MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields

TL;DR

MedFuncta introduces a scalable, unified neural field framework for large-scale medical data, enabling continuous signal modeling, improved generalization, and efficient training, demonstrated across diverse datasets.

Contribution

The paper presents MedFuncta, a novel framework that extends neural fields to large-scale medical datasets using a unified representation and meta-learning strategies.

Findings

Effective modeling of diverse medical signals as continuous functions.

Reduced memory and computational requirements with sparse supervision.

Competitive performance on various downstream medical tasks.

Abstract

Research in medical imaging primarily focuses on discrete data representations that poorly scale with grid resolution and fail to capture the often continuous nature of the underlying signal. Neural Fields (NFs) offer a powerful alternative by modeling data as continuous functions. While single-instance NFs have successfully been applied in medical contexts, extending them to large-scale medical datasets remains an open challenge. We therefore introduce MedFuncta, a unified framework for large-scale NF training on diverse medical signals. Building on Functa, our approach encodes data into a unified representation, namely a 1D latent vector, that modulates a shared, meta-learned NF, enabling generalization across a dataset. We revisit common design choices, introducing a non-constant frequency parameter $\omega$ in widely used SIREN activations, and establish a connection between this $\omega$-schedule and layer-wise learning rates, relating our findings to recent work in theoretical learning dynamics. We additionally introduce a scalable meta-learning strategy for shared network learning that employs sparse supervision during training, thereby reducing memory consumption and computational overhead while maintaining competitive performance. Finally, we evaluate MedFuncta across a diverse range of medical datasets and show how to solve relevant downstream tasks on our neural data representation. To promote further research in this direction, we release our code, model weights and the first large-scale dataset - MedNF - containing > 500 k latent vectors for multi-instance medical NFs.