The Lancet · 2027 · Q1 in General Medicine

Background

Current artificial intelligence (artificial intelligence) models for medical imaging predominantly focus on a single imaging modality and a single disease.

Purpose

We aimed to train and evaluate an artificial intelligence model that can interpret diverse imaging modalities across specialties while maintaining robust performance within each modality.

Methods

We developed Multimodal, Multi-Disease Medical Imaging Foundation Model (MerMED-FM), a multi-specialty model trained using self-supervised learning and a memory module.

n = around 3·3 million images

Results

0·962 for OCT

MerMED-FM was very accurate at diagnosing diseases using eye scans

n = around 3·3 million images

More results

MerMED-FM was trained on around 3·3 million images from 53 publicly available, unlabelled datasets, comprising 713 931 chest x-rays, 292 353 CT slices, 389 885 ultrasound frames, 1 017 712 pathology patches, 333 099 colour fundus photography images, 176 719 optical coherence tomography slices, and 401 059 dermatoscopy images.

“

Conclusion

MerMED-FM has the potential to be a highly adaptable, versatile, cross-specialty foundation model that enables robust interpretation of medical imaging across diverse medical disciplines.

MerMED-FM: Multimodal, Multi-Disease Medical Imaging Foundation Model.

MerMED-FM: Multimodal, Multi-Disease Medical Imaging Foundation Model.

Related papers