A robust and versatile deep learning model for prediction of the arterial input function in dynamic small animal $left[^{18} ext{F} ight]$FDG PET imaging

2025-07-03

AI Summary

To address the invasiveness and non-repeatability of arterial blood sampling in dynamic [$^{18}$F]FDG PET imaging of small animals, this work proposes FC-DLIF—a fully convolutional deep learning model that enables non-invasive, image-only prediction of the arterial input function (AIF) for the first time. FC-DLIF jointly extracts spatiotemporal features and accommodates variable scan durations and temporal offsets, trained and cross-validated on multi-tracer dynamic PET data. Experiments demonstrate that FC-DLIF significantly outperforms existing methods in mean squared error and correlation metrics, and exhibits strong robustness to truncated and time-shifted data. Although cross-tracer generalization remains limited by training data coverage, FC-DLIF establishes the first high-accuracy, non-invasive, and flexible AIF estimation framework for longitudinal kinetic modeling in small-animal PET studies.

Technology Category

• Machine Learning: Life-Long and Continual Learning
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Dynamic positron emission tomography (PET) and kinetic modeling are pivotal in advancing tracer development research in small animal studies. Accurate kinetic modeling requires precise input function estimation, traditionally achieved via arterial blood sampling. However, arterial cannulation in small animals like mice, involves intricate, time-consuming, and terminal procedures, precluding longitudinal studies. This work proposes a non-invasive, fully convolutional deep learning-based approach (FC-DLIF) to predict input functions directly from PET imaging, potentially eliminating the need for blood sampling in dynamic small-animal PET. The proposed FC-DLIF model includes a spatial feature extractor acting on the volumetric time frames of the PET sequence, extracting spatial features. These are subsequently further processed in a temporal feature extractor that predicts the arterial input function. The proposed approach is trained and evaluated using images and arterial blood curves from [$^{18}$F]FDG data using cross validation. Further, the model applicability is evaluated on imaging data and arterial blood curves collected using two additional radiotracers ([$^{18}$F]FDOPA, and [$^{68}$Ga]PSMA). The model was further evaluated on data truncated and shifted in time, to simulate shorter, and shifted, PET scans. The proposed FC-DLIF model reliably predicts the arterial input function with respect to mean squared error and correlation. Furthermore, the FC-DLIF model is able to predict the arterial input function even from truncated and shifted samples. The model fails to predict the AIF from samples collected using different radiotracers, as these are not represented in the training data. Our deep learning-based input function offers a non-invasive and reliable alternative to arterial blood sampling, proving robust and flexible to temporal shifts and different scan durations.

Problem

• Non-invasive prediction of arterial input function in small animal PET
• Eliminates need for arterial blood sampling in dynamic PET imaging
• Handles temporal shifts and varying scan durations robustly

Innovation

• Non-invasive deep learning predicts arterial input function
• Convolutional model extracts spatial and temporal PET features
• Robust to temporal shifts and varied scan durations