MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields

Paul Friedrich, Florentin Bieder, Julian McGinnis, Julia Wolleb, Daniel Rueckert, Philippe C. Cattin
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:56-87, 2026.

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 $>500k$ latent vectors for multi-instance medical NFs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-friedrich26a, title = {MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields}, author = {Friedrich, Paul and Bieder, Florentin and McGinnis, Julian and Wolleb, Julia and Rueckert, Daniel and Cattin, Philippe C.}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {56--87}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/friedrich26a/friedrich26a.pdf}, url = {https://proceedings.mlr.press/v315/friedrich26a.html}, 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 $>500k$ latent vectors for multi-instance medical NFs. } }
Endnote
%0 Conference Paper %T MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields %A Paul Friedrich %A Florentin Bieder %A Julian McGinnis %A Julia Wolleb %A Daniel Rueckert %A Philippe C. Cattin %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-friedrich26a %I PMLR %P 56--87 %U https://proceedings.mlr.press/v315/friedrich26a.html %V 315 %X 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 $>500k$ latent vectors for multi-instance medical NFs.
APA
Friedrich, P., Bieder, F., McGinnis, J., Wolleb, J., Rueckert, D. & Cattin, P.C.. (2026). MedFuncta: A Unified Framework for Learning Efficient Medical Neural Fields. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:56-87 Available from https://proceedings.mlr.press/v315/friedrich26a.html.

Related Material