Generating Post-Acetazolamide Cerebral Blood Flow MRI for High-risk Stroke Patients

Rydham Goyal, Camila Gonzalez, Sasha Alexander, Aja Zou, Michael Moseley, Moss Zhao, Gary K Steinberg

Keywords: Generative models, Conditional Autoencoder, Pixel-space diffusion, Image-to-image translation, Arterial Spin Labeling, MRI, Cerebrovascular reserve

TL;DR: We show that a simple conditional autoencoder can synthesize post-acetazolamide CBF maps directly from baseline ASL, enabling drug-free estimation of cerebrovascular reserve in high-risk stroke patients.

Abstract: Cerebrovascular reserve (CVR) quantifies the brain’s ability to augment cerebral blood flow in response to a vasodilatory stimulus. It is a key biomarker in Moyamoya disease and other steno-occlusive cerebrovascular disorders. Clinically, CVR is typically assessed by administering acetazolamide (ACZ) and acquiring post-ACZ perfusion maps, but this workflow is time-consuming, costly, and contraindicated in a subset of patients. In this work, we investigate whether deep learning can predict post-ACZ perfusion directly from baseline arterial spin labeling (ASL) MRI, enabling pharmacologic-free CVR estimation. We curate a single-center dataset of Moyamoya ASL perfusion imaging, comprising pre/post-ACZ scan pairs from 194 patients. We design a post-ACZ conditional Autoencoder (cAE) network to regress the middle axial post-ACZ slice from the corresponding pre-ACZ slice using a combined L1 and SSIM loss. We evaluate our method against three diffusion-based formulations (conditional DDPM, Cold Diffusion, and Residual Diffusion). On a holdout test set of 49 patients, the proposed post-ACZ cAE achieves the highest reconstruction fidelity (SSIM ≈0.79), outperforming diffusion-based baselines in MAE, SSIM, and PSNR. Region-wise analysis of CBF percentage change in affected versus healthy MCA territories showed that the generated post-ACZ model outputs followed ground truth patterns of cerebrovascular reserve. Our findings demonstrate the feasibility of non-invasive CVR assessment using MRI for high-risk patients. Our data-driven approach could reduce reliance on ACZ challenges in routine clinical workflow and expand access to CVR testing to evaluate brain health.

Primary Subject Area: Generative Models

Secondary Subject Area: Application: Neuroimaging

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 368