Physics-Guided Deep Scatter Estimation by Weak Supervision for Quantitative SPECT

Accurate scatter estimation is important in quantitative SPECT for improving image contrast and accuracy. With a large number of photon histories, Monte-Carlo (MC) simulation can yield accurate scatter estimation, but is computationally expensive. Recent deep learning-based approaches can yield accurate scatter estimates quickly, yet full MC simulation is still required to generate scatter estimates as ground truth labels for all training data. Here we propose a physics-guided weakly supervised training framework for fast and accurate scatter estimation in quantitative SPECT by using a $100\times $ shorter MC simulation as weak labels and enhancing them with deep neural networks. Our weakly supervised approach also allows quick fine-tuning of the trained network to any new test data for further improved performance with an additional short MC simulation (weak label) for patient-specific scatter modelling. Our method was trained with 18 XCAT phantoms with diverse anatomies / activities and then was evaluated on 6 XCAT phantoms, 4 realistic virtual patient phantoms, 1 torso phantom and 3 clinical scans from 2 patients for 177Lu SPECT with single / dual photopeaks (113, 208 keV). Our proposed weakly supervised method yielded comparable performance to the supervised counterpart in phantom experiments, but with significantly reduced computation in labeling. Our proposed method with patient-specific fine-tuning achieved more accurate scatter estimates than the supervised method in clinical scans. Our method with physics-guided weak supervision enables accurate deep scatter estimation in quantitative SPECT, while requiring much lower computation in labeling, enabling patient-specific fine-tuning capability in testing.

I. Introduction

Quantitative single photon emission computed tomography (SPECT) is important for clinical applications including dosimetry-guided treatment planning [1], [2], [3] for optimization of therapies such as peptide receptor radionuclide therapy (PRRT) for the treatment of neuroendocrine tumors with ¹⁷⁷Lu-DOTATATE [4], or radioembolization with ⁹⁰Y microspheres for the treatment of liver malignancies [5]. Scattered photons detected within an energy window degrade SPECT image quality by reducing the contrast in the reconstructed images and introducing additional uncertainties on activity distributions [6]. Scatter estimation has been an active research area for several decades for improving the quality of SPECT images [7], [8], [9], [10], [11]. Scatter estimation methods can be divided into three categories [7]: 1) multiple energy window-based methods [12], 2) Monte-Carlo simulation-based methods [2], [13], [14], and 3) deep learning-based methods [15].