Flow Matching for 3D Craniofacial Skeletal Data Generation

Giacomo Melacini, Stefano Mazzocchetti, Giuseppe Lisanti, Luigi Di Stefano, Samuele Salti
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:1044-1064, 2026.

Abstract

In the medical domain, the use of Machine Learning (ML) techniques for diagnosis, treatment planning, and medical imaging interpretation is becoming increasingly important. However, these approaches require a large amount of data, which is challenging to access due to its sensitive nature and related privacy concerns. Synthetic data generation, enabled by advances in generative techniques, provides a solution to create large anonymized datasets for training models without compromising patient privacy. Recently, Flow Matching with Optimal Transport (OTFM) has proven to be an effective technique for generating realistic 2D natural images, surpassing existing methods, but its usage for 3D medical data generation is limited. In this work we generate craniofacial skeletal data using OTFM and test the validity of the results in two clinical downstream tasks: skull alignment and shape completion. Moreover, we compare the quality of synthetic data generated with OTFM with the ones generated using Denoising Diffusion Probabilistic Models (DDPMs). We show that Flow Matching with Optimal Transport is an effective technique for generating synthetic data and that, in this context, it outperforms DDPMs both in quality and robustness.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-melacini26a, title = {Flow Matching for 3D Craniofacial Skeletal Data Generation}, author = {Melacini, Giacomo and Mazzocchetti, Stefano and Lisanti, Giuseppe and Di Stefano, Luigi and Salti, Samuele}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {1044--1064}, 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/melacini26a/melacini26a.pdf}, url = {https://proceedings.mlr.press/v315/melacini26a.html}, abstract = {In the medical domain, the use of Machine Learning (ML) techniques for diagnosis, treatment planning, and medical imaging interpretation is becoming increasingly important. However, these approaches require a large amount of data, which is challenging to access due to its sensitive nature and related privacy concerns. Synthetic data generation, enabled by advances in generative techniques, provides a solution to create large anonymized datasets for training models without compromising patient privacy. Recently, Flow Matching with Optimal Transport (OTFM) has proven to be an effective technique for generating realistic 2D natural images, surpassing existing methods, but its usage for 3D medical data generation is limited. In this work we generate craniofacial skeletal data using OTFM and test the validity of the results in two clinical downstream tasks: skull alignment and shape completion. Moreover, we compare the quality of synthetic data generated with OTFM with the ones generated using Denoising Diffusion Probabilistic Models (DDPMs). We show that Flow Matching with Optimal Transport is an effective technique for generating synthetic data and that, in this context, it outperforms DDPMs both in quality and robustness.} }
Endnote
%0 Conference Paper %T Flow Matching for 3D Craniofacial Skeletal Data Generation %A Giacomo Melacini %A Stefano Mazzocchetti %A Giuseppe Lisanti %A Luigi Di Stefano %A Samuele Salti %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-melacini26a %I PMLR %P 1044--1064 %U https://proceedings.mlr.press/v315/melacini26a.html %V 315 %X In the medical domain, the use of Machine Learning (ML) techniques for diagnosis, treatment planning, and medical imaging interpretation is becoming increasingly important. However, these approaches require a large amount of data, which is challenging to access due to its sensitive nature and related privacy concerns. Synthetic data generation, enabled by advances in generative techniques, provides a solution to create large anonymized datasets for training models without compromising patient privacy. Recently, Flow Matching with Optimal Transport (OTFM) has proven to be an effective technique for generating realistic 2D natural images, surpassing existing methods, but its usage for 3D medical data generation is limited. In this work we generate craniofacial skeletal data using OTFM and test the validity of the results in two clinical downstream tasks: skull alignment and shape completion. Moreover, we compare the quality of synthetic data generated with OTFM with the ones generated using Denoising Diffusion Probabilistic Models (DDPMs). We show that Flow Matching with Optimal Transport is an effective technique for generating synthetic data and that, in this context, it outperforms DDPMs both in quality and robustness.
APA
Melacini, G., Mazzocchetti, S., Lisanti, G., Di Stefano, L. & Salti, S.. (2026). Flow Matching for 3D Craniofacial Skeletal Data Generation. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:1044-1064 Available from https://proceedings.mlr.press/v315/melacini26a.html.

Related Material