MedVAE: Efficient Automated Interpretation of Medical Images with Large-Scale Generalizable Autoencoders

TL;DR

MedVAE introduces large-scale autoencoders that efficiently compress and reconstruct medical images, enabling faster downstream processing without losing clinically relevant details, demonstrated across diverse datasets.

Contribution

We develop MedVAE, a family of autoencoders trained on over one million images, enabling efficient image downsizing and high-fidelity reconstruction for medical imaging tasks.

Findings

Up to 70x throughput improvement in downstream models

Preservation of clinically relevant features during downsizing

High-fidelity image reconstruction from latent representations

Abstract

Medical images are acquired at high resolutions with large fields of view in order to capture fine-grained features necessary for clinical decision-making. Consequently, training deep learning models on medical images can incur large computational costs. In this work, we address the challenge of downsizing medical images in order to improve downstream computational efficiency while preserving clinically-relevant features. We introduce MedVAE, a family of six large-scale 2D and 3D autoencoders capable of encoding medical images as downsized latent representations and decoding latent representations back to high-resolution images. We train MedVAE autoencoders using a novel two-stage training approach with 1,052,730 medical images. Across diverse tasks obtained from 20 medical image datasets, we demonstrate that (1) utilizing MedVAE latent representations in place of high-resolution images when training downstream models can lead to efficiency benefits (up to 70x improvement in throughput) while simultaneously preserving clinically-relevant features and (2) MedVAE can decode latent representations back to high-resolution images with high fidelity. Our work demonstrates that large-scale, generalizable autoencoders can help address critical efficiency challenges in the medical domain. Our code is available at https://github.com/StanfordMIMI/MedVAE.