Image-derived input functions for [18F]LW223 and [18F]SynVesT-1 PET in the rodent determined using an autoencoder (IDIF-AE).

Objective.Quantitative analysis of dynamic positron emission tomography (PET) scans requires knowledge of the arterial input function (AIF). Existing means of extracting the AIF are invasive and costly (continuous blood sampling), or come with significant errors (image-derived input function, IDIF). We present a novel image-derived AIF method using a machine learning technique that does not require external training data.Approach.Voxel-by-voxel time-activity curves are used as individual input samples for training a customised autoencoder (AE) machine learning model. AEs are models that map input samples to themselves, with an intermediate latent layer with few nodes. This drives the training algorithm to find an optimal bottleneck representation of the input. The IDIF is extracted from the weights of the trained model and normalised using a single timed blood sample.Main results.The method was evaluated on dynamic PET scans of rats with translocator protein tracer [18F]LW223. Volumes of distribution (VT) from arterial blood sampling (ground truth) were compared using Logan plots with IDIF-AE (mean absolute percentage error±32%) and conventional IDIF from left ventricle (±54%). The method was also successfully adapted for scans of mice with neuro PET tracer [18F]SynVesT-1.Significance.This study demonstrates a novel machine-learning based IDIF for dynamic PET that can outperform classical IDIFs in determining kinetic parameterVT, without requiring external training data.