Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis

Salman Shaik, Hung Truong Thanh Nguyen, Hung Cao
Proceedings of the The 39th Canadian Conference on Artificial Intelligence, PMLR 318:319-331, 2026.

Abstract

Accurate classification of diffuse gliomas is often hindered by domain shifts across centers and a lack of large, annotated datasets. We propose the Anatomically-conditioned Latent Diffusion Model (ALDM), a novel framework for data-efficient, few-shot 3D volumetric MRI synthesis. ALDM utilizes a two-stage approach: a 3D variational autoencoder learns anatomical priors from a data-rich source domain, while a conditional latent diffusion model, guided by tumor masks via a ControlNet, generates structurally coherent volumes for a data-scarce target domain. Evaluated in an extreme few-shot setting with only 16 target images, ALDM outperformed GAN and hybrid baselines, achieving a superior Fréchet Inception Distance (FID) of 85.40 and a downstream classification AUC of 0.987. Qualitative results confirm that the model preserves sharp pathology boundaries and cross-modal consistency, with visual fidelity improving progressively during training. By capturing essential diagnostic features, ALDM provides a robust tool for clinical data augmentation in low-resource settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v318-shaik26a, title = {Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis}, author = {Shaik, Salman and Nguyen, Hung Truong Thanh and Cao, Hung}, booktitle = {Proceedings of the The 39th Canadian Conference on Artificial Intelligence}, pages = {319--331}, year = {2026}, editor = {Bouzar-Benlabiod, Lydia and Leung, Carson}, volume = {318}, series = {Proceedings of Machine Learning Research}, month = {25--29 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v318/main/assets/shaik26a/shaik26a.pdf}, url = {https://proceedings.mlr.press/v318/shaik26a.html}, abstract = {Accurate classification of diffuse gliomas is often hindered by domain shifts across centers and a lack of large, annotated datasets. We propose the Anatomically-conditioned Latent Diffusion Model (ALDM), a novel framework for data-efficient, few-shot 3D volumetric MRI synthesis. ALDM utilizes a two-stage approach: a 3D variational autoencoder learns anatomical priors from a data-rich source domain, while a conditional latent diffusion model, guided by tumor masks via a ControlNet, generates structurally coherent volumes for a data-scarce target domain. Evaluated in an extreme few-shot setting with only 16 target images, ALDM outperformed GAN and hybrid baselines, achieving a superior Fréchet Inception Distance (FID) of 85.40 and a downstream classification AUC of 0.987. Qualitative results confirm that the model preserves sharp pathology boundaries and cross-modal consistency, with visual fidelity improving progressively during training. By capturing essential diagnostic features, ALDM provides a robust tool for clinical data augmentation in low-resource settings.} }
Endnote
%0 Conference Paper %T Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis %A Salman Shaik %A Hung Truong Thanh Nguyen %A Hung Cao %B Proceedings of the The 39th Canadian Conference on Artificial Intelligence %C Proceedings of Machine Learning Research %D 2026 %E Lydia Bouzar-Benlabiod %E Carson Leung %F pmlr-v318-shaik26a %I PMLR %P 319--331 %U https://proceedings.mlr.press/v318/shaik26a.html %V 318 %X Accurate classification of diffuse gliomas is often hindered by domain shifts across centers and a lack of large, annotated datasets. We propose the Anatomically-conditioned Latent Diffusion Model (ALDM), a novel framework for data-efficient, few-shot 3D volumetric MRI synthesis. ALDM utilizes a two-stage approach: a 3D variational autoencoder learns anatomical priors from a data-rich source domain, while a conditional latent diffusion model, guided by tumor masks via a ControlNet, generates structurally coherent volumes for a data-scarce target domain. Evaluated in an extreme few-shot setting with only 16 target images, ALDM outperformed GAN and hybrid baselines, achieving a superior Fréchet Inception Distance (FID) of 85.40 and a downstream classification AUC of 0.987. Qualitative results confirm that the model preserves sharp pathology boundaries and cross-modal consistency, with visual fidelity improving progressively during training. By capturing essential diagnostic features, ALDM provides a robust tool for clinical data augmentation in low-resource settings.
APA
Shaik, S., Nguyen, H.T.T. & Cao, H.. (2026). Anatomically-conditioned Latent Diffusion Model for Data-Efficient Few-Shot Cross-Domain 3D Glioma MRI Synthesis. Proceedings of the The 39th Canadian Conference on Artificial Intelligence, in Proceedings of Machine Learning Research 318:319-331 Available from https://proceedings.mlr.press/v318/shaik26a.html.

Related Material