DeepAI AI Chat
Log In Sign Up

Brain MRI-to-PET Synthesis using 3D Convolutional Attention Networks

by   Ramy Hussein, et al.
Stanford University

Accurate quantification of cerebral blood flow (CBF) is essential for the diagnosis and assessment of a wide range of neurological diseases. Positron emission tomography (PET) with radiolabeled water (15O-water) is considered the gold-standard for the measurement of CBF in humans. PET imaging, however, is not widely available because of its prohibitive costs and use of short-lived radiopharmaceutical tracers that typically require onsite cyclotron production. Magnetic resonance imaging (MRI), in contrast, is more readily accessible and does not involve ionizing radiation. This study presents a convolutional encoder-decoder network with attention mechanisms to predict gold-standard 15O-water PET CBF from multi-sequence MRI scans, thereby eliminating the need for radioactive tracers. Inputs to the prediction model include several commonly used MRI sequences (T1-weighted, T2-FLAIR, and arterial spin labeling). The model was trained and validated using 5-fold cross-validation in a group of 126 subjects consisting of healthy controls and cerebrovascular disease patients, all of whom underwent simultaneous 15O-water PET/MRI. The results show that such a model can successfully synthesize high-quality PET CBF measurements (with an average SSIM of 0.924 and PSNR of 38.8 dB) and is more accurate compared to concurrent and previous PET synthesis methods. We also demonstrate the clinical significance of the proposed algorithm by evaluating the agreement for identifying the vascular territories with abnormally low CBF. Such methods may enable more widespread and accurate CBF evaluation in larger cohorts who cannot undergo PET imaging due to radiation concerns, lack of access, or logistic challenges.


page 1

page 5

page 6

page 10

page 11

page 15

page 16

page 18


Multi-task Deep Learning for Cerebrovascular Disease Classification and MRI-to-PET Translation

Accurate quantification of cerebral blood flow (CBF) is essential for th...

Deep Learning for Musculoskeletal Image Analysis

The diagnosis, prognosis, and treatment of patients with musculoskeletal...

Comparative Validation of AI and non-AI Methods in MRI Volumetry to Diagnose Parkinsonian Syndromes

Automated segmentation and volumetry of brain magnetic resonance imaging...

FREA-Unet: Frequency-aware U-net for Modality Transfer

While Positron emission tomography (PET) imaging has been widely used in...

DeepASL: Kinetic Model Incorporated Loss for Denoising Arterial Spin Labeled MRI via Deep Residual Learning

Arterial spin labeling (ASL) allows to quantify the cerebral blood flow ...