Synthesizing Post-Acetazolamide Cerebral Blood Flow Maps from Baseline MRI in Moyamoya Using 3D Generative AI

Julia Huang, Camila Gonzalez, Rydham Goyal, Aja Zou, Sasha Alexander, Michael Moseley, Moss Y. Zhao, Gary K. Steinberg
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:611-635, 2026.

Abstract

For patients with Moyamoya disease, impaired cerebrovascular reserve (CVR) is an important hemodynamic criterion for recommending extracranial-to-intracranial bypass surgery, making reliable CVR assessment central to treatment planning. The reference protocol used in this cohort requires paired arterial spin labeling (ASL) perfusion MRI acquired before and after administration of the vasodilator acetazolamide (ACZ). ACZ may be contraindicated or avoided in patients with substantial renal dysfunction, relevant hypersensitivity, marked electrolyte derangement, or pregnancy, depending on clinical circumstances and institutional protocol. For affected patients in whom ACZ is not administered, the standard two-scan protocol cannot be completed as intended, and the post-ACZ cerebral blood flow (CBF) data used for hemodynamic assessment and bypass planning are unavailable. We propose CAE3D, a deterministic 3D conditional autoencoder that synthesizes post-ACZ CBF maps directly from pre-ACZ ASL input. Among eleven evaluated models (CAE3D, seven directly comparable full-volume in-house baselines spanning deterministic and diffusion-style variants, one middle-slice 2D contextual baseline (CAE 2D), and two frozen-encoder foundation adapters reported separately as contextual references), CAE3D achieves the lowest held-out MAE (MAE 0.066, SSIM 0.80, PSNR 24.0 dB) with near-zero full-brain mean bias, though its regional $\Delta$CBF predictions compress the dynamic range in high-response territories. Its MAE advantage was statistically significant (paired Wilcoxon, Holm-adjusted) over seven of the eight other trained-from-scratch baselines, with the exception of the 2D middle-slice CAE 2D comparator; its SSIM and PSNR advantages were significant over all eight. These results establish the retrospective feasibility of post-ACZ CBF synthesis in patients who completed the standard two-scan protocol; extension to ACZ-contraindicated patients, who were not represented in this cohort, awaits external and prospective validation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-huang26b, title = {Synthesizing Post-Acetazolamide Cerebral Blood Flow Maps from Baseline MRI in Moyamoya Using 3D Generative AI}, author = {Huang, Julia and Gonzalez, Camila and Goyal, Rydham and Zou, Aja and Alexander, Sasha and Moseley, Michael and Zhao, Moss Y. and Steinberg, Gary K.}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {611--635}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/huang26b/huang26b.pdf}, url = {https://proceedings.mlr.press/v340/huang26b.html}, abstract = {For patients with Moyamoya disease, impaired cerebrovascular reserve (CVR) is an important hemodynamic criterion for recommending extracranial-to-intracranial bypass surgery, making reliable CVR assessment central to treatment planning. The reference protocol used in this cohort requires paired arterial spin labeling (ASL) perfusion MRI acquired before and after administration of the vasodilator acetazolamide (ACZ). ACZ may be contraindicated or avoided in patients with substantial renal dysfunction, relevant hypersensitivity, marked electrolyte derangement, or pregnancy, depending on clinical circumstances and institutional protocol. For affected patients in whom ACZ is not administered, the standard two-scan protocol cannot be completed as intended, and the post-ACZ cerebral blood flow (CBF) data used for hemodynamic assessment and bypass planning are unavailable. We propose CAE3D, a deterministic 3D conditional autoencoder that synthesizes post-ACZ CBF maps directly from pre-ACZ ASL input. Among eleven evaluated models (CAE3D, seven directly comparable full-volume in-house baselines spanning deterministic and diffusion-style variants, one middle-slice 2D contextual baseline (CAE 2D), and two frozen-encoder foundation adapters reported separately as contextual references), CAE3D achieves the lowest held-out MAE (MAE 0.066, SSIM 0.80, PSNR 24.0 dB) with near-zero full-brain mean bias, though its regional $\Delta$CBF predictions compress the dynamic range in high-response territories. Its MAE advantage was statistically significant (paired Wilcoxon, Holm-adjusted) over seven of the eight other trained-from-scratch baselines, with the exception of the 2D middle-slice CAE 2D comparator; its SSIM and PSNR advantages were significant over all eight. These results establish the retrospective feasibility of post-ACZ CBF synthesis in patients who completed the standard two-scan protocol; extension to ACZ-contraindicated patients, who were not represented in this cohort, awaits external and prospective validation.} }
Endnote
%0 Conference Paper %T Synthesizing Post-Acetazolamide Cerebral Blood Flow Maps from Baseline MRI in Moyamoya Using 3D Generative AI %A Julia Huang %A Camila Gonzalez %A Rydham Goyal %A Aja Zou %A Sasha Alexander %A Michael Moseley %A Moss Y. Zhao %A Gary K. Steinberg %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-huang26b %I PMLR %P 611--635 %U https://proceedings.mlr.press/v340/huang26b.html %V 340 %X For patients with Moyamoya disease, impaired cerebrovascular reserve (CVR) is an important hemodynamic criterion for recommending extracranial-to-intracranial bypass surgery, making reliable CVR assessment central to treatment planning. The reference protocol used in this cohort requires paired arterial spin labeling (ASL) perfusion MRI acquired before and after administration of the vasodilator acetazolamide (ACZ). ACZ may be contraindicated or avoided in patients with substantial renal dysfunction, relevant hypersensitivity, marked electrolyte derangement, or pregnancy, depending on clinical circumstances and institutional protocol. For affected patients in whom ACZ is not administered, the standard two-scan protocol cannot be completed as intended, and the post-ACZ cerebral blood flow (CBF) data used for hemodynamic assessment and bypass planning are unavailable. We propose CAE3D, a deterministic 3D conditional autoencoder that synthesizes post-ACZ CBF maps directly from pre-ACZ ASL input. Among eleven evaluated models (CAE3D, seven directly comparable full-volume in-house baselines spanning deterministic and diffusion-style variants, one middle-slice 2D contextual baseline (CAE 2D), and two frozen-encoder foundation adapters reported separately as contextual references), CAE3D achieves the lowest held-out MAE (MAE 0.066, SSIM 0.80, PSNR 24.0 dB) with near-zero full-brain mean bias, though its regional $\Delta$CBF predictions compress the dynamic range in high-response territories. Its MAE advantage was statistically significant (paired Wilcoxon, Holm-adjusted) over seven of the eight other trained-from-scratch baselines, with the exception of the 2D middle-slice CAE 2D comparator; its SSIM and PSNR advantages were significant over all eight. These results establish the retrospective feasibility of post-ACZ CBF synthesis in patients who completed the standard two-scan protocol; extension to ACZ-contraindicated patients, who were not represented in this cohort, awaits external and prospective validation.
APA
Huang, J., Gonzalez, C., Goyal, R., Zou, A., Alexander, S., Moseley, M., Zhao, M.Y. & Steinberg, G.K.. (2026). Synthesizing Post-Acetazolamide Cerebral Blood Flow Maps from Baseline MRI in Moyamoya Using 3D Generative AI. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:611-635 Available from https://proceedings.mlr.press/v340/huang26b.html.

Related Material