Arterial Input Function

Arterial input function (AIF) determination is crucial for accurately quantifying tissue perfusion and metabolism in medical imaging, particularly in PET and MRI. Current research focuses on developing robust and automated methods for AIF extraction, moving away from invasive techniques towards non-invasive approaches using deep learning models like U-Nets and Recurrent Neural Networks, or physics-informed CycleGANs. These advancements aim to improve the efficiency, accuracy, and accessibility of quantitative imaging analysis, ultimately leading to better diagnostic and treatment planning in various clinical applications. The development of efficient algorithms, such as graph neural networks, further enhances the speed and feasibility of AIF estimation.

Papers

February 5, 2024

An end-to-end deep learning pipeline to derive blood input with partial volume corrections for automated parametric brain PET mapping
Rugved Chavan, Gabriel Hyman, Zoraiz Qureshi, Nivetha Jayakumar, William Terrell, Stuart Berr, David Schiff, Megan Wardius, Nathan Fountain, Thomas Muttikkal, Mark Quigg, Miaomiao Zhang, Bijoy Kundu
End to End Pipeline System Non Invasive Arterial Input Function

June 7, 2023

Unpaired Deep Learning for Pharmacokinetic Parameter Estimation from Dynamic Contrast-Enhanced MRI
Gyutaek Oh, Won-Jin Moon, Jong Chul Ye
Unpaired Data Dce Mri Pharmacokinetic Parameter Arterial Input Function

March 4, 2023

Detection of the Arterial Input Function Using DSC-MRI Data
Svitlana Alkhimova, Kateryna Sazonova
Data Detection Contrast Enhanced Magnetic Resonance Imaging Perfusion Parameter Arterial Input Function

February 17, 2023

SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets
Julian Suk, Christoph Brune, Jelmer M. Wolterink
Neural Network Graph Drawing Small Datasets Cyclic Symmetry Velocity Field Hemodynamic Analysis Arterial Input Function

Arterial Input Function

Papers

An end-to-end deep learning pipeline to derive blood input with partial volume corrections for automated parametric brain PET mapping

Unpaired Deep Learning for Pharmacokinetic Parameter Estimation from Dynamic Contrast-Enhanced MRI

Detection of the Arterial Input Function Using DSC-MRI Data

SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets