Automatic detection of arterial input function for brain DCE-MRI in multi-site cohorts.

Arterial input function (AIF) extraction is a crucial step in quantitative pharmacokinetic modeling of DCE-MRI. This work proposes a robust deep learning model that can precisely extract an AIF from DCE-MRI images. A diverse dataset of human brain DCE-MRI images from 289 participants, totaling 384 scans, from five different institutions with extracted gadolinium-based contrast agent curves from large penetrating arteries, and with most data collected for blood-brain barrier (BBB) permeability measurement, was retrospectively analyzed. A 3D UNet model was implemented and trained on manually drawn AIF regions. The testing cohort was compared using proposed AIF quality metric AIFitness and Ktrans values from a standard DCE pipeline. This UNet was then applied to a separate dataset of 326 participants with a total of 421 DCE-MRI images with analyzed AIF quality and Ktrans values. The resulting 3D UNet model achieved an average AIFitness score of 93.9 compared to 99.7 for manually selected AIFs, and white matter Ktrans values were 0.45/min × 10-3 and 0.45/min × 10-3, respectively. The intraclass correlation between automated and manual Ktrans values was 0.89. The separate replication dataset yielded an AIFitness score of 97.0 and white matter Ktrans of 0.44/min × 10-3. Findings suggest a 3D UNet model with additional convolutional neural network kernels and a modified Huber loss function achieves superior performance for identifying AIF curves from DCE-MRI in a diverse multi-center cohort. AIFitness scores and DCE-MRI-derived metrics, such as Ktrans maps, showed no significant differences in gray and white matter between manually drawn and automated AIFs.